Search Results for author: Yang Wang

Found 262 papers, 65 papers with code

Geometric Estimation via Robust Subspace Recovery

1 code implementation ECCV 2020 Aoxiang Fan, Xingyu Jiang, Yang Wang, Junjun Jiang, Jiayi Ma

Geometric estimation from image point correspondences is the core procedure of many 3D vision problems, which is prevalently accomplished by random sampling techniques.

Homography Estimation Pose Estimation

Lightweight Embeddings for Graph Collaborative Filtering

1 code implementation27 Mar 2024 Xurong Liang, Tong Chen, Lizhen Cui, Yang Wang, Meng Wang, Hongzhi Yin

Graph neural networks (GNNs) are currently one of the most performant collaborative filtering methods.

FairSTG: Countering performance heterogeneity via collaborative sample-level optimization

no code implementations19 Mar 2024 Gengyu Lin, Zhengyang Zhou, Qihe Huang, Kuo Yang, Shifen Cheng, Yang Wang

To fix this gap, we propose a model-independent Fairness-aware framework for SpatioTemporal Graph learning (FairSTG), which inherits the idea of exploiting advantages of well-learned samples to challenging ones with collaborative mix-up.

Fairness Graph Learning +1

RL in Markov Games with Independent Function Approximation: Improved Sample Complexity Bound under the Local Access Model

no code implementations18 Mar 2024 Junyi Fan, Yuxuan Han, Jialin Zeng, Jian-Feng Cai, Yang Wang, Yang Xiang, Jiheng Zhang

Up to a logarithmic dependence on the size of the state space, Lin-Confident-FTRL learns $\epsilon$-CCE with a provable optimal accuracy bound $O(\epsilon^{-2})$ and gets rids of the linear dependency on the action space, while scaling polynomially with relevant problem parameters (such as the number of agents and time horizon).

Spatio-Temporal Fluid Dynamics Modeling via Physical-Awareness and Parameter Diffusion Guidance

no code implementations18 Mar 2024 Hao Wu, Fan Xu, Yifan Duan, Ziwei Niu, Weiyan Wang, Gaofeng Lu, Kun Wang, Yuxuan Liang, Yang Wang

This paper proposes a two-stage framework named ST-PAD for spatio-temporal fluid dynamics modeling in the field of earth sciences, aiming to achieve high-precision simulation and prediction of fluid dynamics through spatio-temporal physics awareness and parameter diffusion guidance.

Quantization

LAN: Learning Adaptive Neighbors for Real-Time Insider Threat Detection

1 code implementation14 Mar 2024 Xiangrui Cai, Yang Wang, Sihan Xu, Hao Li, Ying Zhang, Zheli Liu, Xiaojie Yuan

Moreover, LAN can be also applied to post-hoc ITD, surpassing 8 competitive baselines by at least 7. 70% and 4. 03% in AUC on two datasets.

Anomaly Detection Graph structure learning

RulePrompt: Weakly Supervised Text Classification with Prompting PLMs and Self-Iterative Logical Rules

1 code implementation5 Mar 2024 Miaomiao Li, Jiaqi Zhu, Yang Wang, Yi Yang, Yilin Li, Hongan Wang

Weakly supervised text classification (WSTC), also called zero-shot or dataless text classification, has attracted increasing attention due to its applicability in classifying a mass of texts within the dynamic and open Web environment, since it requires only a limited set of seed words (label names) for each category instead of labeled data.

Pseudo Label text-classification +1

ComS2T: A complementary spatiotemporal learning system for data-adaptive model evolution

no code implementations4 Mar 2024 Zhengyang Zhou, Qihe Huang, Binwu Wang, Jianpeng Hou, Kuo Yang, Yuxuan Liang, Yang Wang

Motivated by complementary learning in neuroscience, we introduce a prompt-based complementary spatiotemporal learning termed ComS2T, to empower the evolution of models for data adaptation.

Hippocampus

DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models

no code implementations19 Feb 2024 Xiaoyu Tian, Junru Gu, Bailin Li, Yicheng Liu, Chenxu Hu, Yang Wang, Kun Zhan, Peng Jia, Xianpeng Lang, Hang Zhao

We introduce DriveVLM, an autonomous driving system leveraging Vision-Language Models (VLMs) for enhanced scene understanding and planning capabilities.

Autonomous Driving Scene Understanding

Can We Verify Step by Step for Incorrect Answer Detection?

1 code implementation16 Feb 2024 Xin Xu, Shizhe Diao, Can Yang, Yang Wang

Chain-of-Thought (CoT) prompting has marked a significant advancement in enhancing the reasoning capabilities of large language models (LLMs).

Both Matter: Enhancing the Emotional Intelligence of Large Language Models without Compromising the General Intelligence

no code implementations15 Feb 2024 Weixiang Zhao, Zhuojun Li, Shilong Wang, Yang Wang, Yulin Hu, Yanyan Zhao, Chen Wei, Bing Qin

Emotional Intelligence (EI), consisting of emotion perception, emotion cognition and emotion expression, plays the critical roles in improving user interaction experience for the current large language model (LLM) based conversational general AI assistants.

Emotional Intelligence Language Modelling +1

Modeling Spatio-temporal Dynamical Systems with Neural Discrete Learning and Levels-of-Experts

no code implementations6 Feb 2024 Kun Wang, Hao Wu, Guibin Zhang, Junfeng Fang, Yuxuan Liang, Yuankai Wu, Roger Zimmermann, Yang Wang

In this paper, we address the issue of modeling and estimating changes in the state of the spatio-temporal dynamical systems based on a sequence of observations like video frames.

Optical Flow Estimation

One Graph Model for Cross-domain Dynamic Link Prediction

no code implementations3 Feb 2024 Xuanwen Huang, Wei Chow, Yang Wang, Ziwei Chai, Chunping Wang, Lei Chen, Yang Yang

Extensive experiments on eight untrained graphs demonstrate that DyExpert achieves state-of-the-art performance in cross-domain link prediction.

Dynamic Link Prediction

Distance-aware Attention Reshaping: Enhance Generalization of Neural Solver for Large-scale Vehicle Routing Problems

no code implementations13 Jan 2024 Yang Wang, Ya-Hui Jia, Wei-neng Chen, Yi Mei

To address this issue, this paper proposes a distance-aware attention reshaping method, assisting neural solvers in solving large-scale vehicle routing problems.

Lightweight Adaptive Feature De-drifting for Compressed Image Classification

no code implementations3 Jan 2024 Long Peng, Yang Cao, Yuejin Sun, Yang Wang

However, it is not an ideal choice to use these JPEG artifact removal methods as a pre-processing for compressed image classification for the following reasons: 1.

Classification Image Classification +1

Test-Time Personalization with Meta Prompt for Gaze Estimation

1 code implementation3 Jan 2024 Huan Liu, Julia Qi, Zhenhao Li, Mohammad Hassanpour, Yang Wang, Konstantinos Plataniotis, Yuanhao Yu

Despite the recent remarkable achievement in gaze estimation, efficient and accurate personalization of gaze estimation without labels is a practical problem but rarely touched on in the literature.

Gaze Estimation

BEV-CLIP: Multi-modal BEV Retrieval Methodology for Complex Scene in Autonomous Driving

no code implementations2 Jan 2024 Dafeng Wei, Tian Gao, Zhengyu Jia, Changwei Cai, Chengkai Hou, Peng Jia, Fu Liu, Kun Zhan, Jingchen Fan, Yixing Zhao, Yang Wang

The demand for the retrieval of complex scene data in autonomous driving is increasing, especially as passenger vehicles have been equipped with the ability to navigate urban settings, with the imperative to address long-tail scenarios.

Autonomous Driving Descriptive +6

Test-Time Domain Adaptation by Learning Domain-Aware Batch Normalization

1 code implementation15 Dec 2023 Yanan Wu, Zhixiang Chi, Yang Wang, Konstantinos N. Plataniotis, Songhe Feng

In this work, we propose to reduce such learning interference and elevate the domain knowledge learning by only manipulating the BN layer.

Domain Adaptation Meta-Learning +1

Open Set Dandelion Network for IoT Intrusion Detection

no code implementations19 Nov 2023 Jiashu Wu, Hao Dai, Kenneth B. Kent, Jerome Yen, Chengzhong Xu, Yang Wang

The OSDN model performs intrusion knowledge transfer from the knowledge-rich source network intrusion domain to facilitate more accurate intrusion detection for the data-scarce target IoT intrusion domain.

Domain Adaptation Intrusion Detection +1

Rethinking and Benchmarking Predict-then-Optimize Paradigm for Combinatorial Optimization Problems

no code implementations13 Nov 2023 Haoyu Geng, Hang Ruan, Runzhong Wang, Yang Li, Yang Wang, Lei Chen, Junchi Yan

Numerous web applications rely on solving combinatorial optimization problems, such as energy cost-aware scheduling, budget allocation on web advertising, and graph matching on social networks.

Benchmarking Combinatorial Optimization +3

Enhancing Traffic Object Detection in Variable Illumination with RGB-Event Fusion

no code implementations1 Nov 2023 Zhanwen Liu, Nan Yang, Yang Wang, Yuke Li, Xiangmo Zhao, Fei-Yue Wang

To address this issue, we introduce bio-inspired event cameras and propose a novel Structure-aware Fusion Network (SFNet) that extracts sharp and complete object structures from the event stream to compensate for the lost information in images through cross-modality fusion, enabling the network to obtain illumination-robust representations for traffic object detection.

Object object-detection +2

MCE: Mixed Cantonese and English Audio Dataset

no code implementations27 Oct 2023 Peng Xie, Zihao Xin, Yang Wang, Shengjun Huang, Tsz Wai Chan, Kani Chen

We proposed a novel evaluation metric called FAL, which assesses an Automatic Speech Recognition (ASR) system based on fidelity to the original audio, accuracy, and latency.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay

1 code implementation23 Oct 2023 Yihuai Lan, Zhiqiang Hu, Lei Wang, Yang Wang, Deheng Ye, Peilin Zhao, Ee-Peng Lim, Hui Xiong, Hao Wang

To achieve this goal, we adopt Avalon, a representative communication game, as the environment and use system prompts to guide LLM agents to play the game.

The Distributional Impact of Inflation in Pakistan: A Case Study of a New Price Focused Microsimulation Framework, PRICES

no code implementations30 Sep 2023 Cathal ODonoghue, Beenish Amjad, Jules Linden, Nora Lustig, Denisa Sologon, Yang Wang

The secondary purpose is to demonstrate one component of the model by assessing the distributional and welfare impact of recent price changes in Pakistan.

FG-NeRF: Flow-GAN based Probabilistic Neural Radiance Field for Independence-Assumption-Free Uncertainty Estimation

no code implementations28 Sep 2023 Songlin Wei, Jiazhao Zhang, Yang Wang, Fanbo Xiang, Hao Su, He Wang

Existing works rely on the independence assumption of points in the radiance field or the pixels in input views to obtain tractable forms of the probability density function.

Audio Contrastive based Fine-tuning

no code implementations21 Sep 2023 Yang Wang, Qibin Liang, Chenghao Xiao, Yizhi Li, Noura Al Moubayed, Chenghua Lin

Audio classification plays a crucial role in speech and sound processing tasks with a wide range of applications.

Audio Classification Contrastive Learning

Test-Time Adaptation for Point Cloud Upsampling Using Meta-Learning

no code implementations31 Aug 2023 Ahmed Hatem, Yiming Qian, Yang Wang

During meta-testing, the trained model is fine-tuned with a few gradient updates to produce a unique set of network parameters for each test instance.

Meta-Learning Test-time Adaptation

Building explainable graph neural network by sparse learning for the drug-protein binding prediction

1 code implementation27 Aug 2023 Yang Wang, Zanyu Shi, Timothy Richardson, Kun Huang, Pathum Weerawarna, Yijie Wang

Due to the use of the chemical-substructure-based graph, it is guaranteed that any subgraphs in a drug identified by our SLGNN are chemically valid structures.

Sparse Learning valid

Efficient Learned Lossless JPEG Recompression

no code implementations25 Aug 2023 Lina Guo, Yuanyuan Wang, Tongda Xu, Jixiang Luo, Dailan He, Zhenjun Ji, Shanshan Wang, Yang Wang, Hongwei Qin

Second, we propose pipeline parallel context model (PPCM) and compressed checkerboard context model (CCCM) for the effective conditional modeling and efficient decoding within luma and chroma components.

Image Compression Quantization

Attention-Based Acoustic Feature Fusion Network for Depression Detection

1 code implementation24 Aug 2023 Xiao Xu, Yang Wang, Xinru Wei, Fei Wang, Xizhe Zhang

To rectify this, we present the novel Attention-Based Acoustic Feature Fusion Network (ABAFnet) for depression detection.

Depression Detection

The Snowflake Hypothesis: Training Deep GNN with One Node One Receptive field

no code implementations19 Aug 2023 Kun Wang, Guohao Li, Shilong Wang, Guibin Zhang, Kai Wang, Yang You, Xiaojiang Peng, Yuxuan Liang, Yang Wang

Despite Graph Neural Networks demonstrating considerable promise in graph representation learning tasks, GNNs predominantly face significant issues with over-fitting and over-smoothing as they go deeper as models of computer vision realm.

Graph Representation Learning

ARAI-MVSNet: A multi-view stereo depth estimation network with adaptive depth range and depth interval

no code implementations17 Aug 2023 Song Zhang, Wenjia Xu, Zhiwei Wei, Lili Zhang, Yang Wang, Junyi Liu

Moreover, our method also achieves the lowest $e_{1}$ and $e_{3}$ on the BlendedMVS dataset and the highest Acc and $F_{1}$-score on the ETH 3D dataset, surpassing all listed methods. Project website: https://github. com/zs670980918/ARAI-MVSNet

Stereo Depth Estimation

Replace Scoring with Arrangement: A Contextual Set-to-Arrangement Framework for Learning-to-Rank

no code implementations5 Aug 2023 Jiarui Jin, Xianyu Chen, Weinan Zhang, Mengyue Yang, Yang Wang, Yali Du, Yong Yu, Jun Wang

Notice that these ranking metrics do not consider the effects of the contextual dependence among the items in the list, we design a new family of simulation-based ranking metrics, where existing metrics can be regarded as special cases.

Learning-To-Rank

Towards Robust Probabilistic Modeling on SO(3) via Rotation Laplace Distribution

no code implementations17 May 2023 Yingda Yin, Jiangran Lyu, Yang Wang, He Wang, Baoquan Chen

With this benefit, we demonstrate its advantages in semi-supervised rotation regression, where the pseudo labels are noisy.

regression

Semantic-Aware Graph Matching Mechanism for Multi-Label Image Recognition

1 code implementation21 Apr 2023 Yanan Wu, Songhe Feng, Yang Wang

In this paper, we treat each image as a bag of instances, and formulate the task of multi-label image recognition as an instance-label matching selection problem.

Few-Shot Learning Graph Matching

Inferring High-level Geographical Concepts via Knowledge Graph and Multi-scale Data Integration: A Case Study of C-shaped Building Pattern Recognition

no code implementations19 Apr 2023 Zhiwei Wei, Yi Xiao, Wenjia Xu, Mi Shu, Lu Cheng, Yang Wang, Chunbo Liu

To improve efficiency and effectiveness, we integrate multi-scale data using a knowledge graph, focusing on the recognition of C-shaped building patterns.

Data Integration

Delving into Discrete Normalizing Flows on SO(3) Manifold for Probabilistic Rotation Modeling

1 code implementation CVPR 2023 Yulin Liu, Haoran Liu, Yingda Yin, Yang Wang, Baoquan Chen, He Wang

Normalizing flows (NFs) provide a powerful tool to construct an expressive distribution by a sequence of trackable transformations of a base distribution and form a probabilistic model of underlying data.

E-MLB: Multilevel Benchmark for Event-Based Camera Denoising

1 code implementation21 Mar 2023 Saizhe Ding, Jinze Chen, Yang Wang, Yu Kang, Weiguo Song, Jie Cheng, Yang Cao

Event cameras, such as dynamic vision sensors (DVS), are biologically inspired vision sensors that have advanced over conventional cameras in high dynamic range, low latency and low power consumption, showing great application potential in many fields.

Denoising

Adaptive Data-Free Quantization

1 code implementation CVPR 2023 Biao Qian, Yang Wang, Richang Hong, Meng Wang

Data-free quantization (DFQ) recovers the performance of quantized network (Q) without the original data, but generates the fake sample via a generator (G) by learning from full-precision network (P), which, however, is totally independent of Q, overlooking the adaptability of the knowledge from generated samples, i. e., informative or not to the learning process of Q, resulting into the overflow of generalization error.

Data Free Quantization

A Laplace-inspired Distribution on SO(3) for Probabilistic Rotation Estimation

no code implementations3 Mar 2023 Yingda Yin, Yang Wang, He Wang, Baoquan Chen

Rotation Laplace distribution is robust to the disturbance of outliers and enforces much gradient to the low-error region, resulting in a better convergence.

regression

Rethinking Data-Free Quantization as a Zero-Sum Game

1 code implementation19 Feb 2023 Biao Qian, Yang Wang, Richang Hong, Meng Wang

how to generate the samples with desirable adaptability to benefit the quantized network?

Data Free Quantization

Fine-grained Cross-modal Fusion based Refinement for Text-to-Image Synthesis

1 code implementation17 Feb 2023 Haoran Sun, Yang Wang, Haipeng Liu, Biao Qian

The proposed FF-Block integrates an attention block and several convolution layers to effectively fuse the fine-grained word-context features into the corresponding visual features, in which the text information is fully used to refine the initial image with more details.

Image Generation

Convergence Analysis of the Deep Galerkin Method for Weak Solutions

no code implementations5 Feb 2023 Yuling Jiao, Yanming Lai, Yang Wang, Haizhao Yang, Yunfei Yang

This paper analyzes the convergence rate of a deep Galerkin method for the weak solution (DGMW) of second-order elliptic partial differential equations on $\mathbb{R}^d$ with Dirichlet, Neumann, and Robin boundary conditions, respectively.

Graph-Free Learning in Graph-Structured Data: A More Efficient and Accurate Spatiotemporal Learning Perspective

no code implementations27 Jan 2023 Xu Wang, Pengfei Gu, Pengkun Wang, Binwu Wang, Zhengyang Zhou, Lei Bai, Yang Wang

In this paper, with extensive and deep-going experiments, we comprehensively analyze existing spatiotemporal graph learning models and reveal that extracting adjacency matrices with carefully design strategies, which are viewed as the key of enhancing performance on graph learning, are largely ineffective.

Graph Learning

Heterogeneous Domain Adaptation for IoT Intrusion Detection: A Geometric Graph Alignment Approach

no code implementations24 Jan 2023 Jiashu Wu, Hao Dai, Yang Wang, Kejiang Ye, Chengzhong Xu

In this paper, a Geometric Graph Alignment (GGA) approach is leveraged to mask the geometric heterogeneities between domains for better intrusion knowledge transfer.

Domain Adaptation Network Intrusion Detection +2

Decoupling-and-Aggregating for Image Exposure Correction

no code implementations CVPR 2023 Yang Wang, Long Peng, Liang Li, Yang Cao, Zheng-Jun Zha

To this end, we inject the addition/difference operation into the convolution process and devise a Contrast Aware (CA) unit and a Detail Aware (DA) unit to facilitate the statistical and structural regularities modeling.

An interpretable imbalanced semi-supervised deep learning framework for improving differential diagnosis of skin diseases

no code implementations20 Nov 2022 Futian Weng, Yuanting Ma, Jinghan Sun, Shijun Shan, Qiyuan Li, Jianping Zhu, Yang Wang, Yan Xu

This paper presents the first study of the interpretability and imbalanced semi-supervised learning of the multiclass intelligent skin diagnosis framework (ISDL) using 58, 457 skin images with 10, 857 unlabeled samples.

Specificity

Multi-Scenario Bimetric-Balanced IoT Resource Allocation: An Evolutionary Approach

no code implementations10 Nov 2022 Jiashu Wu, Hao Dai, Yang Wang, Zhiying Tu

In this paper, we allocate IoT devices as resources for smart services with time-constrained resource requirements.

A Joint Framework Towards Class-aware and Class-agnostic Alignment for Few-shot Segmentation

no code implementations2 Nov 2022 Kai Huang, Mingfei Cheng, Yang Wang, Bochen Wang, Ye Xi, Feigege Wang, Peng Chen

Few-shot segmentation (FSS) aims to segment objects of unseen classes given only a few annotated support images.

Segmentation

Joint Semantic Transfer Network for IoT Intrusion Detection

no code implementations28 Oct 2022 Jiashu Wu, Yang Wang, Binhui Xie, Shuang Li, Hao Dai, Kejiang Ye, Chengzhong Xu

The scenario semantic endows source NI and II domain with characteristics from each other to ease the knowledge transfer process via a confused domain discriminator and categorical distribution knowledge preservation.

Computational Efficiency Domain Adaptation +3

Video Summarization Overview

no code implementations21 Oct 2022 Mayu Otani, Yale Song, Yang Wang

With the broad growth of video capturing devices and applications on the web, it is more demanding to provide desired video content for users efficiently.

Video Summarization

Optimal Contextual Bandits with Knapsacks under Realizability via Regression Oracles

1 code implementation21 Oct 2022 Yuxuan Han, Jialin Zeng, Yang Wang, Yang Xiang, Jiheng Zhang

We study the stochastic contextual bandit with knapsacks (CBwK) problem, where each action, taken upon a context, not only leads to a random reward but also costs a random resource consumption in a vector form.

Multi-Armed Bandits regression

Few-Shot Learning of Compact Models via Task-Specific Meta Distillation

no code implementations18 Oct 2022 Yong Wu, Shekhor Chanda, Mehrdad Hosseinzadeh, Zhi Liu, Yang Wang

In this paper, we propose task-specific meta distillation that simultaneously learns two models in meta-learning: a large teacher model and a small student model.

Few-Shot Image Classification Few-Shot Learning

HQNAS: Auto CNN deployment framework for joint quantization and architecture search

no code implementations16 Oct 2022 Hongjiang Chen, Yang Wang, Leibo Liu, Shaojun Wei, Shouyi Yin

Deep learning applications are being transferred from the cloud to edge with the rapid development of embedded computing systems.

Neural Architecture Search Quantization

FAQS: Communication-efficient Federate DNN Architecture and Quantization Co-Search for personalized Hardware-aware Preferences

no code implementations16 Oct 2022 Hongjiang Chen, Yang Wang, Leibo Liu, Shaojun Wei, Shouyi Yin

Due to user privacy and regulatory restrictions, federate learning (FL) is proposed as a distributed learning framework for training deep neural networks (DNN) on decentralized data clients.

Neural Architecture Search Quantization

Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-Experts

1 code implementation8 Oct 2022 Tao Zhong, Zhixiang Chi, Li Gu, Yang Wang, Yuanhao Yu, Jin Tang

Most existing methods perform training on multiple source domains using a single model, and the same trained model is used on all unseen target domains.

Domain Generalization Knowledge Distillation +3

Hierarchical Few-Shot Object Detection: Problem, Benchmark and Method

1 code implementation8 Oct 2022 Lu Zhang, Yang Wang, Jiaogen Zhou, Chenbo Zhang, Yinglu Zhang, Jihong Guan, Yatao Bian, Shuigeng Zhou

In this paper, we propose and solve a new problem called hierarchical few-shot object detection (Hi-FSOD), which aims to detect objects with hierarchical categories in the FSOD paradigm.

Contrastive Learning Few-Shot Object Detection +2

Spatio-Temporal Contrastive Learning Enhanced GNNs for Session-based Recommendation

1 code implementation23 Sep 2022 Zhongwei Wan, Xin Liu, Benyou Wang, Jiezhong Qiu, Boyu Li, Ting Guo, Guangyong Chen, Yang Wang

The idea is to supplement the GNN-based main supervised recommendation task with the temporal representation via an auxiliary cross-view contrastive learning mechanism.

Collaborative Filtering Contrastive Learning +1

Delving Globally into Texture and Structure for Image Inpainting

1 code implementation17 Sep 2022 Haipeng Liu, Yang Wang, Meng Wang, Yong Rui

Our model is orthogonal to the fashionable arts, such as Convolutional Neural Networks (CNNs), Attention and Transformer model, from the perspective of texture and structure information for image inpainting.

Image Inpainting

Switchable Online Knowledge Distillation

1 code implementation12 Sep 2022 Biao Qian, Yang Wang, Hongzhi Yin, Richang Hong, Meng Wang

Instead of focusing on the accuracy gap at test phase by the existing arts, the core idea of SwitOKD is to adaptively calibrate the gap at training phase, namely distillation gap, via a switching strategy between two modes -- expert mode (pause the teacher while keep the student learning) and learning mode (restart the teacher).

Knowledge Distillation

Towards Learning in Grey Spatiotemporal Systems: A Prophet to Non-consecutive Spatiotemporal Dynamics

no code implementations17 Aug 2022 Zhengyang Zhou, Yang Kuo, Wei Sun, Binwu Wang, Min Zhou, Yunan Zong, Yang Wang

To infer region-wise proximity under flexible factor-wise combinations and enable dynamic neighborhood aggregations, we further disentangle compounded influences of exogenous factors on region-wise proximity and learn to aggregate them.

Uncertainty Quantification

Grasping Core Rules of Time Series through Pure Models

no code implementations15 Aug 2022 Gedi Liu, Yifeng Jiang, Yi Ouyang, Keyang Zhong, Yang Wang

Time series underwent the transition from statistics to deep learning, as did many other machine learning fields.

Time Series Time Series Analysis

Instance Image Retrieval by Learning Purely From Within the Dataset

no code implementations12 Aug 2022 Zhongyan Zhang, Lei Wang, Yang Wang, Luping Zhou, Jianjia Zhang, Peng Wang, Fang Chen

Although achieving promising results, this approach is restricted by two issues: 1) the domain gap between benchmark datasets and the dataset of a given retrieval task; 2) the required auxiliary dataset cannot be readily obtained.

Image Retrieval Retrieval +2

Trajectory Tracking Control of the Bionic Joint Actuated by Pneumatic Artificial Muscle Based on Robust Modeling

no code implementations10 Aug 2022 Yang Wang, Qiang Zhang, Xiao-hui Xiao

Then, a hybrid model is established based on the two models (the nonlinear model and the LTI model) and corresponding to it, a cascaded controller is developed, the outer loop of which is an H-infinite controller for the angular position tracking designed by loop-shaping design procedure (LSDP) and the inner loop is a nonlinear controller based on the feedback linearization theory for the PAM driving pressure control.

Position

PECCO: A Profit and Cost-oriented Computation Offloading Scheme in Edge-Cloud Environment with Improved Moth-flame Optimisation

no code implementations9 Aug 2022 Jiashu Wu, Hao Dai, Yang Wang, Shigen Shen, Chengzhong Xu

With the fast growing quantity of data generated by smart devices and the exponential surge of processing demand in the Internet of Things (IoT) era, the resource-rich cloud centres have been utilised to tackle these challenges.

De-biased Representation Learning for Fairness with Unreliable Labels

no code implementations1 Aug 2022 Yixuan Zhang, Feng Zhou, Zhidong Li, Yang Wang, Fang Chen

In other words, the fair pre-processing methods ignore the discrimination encoded in the labels either during the learning procedure or the evaluation stage.

Fairness Representation Learning

Learning Resolution-Adaptive Representations for Cross-Resolution Person Re-Identification

no code implementations9 Jul 2022 Lin Wu, Lingqiao Liu, Yang Wang, Zheng Zhang, Farid Boussaid, Mohammed Bennamoun

It is a challenging and practical problem since the query images often suffer from resolution degradation due to the different capturing conditions from real-world cameras.

Person Re-Identification Super-Resolution

DGraph: A Large-Scale Financial Dataset for Graph Anomaly Detection

no code implementations30 Jun 2022 Xuanwen Huang, Yang Yang, Yang Wang, Chunping Wang, Zhisheng Zhang, Jiarong Xu, Lei Chen, Michalis Vazirgiannis

Since GAD emphasizes the application and the rarity of anomalous samples, enriching the varieties of its datasets is fundamental work.

Graph Anomaly Detection

Improving Visual Speech Enhancement Network by Learning Audio-visual Affinity with Multi-head Attention

no code implementations30 Jun 2022 Xinmeng Xu, Yang Wang, Jie Jia, Binbin Chen, Dejun Li

The proposed model alleviates these drawbacks by a) applying a model that fuses audio and visual features layer by layer in encoding phase, and that feeds fused audio-visual features to each corresponding decoder layer, and more importantly, b) introducing a 2-stage multi-head cross attention (MHCA) mechanism to infer audio-visual speech enhancement for balancing the fused audio-visual features and eliminating irrelevant features.

Speech Enhancement

On Private Online Convex Optimization: Optimal Algorithms in $\ell_p$-Geometry and High Dimensional Contextual Bandits

1 code implementation16 Jun 2022 Yuxuan Han, Zhicong Liang, Zhipeng Liang, Yang Wang, Yuan YAO, Jiheng Zhang

To address such a challenge as the online convex optimization with privacy protection, we propose a private variant of online Frank-Wolfe algorithm with recursive gradients for variance reduction to update and reveal the parameters upon each data.

Multi-Armed Bandits

Transformer-Empowered 6G Intelligent Networks: From Massive MIMO Processing to Semantic Communication

no code implementations8 May 2022 Yang Wang, Zhen Gao, Dezhi Zheng, Sheng Chen, Deniz Gündüz, H. Vincent Poor

It is anticipated that 6G wireless networks will accelerate the convergence of the physical and cyber worlds and enable a paradigm-shift in the way we deploy and exploit communication networks.

Thinking inside The Box: Learning Hypercube Representations for Group Recommendation

1 code implementation6 Apr 2022 Tong Chen, Hongzhi Yin, Jing Long, Quoc Viet Hung Nguyen, Yang Wang, Meng Wang

Such user and group preferences are commonly represented as points in the vector space (i. e., embeddings), where multiple user embeddings are compressed into one to facilitate ranking for group-item pairs.

Decision Making

BigDL 2.0: Seamless Scaling of AI Pipelines from Laptops to Distributed Cluster

1 code implementation CVPR 2022 Jason Dai, Ding Ding, Dongjie Shi, Shengsheng Huang, Jiao Wang, Xin Qiu, Kai Huang, Guoqiong Song, Yang Wang, Qiyuan Gong, Jiaming Song, Shan Yu, Le Zheng, Yina Chen, Junwei Deng, Ge Song

To address this challenge, we have open sourced BigDL 2. 0 at https://github. com/intel-analytics/BigDL/ under Apache 2. 0 license (combining the original BigDL and Analytics Zoo projects); using BigDL 2. 0, users can simply build conventional Python notebooks on their laptops (with possible AutoML support), which can then be transparently accelerated on a single node (with up-to 9. 6x speedup in our experiments), and seamlessly scaled out to a large cluster (across several hundreds servers in real-world use cases).

AutoML Distributed Computing +1

Recent Few-Shot Object Detection Algorithms: A Survey with Performance Comparison

no code implementations27 Mar 2022 Tianying Liu, Lu Zhang, Yang Wang, Jihong Guan, Yanwei Fu, Jiajia Zhao, Shuigeng Zhou

To this end, the Few-Shot Object Detection (FSOD) has been topical recently, as it mimics the humans' ability of learning to learn, and intelligently transfers the learned generic object knowledge from the common heavy-tailed, to the novel long-tailed object classes.

Few-Shot Object Detection Meta-Learning +3

ProgressiveMotionSeg: Mutually Reinforced Framework for Event-Based Motion Segmentation

no code implementations22 Mar 2022 Jinze Chen, Yang Wang, Yang Cao, Feng Wu, Zheng-Jun Zha

Dynamic Vision Sensor (DVS) can asynchronously output the events reflecting apparent motion of objects with microsecond resolution, and shows great application potential in monitoring and other fields.

Denoising Motion Estimation +1

S-Rocket: Selective Random Convolution Kernels for Time Series Classification

1 code implementation7 Mar 2022 Hojjat Salehinejad, Yang Wang, Yuanhao Yu, Tang Jin, Shahrokh Valaee

A population-based optimization algorithm evolves the population in order to find a best state vector which minimizes the number of active kernels while maximizing the accuracy of the classifier.

Combinatorial Optimization regression +3

When Does A Spectral Graph Neural Network Fail in Node Classification?

no code implementations16 Feb 2022 Zhixian Chen, Tengfei Ma, Yang Wang

Although graph filters provide theoretical foundations for model explanations, it is unclear when a spectral GNN will fail.

Graph Learning Node Classification

Approximation bounds for norm constrained neural networks with applications to regression and GANs

no code implementations24 Jan 2022 Yuling Jiao, Yang Wang, Yunfei Yang

This paper studies the approximation capacity of ReLU neural networks with norm constraint on the weights.

regression

MetaFSCIL: A Meta-Learning Approach for Few-Shot Class Incremental Learning

no code implementations CVPR 2022 Zhixiang Chi, Li Gu, Huan Liu, Yang Wang, Yuanhao Yu, Jin Tang

The learning objective of these methods is often hand-engineered and is not directly tied to the objective (i. e. incrementally learning new classes) during testing.

Few-Shot Class-Incremental Learning Incremental Learning +1

Dreaming To Prune Image Deraining Networks

no code implementations CVPR 2022 Weiqi Zou, Yang Wang, Xueyang Fu, Yang Cao

It is based on our observation that deep degradation representations can be clustered by degradation characteristics (types of rain) while independent of image content.

Model Compression Rain Removal

Multi-Grained Spatio-Temporal Features Perceived Network for Event-Based Lip-Reading

no code implementations CVPR 2022 Ganchao Tan, Yang Wang, Han Han, Yang Cao, Feng Wu, Zheng-Jun Zha

To recognize words from the event data, we propose a novel Multi-grained Spatio-Temporal Features Perceived Network (MSTP) to perceive fine-grained spatio-temporal features from microsecond time-resolved event data.

Action Recognition Lip Reading

Exposure Normalization and Compensation for Multiple-Exposure Correction

no code implementations CVPR 2022 Jie Huang, Yajing Liu, Xueyang Fu, Man Zhou, Yang Wang, Feng Zhao, Zhiwei Xiong

However, the procedures of correcting underexposure and overexposure to normal exposures are much different from each other, leading to large discrepancies for the network in correcting multiple exposures, thus resulting in poor performance.

Image Enhancement

Contrastive Learning for Unsupervised Video Highlight Detection

no code implementations CVPR 2022 Taivanbat Badamdorj, Mrigank Rochan, Yang Wang, Li Cheng

Our framework encodes a video into a vector representation by learning to pick video clips that help to distinguish it from other videos via a contrastive objective using dropout noise.

Contrastive Learning Highlight Detection

Self-supervised Spatiotemporal Representation Learning by Exploiting Video Continuity

no code implementations11 Dec 2021 Hanwen Liang, Niamul Quader, Zhixiang Chi, Lizhe Chen, Peng Dai, Juwei Lu, Yang Wang

Recent self-supervised video representation learning methods have found significant success by exploring essential properties of videos, e. g. speed, temporal order, etc.

Action Localization Action Recognition +3

Non-Asymptotic Error Bounds for Bidirectional GANs

no code implementations NeurIPS 2021 Shiao Liu, Yunfei Yang, Jian Huang, Yuling Jiao, Yang Wang

Our results are also applicable to the Wasserstein bidirectional GAN if the target distribution is assumed to have a bounded support.

FedDrop: Trajectory-weighted Dropout for Efficient Federated Learning

no code implementations29 Sep 2021 Dongping Liao, Xitong Gao, Yiren Zhao, Hao Dai, Li Li, Kafeng Wang, Kejiang Ye, Yang Wang, Cheng-Zhong Xu

Federated learning (FL) enables edge clients to train collaboratively while preserving individual's data privacy.

Federated Learning

Graph Information Matters: Understanding Graph Filters from Interaction Probability

no code implementations29 Sep 2021 Zhixian Chen, Tengfei Ma, Yang Wang

We show that the homophily degree of graphs significantly affects the prediction error of graph filters.

Graph Learning Node Classification

NOAHQA: Numerical Reasoning with Interpretable Graph Question Answering Dataset

1 code implementation Findings (EMNLP) 2021 Qiyuan Zhang, Lei Wang, Sicheng Yu, Shuohang Wang, Yang Wang, Jing Jiang, Ee-Peng Lim

While diverse question answering (QA) datasets have been proposed and contributed significantly to the development of deep learning models for QA tasks, the existing datasets fall short in two aspects.

Graph Question Answering Question Answering

Spatio-Temporal Self-Attention Network for Video Saliency Prediction

no code implementations24 Aug 2021 Ziqiang Wang, Zhi Liu, Gongyang Li, Yang Wang, Tianhong Zhang, Lihua Xu, Jijun Wang

3D convolutional neural networks have achieved promising results for video tasks in computer vision, including video saliency prediction that is explored in this paper.

Saliency Prediction Video Saliency Prediction

Data-Driven Constitutive Relation Reveals Scaling Law for Hydrodynamic Transport Coefficients

no code implementations1 Aug 2021 Candi Zheng, Yang Wang, Shiyi Chen

We further proposed a constitutive relation model based on scaling law and tested it on the calculation of Rayleigh scattering spectra.

regression Relation +2

Bias-Tolerant Fair Classification

no code implementations7 Jul 2021 Yixuan Zhang, Feng Zhou, Zhidong Li, Yang Wang, Fang Chen

Therefore, we propose a Bias-TolerantFAirRegularizedLoss (B-FARL), which tries to regain the benefits using data affected by label bias and selection bias.

Classification Fairness +2

Visualizing Graph Neural Networks with CorGIE: Corresponding a Graph to Its Embedding

1 code implementation24 Jun 2021 Zipeng Liu, Yang Wang, Jürgen Bernard, Tamara Munzner

Graph neural networks (GNNs) are a class of powerful machine learning tools that model node relations for making predictions of nodes or links.

Test-Time Fast Adaptation for Dynamic Scene Deblurring via Meta-Auxiliary Learning

no code implementations CVPR 2021 Zhixiang Chi, Yang Wang, Yuanhao Yu, Jin Tang

Therefore, we are able to exploit the internal information at test time via the auxiliary task to enhance the performance of deblurring.

Auxiliary Learning Deblurring +1

Image Change Captioning by Learning From an Auxiliary Task

no code implementations CVPR 2021 Mehrdad Hosseinzadeh, Yang Wang

Inspired by the success of multi-task learning, we formulate a training scheme that uses an auxiliary task to improve the training of the change captioning network.

Image Retrieval Multi-Task Learning +2

Deep Generative Learning via Schrödinger Bridge

no code implementations19 Jun 2021 Gefei Wang, Yuling Jiao, Qian Xu, Yang Wang, Can Yang

At the sample level, we derive our Schr\"{o}dinger Bridge algorithm by plugging the drift term estimated by a deep score estimator and a deep density ratio estimator into the Euler-Maruyama method.

Image Inpainting

Data Augmentation for Graph Convolutional Network on Semi-Supervised Classification

no code implementations16 Jun 2021 Zhengzheng Tang, Ziyue Qiao, Xuehai Hong, Yang Wang, Fayaz Ali Dharejo, Yuanchun Zhou, Yi Du

However, data augmentation for graph-based models remains a challenging problem, as graph data is more complex than traditional data, which consists of two features with different properties: graph topology and node attributes.

Classification Data Augmentation +1

DECORE: Deep Compression with Reinforcement Learning

no code implementations CVPR 2022 Manoj Alwani, Yang Wang, Vashisht Madhavan

For a larger dataset like ImageNet with just 30 epochs of training, it can compress the ResNet-50 architecture by 44. 7% and reduce FLOPs by 42. 3%, with just a 0. 69% drop on Top-5 accuracy of the uncompressed model.

reinforcement-learning Reinforcement Learning (RL)

Generalized Linear Bandits with Local Differential Privacy

1 code implementation NeurIPS 2021 Yuxuan Han, Zhipeng Liang, Yang Wang, Jiheng Zhang

In this paper, we design LDP algorithms for stochastic generalized linear bandits to achieve the same regret bound as in non-privacy settings.

Decision Making Multi-Armed Bandits

Learning Elastic Embeddings for Customizing On-Device Recommenders

no code implementations4 Jun 2021 Tong Chen, Hongzhi Yin, Yujia Zheng, Zi Huang, Yang Wang, Meng Wang

The core idea is to compose elastic embeddings for each item, where an elastic embedding is the concatenation of a set of embedding blocks that are carefully chosen by an automated search function.

Recommendation Systems

An error analysis of generative adversarial networks for learning distributions

no code implementations27 May 2021 Jian Huang, Yuling Jiao, Zhen Li, Shiao Liu, Yang Wang, Yunfei Yang

This paper studies how well generative adversarial networks (GANs) learn probability distributions from finite samples.

Dual-side Sparse Tensor Core

no code implementations20 May 2021 Yang Wang, Chen Zhang, Zhiqiang Xie, Cong Guo, Yunxin Liu, Jingwen Leng

We demonstrate the feasibility of our design with minimal changes to the existing production-scale inner-product-based Tensor Core.

Quaternion Factorization Machines: A Lightweight Solution to Intricate Feature Interaction Modelling

no code implementations5 Apr 2021 Tong Chen, Hongzhi Yin, Xiangliang Zhang, Zi Huang, Yang Wang, Meng Wang

As a well-established approach, factorization machine (FM) is capable of automatically learning high-order interactions among features to make predictions without the need for manual feature engineering.

Feature Engineering

DynACPD Embedding Algorithm for Prediction Tasks in Dynamic Networks

no code implementations12 Mar 2021 Chris Connell, Yang Wang

Classical network embeddings create a low dimensional representation of the learned relationships between features across nodes.

Link Prediction Node Classification

Referring Segmentation in Images and Videos with Cross-Modal Self-Attention Network

no code implementations9 Feb 2021 Linwei Ye, Mrigank Rochan, Zhi Liu, Xiaoqin Zhang, Yang Wang

In this paper, we propose a cross-modal self-attention (CMSA) module to utilize fine details of individual words and the input image or video, which effectively captures the long-range dependencies between linguistic and visual features.

Ranked #5 on Referring Expression Segmentation on J-HMDB (Precision@0.9 metric)

Referring Expression Referring Expression Segmentation +3

STUaNet: Understanding uncertainty in spatiotemporal collective human mobility

no code implementations9 Feb 2021 Zhengyang Zhou, Yang Wang, Xike Xie, Lei Qiao, Yuantao Li

The high dynamics and heterogeneous interactions in the complicated urban systems have raised the issue of uncertainty quantification in spatiotemporal human mobility, to support critical decision-makings in risk-aware web applications such as urban event prediction where fluctuations are of significant interests.

Uncertainty Quantification

Wasserstein Graph Neural Networks for Graphs with Missing Attributes

no code implementations6 Feb 2021 Zhixian Chen, Tengfei Ma, Yangqiu Song, Yang Wang

In this paper, we propose an innovative node representation learning framework, Wasserstein Graph Neural Network (WGNN), to mitigate the problem.

Attribute Graph Representation Learning +3

VSEGAN: Visual Speech Enhancement Generative Adversarial Network

no code implementations4 Feb 2021 Xinmeng Xu, Yang Wang, Dongxiang Xu, Yiyuan Peng, Cong Zhang, Jie Jia, Binbin Chen

This paper proposes a novel frameworkthat involves visual information for speech enhancement, by in-corporating a Generative Adversarial Network (GAN).

Generative Adversarial Network Speech Enhancement

On the capacity of deep generative networks for approximating distributions

no code implementations29 Jan 2021 Yunfei Yang, Zhen Li, Yang Wang

Furthermore, it is shown that the approximation error in Wasserstein distance grows at most linearly on the ambient dimension and that the approximation order only depends on the intrinsic dimension of the target distribution.

Learning Hybrid Representations for Automatic 3D Vessel Centerline Extraction

no code implementations14 Dec 2020 Jiafa He, Chengwei Pan, Can Yang, Ming Zhang, Yang Wang, Xiaowei Zhou, Yizhou Yu

The main idea is to use CNNs to learn local appearances of vessels in image crops while using another point-cloud network to learn the global geometry of vessels in the entire image.

Representation Learning

Long-Term Pipeline Failure Prediction Using Nonparametric Survival Analysis

no code implementations11 Nov 2020 Dilusha Weeraddana, Sudaraka MallawaArachchi, Tharindu Warnakula, Zhidong Li, Yang Wang

We applied Machine Learning techniques to find a cost-effective solution to the pipe failure problem in these Australian cities, where on average 1500 of water main failures occur each year.

BIG-bench Machine Learning Survival Analysis

AdaCrowd: Unlabeled Scene Adaptation for Crowd Counting

1 code implementation23 Oct 2020 Mahesh Kumar Krishna Reddy, Mrigank Rochan, Yiwei Lu, Yang Wang

In particular, we propose a new problem called unlabeled scene-adaptive crowd counting.

Crowd Counting

Deep-HOSeq: Deep Higher Order Sequence Fusion for Multimodal Sentiment Analysis

1 code implementation16 Oct 2020 Sunny Verma, Jiwei Wang, Zhefeng Ge, Rujia Shen, Fan Jin, Yang Wang, Fang Chen, Wei Liu

In this research, we first propose a common network to discover both intra-modal and inter-modal dynamics by utilizing basic LSTMs and tensor based convolution networks.

Multimodal Sentiment Analysis Sentiment Classification

High Quality Remote Sensing Image Super-Resolution Using Deep Memory Connected Network

no code implementations1 Oct 2020 Wenjia Xu, Guangluan Xu, Yang Wang, Xian Sun, Daoyu Lin, Yirong Wu

Single image super-resolution is an effective way to enhance the spatial resolution of remote sensing image, which is crucial for many applications such as target detection and image classification.

Image Classification Image Super-Resolution

Where is the Model Looking At?--Concentrate and Explain the Network Attention

no code implementations29 Sep 2020 Wenjia Xu, Jiuniu Wang, Yang Wang, Guangluan Xu, Wei Dai, Yirong Wu

We generate attribute-based textual explanations for the network and ground the attributes on the image to show visual explanations.

Attribute Image Classification +1

Dual-constrained Deep Semi-Supervised Coupled Factorization Network with Enriched Prior

no code implementations8 Sep 2020 Yan Zhang, Zhao Zhang, Yang Wang, Zheng Zhang, Li Zhang, Shuicheng Yan, Meng Wang

Nonnegative matrix factorization is usually powerful for learning the "shallow" parts-based representation, but it clearly fails to discover deep hierarchical information within both the basis and representation spaces.

Clustering Graph Learning +1

A Mathematical Introduction to Generative Adversarial Nets (GAN)

no code implementations1 Sep 2020 Yang Wang

This paper attempts to provide an overview of GANs from a mathematical point of view.

Ontology-based annotation and analysis of COVID-19 phenotypes

no code implementations5 Aug 2020 Yang Wang, Fengwei Zhang, Hong Yu, Xianwei Ye, Yongqun He

The commonly occurring 17 phenotypes were classified into different groups based on the Human Phenotype Ontology (HPO).

Adaptive Video Highlight Detection by Learning from User History

1 code implementation ECCV 2020 Mrigank Rochan, Mahesh Kumar Krishna Reddy, Linwei Ye, Yang Wang

In this paper, we propose a simple yet effective framework that learns to adapt highlight detection to a user by exploiting the user's history in the form of highlights that the user has previously created.

Highlight Detection

Few-shot Scene-adaptive Anomaly Detection

1 code implementation ECCV 2020 Yiwei Lu, Frank Yu, Mahesh Kumar Krishna Reddy, Yang Wang

In this paper, we propose a novel few-shot scene-adaptive anomaly detection problem to address the limitations of previous approaches.

Anomaly Detection Meta-Learning

Cross-Modal Weighting Network for RGB-D Salient Object Detection

2 code implementations ECCV 2020 Gongyang Li, Zhi Liu, Linwei Ye, Yang Wang, Haibin Ling

In this paper, we propose a novel Cross-Modal Weighting (CMW) strategy to encourage comprehensive interactions between RGB and depth channels for RGB-D SOD.

object-detection Object Localization +3

Recurrent Relational Memory Network for Unsupervised Image Captioning

no code implementations24 Jun 2020 Dan Guo, Yang Wang, Peipei Song, Meng Wang

Unsupervised image captioning with no annotations is an emerging challenge in computer vision, where the existing arts usually adopt GAN (Generative Adversarial Networks) models.

Computational Efficiency Image Captioning +2

Unsupervised Vehicle Re-identification with Progressive Adaptation

no code implementations20 Jun 2020 Jinjia Peng, Yang Wang, Huibing Wang, Zhao Zhang, Xianping Fu, Meng Wang

For PAL, a data adaptation module is employed for source domain, which generates the images with similar data distribution to unlabeled target domain as ``pseudo target samples''.

Unsupervised Vehicle Re-Identification Vehicle Re-Identification

Recovering Accurate Labeling Information from Partially Valid Data for Effective Multi-Label Learning

no code implementations20 Jun 2020 Xi-Ming Li, Yang Wang

Partial Multi-label Learning (PML) aims to induce the multi-label predictor from datasets with noisy supervision, where each training instance is associated with several candidate labels but only partially valid.

Multi-Label Learning valid

Survey on Deep Multi-modal Data Analytics: Collaboration, Rivalry and Fusion

1 code implementation15 Jun 2020 Yang Wang

In this paper, we provide a substantial overview of the existing state-of-the-arts on the filed of multi-modal data analytics from shallow to deep spaces.

Utilizing machine learning to prevent water main breaks by understanding pipeline failure drivers

no code implementations5 Jun 2020 Dilusha Weeraddana, Bin Liang, Zhidong Li, Yang Wang, Fang Chen, Livia Bonazzi, Dean Phillips, Nitin Saxena

Data61 and Western Water worked collaboratively to apply engineering expertise and Machine Learning tools to find a cost-effective solution to the pipe failure problem in the region west of Melbourne, where on average 400 water main failures occur per year.

BIG-bench Machine Learning

Deep Degradation Prior for Low-Quality Image Classification

no code implementations CVPR 2020 Yang Wang, Yang Cao, Zheng-Jun Zha, Jing Zhang, Zhiwei Xiong

Since the statistical properties are independent to image content, deep degradation prior can be learned on a training set of limited images without supervision of semantic labels and served in a form of "plugging-in" module of the existing classification networks to improve their performance on degraded images.

Classification General Classification +1

Approximation in shift-invariant spaces with deep ReLU neural networks

no code implementations25 May 2020 Yunfei Yang, Zhen Li, Yang Wang

We also give lower bounds of the $L^p (1\le p \le \infty)$ approximation error for Sobolev spaces, which show that our construction of neural network is asymptotically optimal up to a logarithmic factor.

Try This Instead: Personalized and Interpretable Substitute Recommendation

no code implementations19 May 2020 Tong Chen, Hongzhi Yin, Guanhua Ye, Zi Huang, Yang Wang, Meng Wang

Then, by treating attributes as the bridge between users and items, we can thoroughly model the user-item preferences (i. e., personalization) and item-item relationships (i. e., substitution) for recommendation.

Attribute Collaborative Filtering +1

SimpleMKKM: Simple Multiple Kernel K-means

1 code implementation11 May 2020 Xinwang Liu, En Zhu, Jiyuan Liu, Timothy Hospedales, Yang Wang, Meng Wang

We propose a simple yet effective multiple kernel clustering algorithm, termed simple multiple kernel k-means (SimpleMKKM).

Clustering

LadaBERT: Lightweight Adaptation of BERT through Hybrid Model Compression

no code implementations COLING 2020 Yihuan Mao, Yujing Wang, Chufan Wu, Chen Zhang, Yang Wang, Yaming Yang, Quanlu Zhang, Yunhai Tong, Jing Bai

BERT is a cutting-edge language representation model pre-trained by a large corpus, which achieves superior performances on various natural language understanding tasks.

Blocking Knowledge Distillation +2

RiskOracle: A Minute-level Citywide Traffic Accident Forecasting Framework

no code implementations19 Feb 2020 Zhengyang Zhou, Yang Wang, Xike Xie, Lianliang Chen, Hengchang Liu

Real-time traffic accident forecasting is increasingly important for public safety and urban management (e. g., real-time safe route planning and emergency response deployment).

Management

Dual Convolutional LSTM Network for Referring Image Segmentation

no code implementations30 Jan 2020 Linwei Ye, Zhi Liu, Yang Wang

Given an input image and a referring expression in the form of a natural language sentence, the goal is to segment the object of interest in the image referred by the linguistic query.

Image Segmentation Natural Language Understanding +4

Deep Learning-based Image Compression with Trellis Coded Quantization

no code implementations26 Jan 2020 Binglin Li, Mohammad Akbari, Jie Liang, Yang Wang

Recently many works attempt to develop image compression models based on deep learning architectures, where the uniform scalar quantizer (SQ) is commonly applied to the feature maps between the encoder and decoder.

Image Compression Quantization

Semi-DerainGAN: A New Semi-supervised Single Image Deraining Network

no code implementations23 Jan 2020 Yanyan Wei, Zhao Zhang, Yang Wang, Haijun Zhang, Mingbo Zhao, Mingliang Xu, Meng Wang

Although supervised deep deraining networks have obtained impressive results on synthetic datasets, they still cannot obtain satisfactory results on real images due to weak generalization of rain removal capacity, i. e., the pre-trained models usually cannot handle new shapes and directions that may lead to over-derained/under-derained results.

Single Image Deraining

Dense Residual Network: Enhancing Global Dense Feature Flow for Character Recognition

no code implementations23 Jan 2020 Zhao Zhang, Zemin Tang, Yang Wang, Zheng Zhang, Choujun Zhan, ZhengJun Zha, Meng Wang

To construct FDRN, we propose a new fast residual dense block (f-RDB) to retain the ability of local feature fusion and local residual learning of original RDB, which can reduce the computing efforts at the same time.

Learning Hybrid Representation by Robust Dictionary Learning in Factorized Compressed Space

no code implementations26 Dec 2019 Jiahuan Ren, Zhao Zhang, Sheng Li, Yang Wang, Guangcan Liu, Shuicheng Yan, Meng Wang

Specifically, J-RFDL performs the robust representation by DL in a factorized compressed space to eliminate the negative effects of noise and outliers on the results, which can also make the DL process efficient.

Dictionary Learning

Convolutional Dictionary Pair Learning Network for Image Representation Learning

no code implementations17 Dec 2019 Zhao Zhang, Yulin Sun, Yang Wang, Zheng-Jun Zha, Shuicheng Yan, Meng Wang

To address this issue, we propose a novel generalized end-to-end representation learning architecture, dubbed Convolutional Dictionary Pair Learning Network (CDPL-Net) in this paper, which integrates the learning schemes of the CNN and dictionary pair learning into a unified framework.

Dictionary Learning Representation Learning

DerainCycleGAN: Rain Attentive CycleGAN for Single Image Deraining and Rainmaking

1 code implementation15 Dec 2019 Yanyan Wei, Zhao Zhang, Yang Wang, Mingliang Xu, Yi Yang, Shuicheng Yan, Meng Wang

However, in practice it is rather common to have no un-paired images in real deraining task, in such cases how to remove the rain streaks in an unsupervised way will be a very challenging task due to lack of constraints between images and hence suffering from low-quality recovery results.

Single Image Deraining

Compressed DenseNet for Lightweight Character Recognition

no code implementations15 Dec 2019 Zhao Zhang, Zemin Tang, Yang Wang, Haijun Zhang, Shuicheng Yan, Meng Wang

LDB is a convolutional block similarly as dense block, but it can reduce the computation cost and weight size to (1/L, 2/L), compared with original ones, where L is the number of layers in blocks.

Fully-Convolutional Intensive Feature Flow Neural Network for Text Recognition

no code implementations13 Dec 2019 Zhao Zhang, Zemin Tang, Zheng Zhang, Yang Wang, Jie Qin, Meng Wang

But existing CNNs based frameworks still have several drawbacks: 1) the traditaional pooling operation may lose important feature information and is unlearnable; 2) the tradi-tional convolution operation optimizes slowly and the hierar-chical features from different layers are not fully utilized.

Multilayer Collaborative Low-Rank Coding Network for Robust Deep Subspace Discovery

no code implementations13 Dec 2019 Xianzhen Li, Zhao Zhang, Yang Wang, Guangcan Liu, Shuicheng Yan, Meng Wang

In this paper, we explore the deep multi-subspace recovery problem by designing a multilayer architecture for latent LRR.

Clustering Representation Learning

Learning to Recommend via Meta Parameter Partition

no code implementations4 Dec 2019 Liang Zhao, Yang Wang, daxiang dong, Hao Tian

The fixed part, capturing user invariant features, is shared by all users and is learned during offline meta learning stage.

Meta-Learning

Diversifying Inference Path Selection: Moving-Mobile-Network for Landmark Recognition

no code implementations1 Dec 2019 Biao Qian, Yang Wang, Zhao Zhang, Richang Hong, Meng Wang, Ling Shao

We intuitively find that M$^2$Net can essentially promote the diversity of the inference path (selected blocks subset) selection, so as to enhance the recognition accuracy.

Landmark Recognition

Kernelized Multiview Subspace Analysis by Self-weighted Learning

no code implementations23 Nov 2019 Huibing Wang, Yang Wang, Zhao Zhang, Xianping Fu, Zhuo Li, Mingliang Xu, Meng Wang

With the popularity of multimedia technology, information is always represented or transmitted from multiple views.

Dimensionality Reduction Image Retrieval +1

Scalable Inference for Nonparametric Hawkes Process Using Pólya-Gamma Augmentation

no code implementations29 Oct 2019 Feng Zhou, Zhidong Li, Xuhui Fan, Yang Wang, Arcot Sowmya, Fang Chen

In this paper, we consider the sigmoid Gaussian Hawkes process model: the baseline intensity and triggering kernel of Hawkes process are both modeled as the sigmoid transformation of random trajectories drawn from Gaussian processes (GP).

Bayesian Inference Gaussian Processes +1

Region Mutual Information Loss for Semantic Segmentation

2 code implementations NeurIPS 2019 Shuai Zhao, Yang Wang, Zheng Yang, Deng Cai

In this paper, we develop a region mutual information (RMI) loss to model the dependencies among pixels more simply and efficiently.

Semantic Segmentation

Future Frame Prediction Using Convolutional VRNN for Anomaly Detection

no code implementations5 Sep 2019 Yiwei Lu, Mahesh Kumar Krishna Reddy, Seyed shahabeddin Nabavi, Yang Wang

Anomaly detection in videos aims at reporting anything that does not conform the normal behaviour or distribution.

Anomaly Detection

A Convolutional Neural Network with Mapping Layers for Hyperspectral Image Classification

no code implementations26 Aug 2019 Rui Li, Zhibin Pan, Yang Wang, Ping Wang

In this paper, we propose a convolutional neural network with mapping layers (MCNN) for hyperspectral image (HSI) classification.

Classification General Classification +1

Multi-Task Deep Learning with Dynamic Programming for Embryo Early Development Stage Classification from Time-Lapse Videos

no code implementations22 Aug 2019 Zihan Liu, Bo Huang, Yuqi Cui, Yifan Xu, Bo Zhang, Lixia Zhu, Yang Wang, Lei Jin, Dongrui Wu

Accurate classification of embryo early development stages can provide embryologists valuable information for assessing the embryo quality, and hence is critical to the success of IVF.

General Classification

Adaptive Structure-constrained Robust Latent Low-Rank Coding for Image Recovery

no code implementations21 Aug 2019 Zhao Zhang, Lei Wang, Sheng Li, Yang Wang, Zheng Zhang, Zheng-Jun Zha, Meng Wang

Specifically, AS-LRC performs the latent decomposition of given data into a low-rank reconstruction by a block-diagonal codes matrix, a group sparse locality-adaptive salient feature part and a sparse error part.

Representation Learning

Learning Structured Twin-Incoherent Twin-Projective Latent Dictionary Pairs for Classification

no code implementations21 Aug 2019 Zhao Zhang, Yulin Sun, Zheng Zhang, Yang Wang, Guangcan Liu, Meng Wang

In this setting, our TP-DPL integrates the twin-incoherence based latent flexible DPL and the joint embedding of codes as well as salient features by twin-projection into a unified model in an adaptive neighborhood-preserving manner.

General Classification

A Targeted Acceleration and Compression Framework for Low bit Neural Networks

no code implementations9 Jul 2019 Biao Qian, Yang Wang

In this paper, we propose a novel Targeted Acceleration and Compression (TAC) framework to improve the performance of 1 bit deep neural networks W e consider that the acceleration and compression effects of binarizing fully connected layer s are not sufficient to compensate for the accuracy loss caused by it In the proposed framework, t he convolutional and fully connected layer are separated and optimized i ndividually .

Binarization Computational Efficiency +2

Optimal low rank tensor recovery

no code implementations12 Jun 2019 Jian-Feng Cai, Lizhang Miao, Yang Wang, Yin Xian

We investigate the sample size requirement for exact recovery of a high order tensor of low rank from a subset of its entries.

Riemannian optimization

UnOS: Unified Unsupervised Optical-Flow and Stereo-Depth Estimation by Watching Videos

1 code implementation CVPR 2019 Yang Wang, Peng Wang, Zhenheng Yang, Chenxu Luo, Yi Yang, Wei Xu

In this paper, we propose UnOS, an unified system for unsupervised optical flow and stereo depth estimation using convolutional neural network (CNN) by taking advantages of their inherent geometrical consistency based on the rigid-scene assumption.

Motion Segmentation Optical Flow Estimation +2

Efficient EM-Variational Inference for Hawkes Process

no code implementations29 May 2019 Feng Zhou, Zhidong Li, Xuhui Fan, Yang Wang, Arcot Sowmya, Fang Chen

In classical Hawkes process, the baseline intensity and triggering kernel are assumed to be a constant and parametric function respectively, which limits the model flexibility.

Variational Inference

Visualizing and Understanding the Semantics of Embedding Spaces via Algebraic Formulae

no code implementations ICLR 2019 Piero Molino, Yang Wang, Jiawei Zhang

Embeddings are a fundamental component of many modern machine learning and natural language processing models.

Attentive Action and Context Factorization

no code implementations10 Apr 2019 Yang Wang, Vinh Tran, Gedas Bertasius, Lorenzo Torresani, Minh Hoai

This is a challenging task due to the subtlety of human actions in video and the co-occurrence of contextual elements.

Action Recognition Temporal Action Localization

Contextual Attention for Hand Detection in the Wild

1 code implementation ICCV 2019 Supreeth Narasimhaswamy, Zhengwei Wei, Yang Wang, Justin Zhang, Minh Hoai

We also conduct ablation studies on hand detection to show the effectiveness of the proposed contextual attention module.

Hand Detection object-detection +1

Knowledge Distillation for Human Action Anticipation

no code implementations9 Apr 2019 Vinh Tran, Yang Wang, Minh Hoai

In this paper, we propose a novel knowledge distillation framework that uses an action recognition network to supervise the training of an action anticipation network, guiding the latter to attend to the relevant information needed for correctly anticipating the future actions.

Action Anticipation Action Recognition +3

Convolutional Temporal Attention Model for Video-based Person Re-identification

no code implementations9 Apr 2019 Tanzila Rahman, Mrigank Rochan, Yang Wang

A common approach for person re-identification is to first extract image features for all frames in the video, then aggregate all the features to form a video-level feature.

Semantic Segmentation Video-Based Person Re-Identification

When AWGN-based Denoiser Meets Real Noises

2 code implementations6 Apr 2019 Yuqian Zhou, Jianbo Jiao, Haibin Huang, Yang Wang, Jue Wang, Honghui Shi, Thomas Huang

In this paper, we propose a novel approach to boost the performance of a real image denoiser which is trained only with synthetic pixel-independent noise data dominated by AWGN.

Denoising

Cross-Entropy Adversarial View Adaptation for Person Re-identification

no code implementations3 Apr 2019 Lin Wu, Richang Hong, Yang Wang, Meng Wang

The main contribution is to learn coupled asymmetric mappings regarding view characteristics which are adversarially trained to address the view discrepancy by optimising the cross-entropy view confusion objective.

Person Re-Identification

Few-Shot Deep Adversarial Learning for Video-based Person Re-identification

no code implementations29 Mar 2019 Lin Wu, Yang Wang, Hongzhi Yin, Meng Wang, Ling Shao

Video-based person re-identification (re-ID) refers to matching people across camera views from arbitrary unaligned video footages.

Time Series Time Series Analysis +1

Wasserstein-Wasserstein Auto-Encoders

no code implementations25 Feb 2019 Shunkang Zhang, Yuan Gao, Yuling Jiao, Jin Liu, Yang Wang, Can Yang

To address the challenges in learning deep generative models (e. g., the blurriness of variational auto-encoder and the instability of training generative adversarial networks, we propose a novel deep generative model, named Wasserstein-Wasserstein auto-encoders (WWAE).

Deep Discriminative Representation Learning with Attention Map for Scene Classification

no code implementations21 Feb 2019 Jun Li, Daoyu Lin, Yang Wang, Guangluan Xu, Chibiao Ding

However, most recent approaches to remote sensing scene classification are based on Convolutional Neural Networks (CNNs).

Classification Face Recognition +3

Deep Generative Learning via Variational Gradient Flow

1 code implementation24 Jan 2019 Yuan Gao, Yuling Jiao, Yang Wang, Yao Wang, Can Yang, Shunkang Zhang

We propose a general framework to learn deep generative models via \textbf{V}ariational \textbf{Gr}adient Fl\textbf{ow} (VGrow) on probability spaces.

Binary Classification

GIF2Video: Color Dequantization and Temporal Interpolation of GIF images

no code implementations CVPR 2019 Yang Wang, Haibin Huang, Chuan Wang, Tong He, Jue Wang, Minh Hoai

In this paper, we propose GIF2Video, the first learning-based method for enhancing the visual quality of GIFs in the wild.

Quantization

A Remote Sensing Image Dataset for Cloud Removal

2 code implementations3 Jan 2019 Daoyu Lin, Guangluan Xu, Xiaoke Wang, Yang Wang, Xian Sun, Kun fu

Removing clouds is an indispensable pre-processing step in remote sensing image analysis.

Change Detection Cloud Removal +1

3D PersonVLAD: Learning Deep Global Representations for Video-based Person Re-identification

no code implementations26 Dec 2018 Lin Wu, Yang Wang, Ling Shao, Meng Wang

In this paper, we introduce a global video representation to video-based person re-identification (re-ID) that aggregates local 3D features across the entire video extent.

Video-Based Person Re-Identification

Multi-view Laplacian Eigenmaps Based on Bag-of-Neighbors For RGBD Human Emotion Recognition

no code implementations8 Nov 2018 Shenglan Liu, Shuai Guo, Hong Qiao, Yang Wang, Bin Wang, Wenbo Luo, Mingming Zhang, Keye Zhang, Bixuan Du

As RGB view and depth view lie in different spaces, a new distance metric bag of neighbors (BON) used in MvLE can get the similar distributions of the two views.

Emotion Recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.