Search Results for author: Tao Wang

Found 121 papers, 41 papers with code

Task-oriented Domain-specific Meta-Embedding for Text Classification

no code implementations EMNLP 2020 Xin Wu, Yi Cai, Yang Kai, Tao Wang, Qing Li

Meta-embedding learning, which combines complementary information in different word embeddings, have shown superior performances across different Natural Language Processing tasks.

Classification General Classification +2

The Value of Information in Stopping Problems

no code implementations13 May 2022 Ehud Lehrer, Tao Wang

We consider stopping problems in which a decision maker (DM) faces an unknown state of nature and decides sequentially whether to stop and take an irreversible action; pay a fee and obtain additional information; or wait without acquiring information.

FRIH: Fine-grained Region-aware Image Harmonization

no code implementations13 May 2022 Jinlong Peng, Zekun Luo, Liang Liu, Boshen Zhang, Tao Wang, Yabiao Wang, Ying Tai, Chengjie Wang, Weiyao Lin

Image harmonization aims to generate a more realistic appearance of foreground and background for a composite image.

Causal Intervention for Subject-Deconfounded Facial Action Unit Recognition

no code implementations17 Apr 2022 Yingjie Chen, Diqi Chen, Tao Wang, Yizhou Wang, Yun Liang

Subject-invariant facial action unit (AU) recognition remains challenging for the reason that the data distribution varies among subjects.

Causal Inference Facial Action Unit Detection

GigaST: A 10,000-hour Pseudo Speech Translation Corpus

no code implementations8 Apr 2022 Rong Ye, Chengqi Zhao, Tom Ko, Chutong Meng, Tao Wang, Mingxuan Wang, Jun Cao

The training set is translated by a strong machine translation system and the test set is translated by human.

Machine Translation Translation

PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision

1 code implementation29 Mar 2022 Kehong Gong, Bingbing Li, Jianfeng Zhang, Tao Wang, Jing Huang, Michael Bi Mi, Jiashi Feng, Xinchao Wang

Existing self-supervised 3D human pose estimation schemes have largely relied on weak supervisions like consistency loss to guide the learning, which, inevitably, leads to inferior results in real-world scenarios with unseen poses.

3D Human Pose Estimation

A Long Short-term Memory Based Recurrent Neural Network for Interventional MRI Reconstruction

no code implementations28 Mar 2022 Ruiyang Zhao, Zhao He, Tao Wang, Suhao Qiu, Pawel Herman, Yanle Hu, Chencheng Zhang, Dinggang Shen, Bomin Sun, Guang-Zhong Yang, Yuan Feng

Here we proposed a convolutional long short-term memory (Conv-LSTM) based recurrent neural network (RNN), or ConvLR, to reconstruct interventional images with golden-angle radial sampling.

Frame MRI Reconstruction

Geometric Synthesis: A Free lunch for Large-scale Palmprint Recognition Model Pretraining

no code implementations11 Mar 2022 Kai Zhao, Lei Shen, Yingyi Zhang, Chuhan Zhou, Tao Wang, Ruixin Zhang, Shouhong Ding, Wei Jia, Wei Shen

In this paper, by observing that palmar creases are the key information to deep-learning-based palmprint recognition, we propose to synthesize training data by manipulating palmar creases.

End-to-end video instance segmentation via spatial-temporal graph neural networks

1 code implementation ICCV 2021 Tao Wang, Ning Xu, Kean Chen, Weiyao Lin

Specifically, graph nodes representing instance features are used for detection and segmentation while graph edges representing instance relations are used for tracking.

Frame Instance Segmentation +2

An STDP-Based Supervised Learning Algorithm for Spiking Neural Networks

no code implementations7 Mar 2022 Zhanhao Hu, Tao Wang, Xiaolin Hu

Compared with rate-based artificial neural networks, Spiking Neural Networks (SNN) provide a more biological plausible model for the brain.

NeuralDPS: Neural Deterministic Plus Stochastic Model with Multiband Excitation for Noise-Controllable Waveform Generation

no code implementations5 Mar 2022 Tao Wang, Ruibo Fu, Jiangyan Yi, JianHua Tao, Zhengqi Wen

We have also verified through experiments that this method can effectively control the noise components in the predicted speech and adjust the SNR of speech.

CampNet: Context-Aware Mask Prediction for End-to-End Text-Based Speech Editing

no code implementations21 Feb 2022 Tao Wang, Jiangyan Yi, Ruibo Fu, JianHua Tao, Zhengqi Wen

It can solve unnatural prosody in the edited region and synthesize the speech corresponding to the unseen words in the transcript.

Few-Shot Learning speech editing

Single UHD Image Dehazing via Interpretable Pyramid Network

1 code implementation17 Feb 2022 Boxue Xiao, Zhuoran Zheng, Xiang Chen, Chen Lv, Yunliang Zhuang, Tao Wang

Currently, most single image dehazing models cannot run an ultra-high-resolution (UHD) image with a single GPU shader in real-time.

Image Dehazing Single Image Dehazing

SODAR: Segmenting Objects by DynamicallyAggregating Neighboring Mask Representations

no code implementations15 Feb 2022 Tao Wang, Jun Hao Liew, Yu Li, Yunpeng Chen, Jiashi Feng

Unlike the original per grid cell object masks, SODAR is implicitly supervised to learn mask representations that encode geometric structure of nearby objects and complement adjacent representations with context.

Instance Segmentation Semantic Segmentation

LighTN: Light-weight Transformer Network for Performance-overhead Tradeoff in Point Cloud Downsampling

no code implementations13 Feb 2022 Xu Wang, Yi Jin, Yigang Cen, Tao Wang, Bowen Tang, Yidong Li

Compared with traditional task-irrelevant downsampling methods, task-oriented neural networks have shown improved performance in point cloud downsampling range.

COVID-19 Hospitalizations Forecasts Using Internet Search Data

no code implementations3 Feb 2022 Tao Wang, Simin Ma, Soobin Baek, Shihao Yang

As the COVID-19 spread over the globe and new variants of COVID-19 keep occurring, reliable real-time forecasts of COVID-19 hospitalizations are critical for public health decision on medical resources allocations such as ICU beds, ventilators, and personnel to prepare for the surge of COVID-19 pandemics.

Decision Making Time Series

IoTGAN: GAN Powered Camouflage Against Machine Learning Based IoT Device Identification

no code implementations10 Jan 2022 Tao Hou, Tao Wang, Zhuo Lu, Yao Liu, Yalin Sagduyu

In this research, we propose a novel attack strategy named IoTGAN to manipulate an IoT device's traffic such that it can evade machine learning based IoT device identification.

GLAN: A Graph-based Linear Assignment Network

no code implementations5 Jan 2022 He Liu, Tao Wang, Congyan Lang, Songhe Feng, Yi Jin, Yidong Li

The experimental results on a synthetic dataset reveal that our method outperforms state-of-the-art baselines and achieves consistently high accuracy with the increment of the problem size.

Multi-Object Tracking

Deep Probabilistic Graph Matching

no code implementations5 Jan 2022 He Liu, Tao Wang, Yidong Li, Congyan Lang, Songhe Feng, Haibin Ling

Most previous learning-based graph matching algorithms solve the \textit{quadratic assignment problem} (QAP) by dropping one or more of the matching constraints and adopting a relaxed assignment solver to obtain sub-optimal correspondences.

Graph Matching

Powerful Graph Convolutioal Networks with Adaptive Propagation Mechanism for Homophily and Heterophily

no code implementations27 Dec 2021 Tao Wang, Rui Wang, Di Jin, Dongxiao He, Yuxiao Huang

To address this problem, in this paper we design a novel propagation mechanism, which can automatically change the propagation and aggregation process according to homophily or heterophily between node pairs.

ITA: Image-Text Alignments for Multi-Modal Named Entity Recognition

1 code implementation13 Dec 2021 Xinyu Wang, Min Gui, Yong Jiang, Zixia Jia, Nguyen Bach, Tao Wang, Zhongqiang Huang, Fei Huang, Kewei Tu

As text representations take the most important role in MNER, in this paper, we propose {\bf I}mage-{\bf t}ext {\bf A}lignments (ITA) to align image features into the textual space, so that the attention mechanism in transformer-based pretrained textual embeddings can be better utilized.

Named Entity Recognition

Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition

1 code implementation7 Dec 2021 Tianyu Guo, Hong Liu, Zhan Chen, Mengyuan Liu, Tao Wang, Runwei Ding

In this paper, to make better use of the movement patterns introduced by extreme augmentations, a Contrastive Learning framework utilizing Abundant Information Mining for self-supervised action Representation (AimCLR) is proposed.

Contrastive Learning Representation Learning +2

Pose-guided Feature Disentangling for Occluded Person Re-identification Based on Transformer

1 code implementation5 Dec 2021 Tao Wang, Hong Liu, Pinhao Song, Tianyu Guo, Wei Shi

Therefore, we propose a transformer-based Pose-guided Feature Disentangling (PFD) method by utilizing pose information to clearly disentangle semantic components (e. g. human body or joint parts) and selectively match non-occluded parts correspondingly.

Person Re-Identification

Topological and Algebraic Structures of the Space of Atanassov's Intuitionistic Fuzzy Values

no code implementations17 Nov 2021 Xinxing Wu, Tao Wang, Peide Liu, Gul Deniz Cayli, Xu Zhang

By introducing a new operator for IFVs via the linear order based on a score function and an accuracy function, we present that such an operator is a strong negation on IFVs.

Direct Multi-view Multi-person 3D Pose Estimation

1 code implementation NeurIPS 2021 Tao Wang, Jianfeng Zhang, Yujun Cai, Shuicheng Yan, Jiashi Feng

Instead of estimating 3D joint locations from costly volumetric representation or reconstructing the per-person 3D pose from multiple detected 2D poses as in previous methods, MvP directly regresses the multi-person 3D poses in a clean and efficient way, without relying on intermediate tasks.

3D Multi-Person Pose Estimation 3D Pose Estimation

CMTR: Cross-modality Transformer for Visible-infrared Person Re-identification

no code implementations18 Oct 2021 Tengfei Liang, Yi Jin, Yajun Gao, Wu Liu, Songhe Feng, Tao Wang, Yidong Li

The existing convolutional neural network-based methods mainly face the problem of insufficient perception of modalities' information, and can not learn good discriminative modality-invariant embeddings for identities, which limits their performance.

Cross-Modality Person Re-identification Person Re-Identification

Distract Your Attention: Multi-head Cross Attention Network for Facial Expression Recognition

1 code implementation15 Sep 2021 Zhengyao Wen, Wenzhong Lin, Tao Wang, Ge Xu

To address these issues, we propose our DAN with three key components: Feature Clustering Network (FCN), Multi-head cross Attention Network (MAN), and Attention Fusion Network (AFN).

Facial Expression Recognition

PnP-DETR: Towards Efficient Visual Analysis with Transformers

1 code implementation ICCV 2021 Tao Wang, Li Yuan, Yunpeng Chen, Jiashi Feng, Shuicheng Yan

Recently, DETR pioneered the solution of vision tasks with transformers, it directly translates the image feature map into the object detection result.

Object Detection Panoptic Segmentation

MuVER: Improving First-Stage Entity Retrieval with Multi-View Entity Representations

1 code implementation EMNLP 2021 Xinyin Ma, Yong Jiang, Nguyen Bach, Tao Wang, Zhongqiang Huang, Fei Huang, Weiming Lu

Entity retrieval, which aims at disambiguating mentions to canonical entities from massive KBs, is essential for many tasks in natural language processing.

Entity Linking Entity Retrieval

Joint Graph Learning and Matching for Semantic Feature Correspondence

2 code implementations1 Sep 2021 He Liu, Tao Wang, Yidong Li, Congyan Lang, Yi Jin, Haibin Ling

In this paper, we propose a joint \emph{graph learning and matching} network, named GLAM, to explore reliable graph structures for boosting graph matching.

Graph Learning Graph Matching

Secoco: Self-Correcting Encoding for Neural Machine Translation

no code implementations Findings (EMNLP) 2021 Tao Wang, Chengqi Zhao, Mingxuan Wang, Lei LI, Hang Li, Deyi Xiong

This paper presents Self-correcting Encoding (Secoco), a framework that effectively deals with input noise for robust neural machine translation by introducing self-correcting predictors.

Machine Translation Translation

Learning Class-level Prototypes for Few-shot Learning

no code implementations25 Aug 2021 Minglei Yuan, Wenhai Wang, Tao Wang, Chunhao Cai, Qian Xu, Tong Lu

Few-shot learning aims to recognize new categories using very few labeled samples.

Few-Shot Learning

Real-time Image Enhancer via Learnable Spatial-aware 3D Lookup Tables

no code implementations ICCV 2021 Tao Wang, Yong Li, Jingyang Peng, Yipeng Ma, Xian Wang, Fenglong Song, Youliang Yan

One is a 1D weight vector used for image-level scenario adaptation, the other is a 3D weight map aimed for pixel-wise category fusion.

Image Enhancement

Risk Minimization for Zero-shot Sequence Labeling

no code implementations ACL 2021 Zechuan Hu, Yong Jiang, Nguyen Bach, Tao Wang, Zhongqiang Huang, Fei Huang, Kewei Tu

In this paper, we propose a novel unified framework for zero-shot sequence labeling with minimum risk training and design a new decomposable risk function that models the relations between the predicted labels from the source models and the true labels.

Multi-View Cross-Lingual Structured Prediction with Minimum Supervision

no code implementations ACL 2021 Zechuan Hu, Yong Jiang, Nguyen Bach, Tao Wang, Zhongqiang Huang, Fei Huang, Kewei Tu

In structured prediction problems, cross-lingual transfer learning is an efficient way to train quality models for low-resource languages, and further improvement can be obtained by learning from multiple source languages.

Cross-Lingual Transfer Structured Prediction +1

No-Reference Quality Assessment for 3D Colored Point Cloud and Mesh Models

2 code implementations5 Jul 2021 ZiCheng Zhang, Wei Sun, Xiongkuo Min, Tao Wang, Wei Lu, Guangtao Zhai

Therefore, many related studies such as point cloud quality assessment (PCQA) and mesh quality assessment (MQA) have been carried out to measure the visual quality degradations of 3D models.

Point Cloud Quality Assessment

Ultra-High-Definition Image Dehazing via Multi-Guided Bilateral Learning

1 code implementation CVPR 2021 Zhuoran Zheng, Wenqi Ren, Xiaochun Cao, Xiaobin Hu, Tao Wang, Fenglong Song, Xiuyi Jia

To address the problem, we propose a novel network capable of real-time dehazing of 4K images on a single GPU, which consists of three deep CNNs.

Image Dehazing Single Image Dehazing

Deep Learning based Full-reference and No-reference Quality Assessment Models for Compressed UGC Videos

1 code implementation2 Jun 2021 Wei Sun, Tao Wang, Xiongkuo Min, Fuwang Yi, Guangtao Zhai

The proposed VQA framework consists of three modules, the feature extraction module, the quality regression module, and the quality pooling module.

Frame Video Quality Assessment +2

Adaptive Feature Alignment for Adversarial Training

no code implementations31 May 2021 Tao Wang, Ruixin Zhang, Xingyu Chen, Kai Zhao, Xiaolin Huang, Yuge Huang, Shaoxin Li, Jilin Li, Feiyue Huang

Based on this observation, we propose the adaptive feature alignment (AFA) to generate features of arbitrary attacking strengths.

Adversarial Defense

The Volctrans Neural Speech Translation System for IWSLT 2021

1 code implementation ACL (IWSLT) 2021 Chengqi Zhao, Zhicheng Liu, Jian Tong, Tao Wang, Mingxuan Wang, Rong Ye, Qianqian Dong, Jun Cao, Lei LI

For offline speech translation, our best end-to-end model achieves 8. 1 BLEU improvements over the benchmark on the MuST-C test set and is even approaching the results of a strong cascade solution.


Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning

1 code implementation ACL 2021 Xinyu Wang, Yong Jiang, Nguyen Bach, Tao Wang, Zhongqiang Huang, Fei Huang, Kewei Tu

We find empirically that the contextual representations computed on the retrieval-based input view, constructed through the concatenation of a sentence and its external contexts, can achieve significantly improved performance compared to the original input view based only on the sentence.

Named Entity Recognition NER

FedCom: A Byzantine-Robust Local Model Aggregation Rule Using Data Commitment for Federated Learning

no code implementations16 Apr 2021 Bo Zhao, Peng Sun, Liming Fang, Tao Wang, Keyu Jiang

The results demonstrate its effectiveness and superior performance compared to the state-of-the-art Byzantine-robust schemes in defending against typical data poisoning and model poisoning attacks under practical Non-IID data distributions.

Data Poisoning Federated Learning

Half-Truth: A Partially Fake Audio Detection Dataset

no code implementations8 Apr 2021 Jiangyan Yi, Ye Bai, JianHua Tao, Zhengkun Tian, Chenglong Wang, Tao Wang, Ruibo Fu

Diverse promising datasets have been designed to hold back the development of fake audio detection, such as ASVspoof databases.

Speech Synthesis

IDOL-Net: An Interactive Dual-Domain Parallel Network for CT Metal Artifact Reduction

no code implementations3 Apr 2021 Tao Wang, Wenjun Xia, Zexin Lu, Huaiqiang Sun, Yan Liu, Hu Chen, Jiliu Zhou, Yi Zhang

Since the dual-domain MAR methods can leverage the hybrid information from both sinogram and image domains, they have significantly improved the performance compared to single-domain methods.

Computed Tomography (CT) Disentanglement +1

A Universal Model for Cross Modality Mapping by Relational Reasoning

no code implementations26 Feb 2021 Zun Li, Congyan Lang, Liqian Liang, Tao Wang, Songhe Feng, Jun Wu, Yidong Li

With the aim of matching a pair of instances from two different modalities, cross modality mapping has attracted growing attention in the computer vision community.

Image Classification Relational Reasoning

Regional and Sectoral Structures and Their Dynamics of Chinese Economy: A Network Perspective from Multi-Regional Input-Output Tables

no code implementations24 Feb 2021 Tao Wang, Shiying Xiao, Jun Yan, Panpan Zhang

Quantified metrics assessing the relative importance of the province-sectors in the national economy echo the national and regional economic development policies to a certain extent.

Community Detection Physics and Society General Economics Economics Applications

Attention Models for Point Clouds in Deep Learning: A Survey

no code implementations22 Feb 2021 Xu Wang, Yi Jin, Yigang Cen, Tao Wang, Yidong Li

Recently, the advancement of 3D point clouds in deep learning has attracted intensive research in different application domains such as computer vision and robotic tasks.

3D Pose Estimation 3D Semantic Segmentation

DAN-Net: Dual-Domain Adaptive-Scaling Non-local Network for CT Metal Artifact Reduction

1 code implementation16 Feb 2021 Tao Wang, Wenjun Xia, Yongqiang Huang, Huaiqiang Sun, Yan Liu, Hu Chen, Jiliu Zhou, Yi Zhang

With the rapid development of deep learning in the field of medical imaging, several network models have been proposed for metal artifact reduction (MAR) in CT.

Computed Tomography (CT) Metal Artifact Reduction

Isolation mechanisms for high-speed packet-processing pipelines

no code implementations29 Jan 2021 Tao Wang, Xiangrui Yang, Gianni Antichi, Anirudh Sivaraman, Aurojit Panda

We have open sourced the code for Menshen's hardware and software at https://isolation. quest/.

Networking and Internet Architecture Hardware Architecture

Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet

10 code implementations ICCV 2021 Li Yuan, Yunpeng Chen, Tao Wang, Weihao Yu, Yujun Shi, Zihang Jiang, Francis EH Tay, Jiashi Feng, Shuicheng Yan

To overcome such limitations, we propose a new Tokens-To-Token Vision Transformer (T2T-ViT), which incorporates 1) a layer-wise Tokens-to-Token (T2T) transformation to progressively structurize the image to tokens by recursively aggregating neighboring Tokens into one Token (Tokens-to-Token), such that local structure represented by surrounding tokens can be modeled and tokens length can be reduced; 2) an efficient backbone with a deep-narrow structure for vision transformer motivated by CNN architecture design after empirical study.

Image Classification Language Modelling

Search for axion-like dark matter using solid-state nuclear magnetic resonance

no code implementations4 Jan 2021 Deniz Aybas, Janos Adam, Emmy Blumenthal, Alexander V. Gramolin, Dorian Johnson, Annalies Kleyheeg, Samer Afach, John W. Blanchard, Gary P. Centers, Antoine Garcon, Martin Engler, Nataniel L. Figueroa, Marina Gil Sendra, Arne Wickenbrock, Matthew Lawson, Tao Wang, Teng Wu, Haosu Luo, Hamdi Mani, Philip Mauskopf, Peter W. Graham, Surjeet Rajendran, Derek F. Jackson Kimball, Dmitry Budker, Alexander O. Sushkov

We calibrated the detector and characterized the excitation spectrum and relaxation parameters of the nuclear spin ensemble with pulsed magnetic resonance measurements in a 4. 4 T magnetic field.

High Energy Physics - Experiment Other Condensed Matter Instrumentation and Detectors

Multi-Scale Separable Network for Ultra-High-Definition Video Deblurring

1 code implementation ICCV 2021 Senyou Deng, Wenqi Ren, Yanyang Yan, Tao Wang, Fenglong Song, Xiaochun Cao

Although recent research has witnessed a significant progress on the video deblurring task, these methods struggle to reconcile inference efficiency and visual quality simultaneously, especially on ultra-high-definition (UHD) videos (e. g., 4K resolution).


FASG: Feature Aggregation Self-training GCN for Semi-supervised Node Classification

no code implementations1 Jan 2021 Gongpei Zhao, Tao Wang, Yidong Li, Yi Jin

Recently, Graph Convolutioal Networks (GCNs) have achieved significant success in many graph-based learning tasks, especially for node classification, due to its excellent ability in representation learning.

Classification General Classification +2

AggMask: Exploring locally aggregated learning of mask representations for instance segmentation

1 code implementation1 Jan 2021 Tao Wang, Jun Hao Liew, Yu Li, Yunpeng Chen, Jiashi Feng

Recently proposed one-stage instance segmentation models (\emph{e. g.}, SOLO) learn to directly predict location-specific object mask with fully-convolutional networks.

Instance Segmentation Semantic Segmentation

Ultra-High-Definition Image HDR Reconstruction via Collaborative Bilateral Learning

no code implementations ICCV 2021 Zhuoran Zheng, Wenqi Ren, Xiaochun Cao, Tao Wang, Xiuyi Jia

First, we propose a dual-path network to extract content and chromatic features at a reduced resolution of the low dynamic range (LDR) input.

HDR Reconstruction

Exploring the limits of Concurrency in ML Training on Google TPUs

no code implementations7 Nov 2020 Sameer Kumar, James Bradbury, Cliff Young, Yu Emma Wang, Anselm Levskaya, Blake Hechtman, Dehao Chen, HyoukJoong Lee, Mehmet Deveci, Naveen Kumar, Pankaj Kanwar, Shibo Wang, Skye Wanderman-Milne, Steve Lacy, Tao Wang, Tayo Oguntebi, Yazhou Zu, Yuanzhong Xu, Andy Swing

Recent results in language understanding using neural networks have required training hardware of unprecedentedscale, with thousands of chips cooperating on a single training run.

The Box is in the Pen: Evaluating Commonsense Reasoning in Neural Machine Translation

1 code implementation Findings of the Association for Computational Linguistics 2020 Jie He, Tao Wang, Deyi Xiong, Qun Liu

Our experiments and analyses demonstrate that neural machine translation performs poorly on commonsense reasoning of the three ambiguity types in terms of both reasoning accuracy ( 6 60. 1{\%}) and reasoning consistency (6 31{\%}).

Common Sense Reasoning Machine Translation +1

Toward Accurate Person-level Action Recognition in Videos of Crowded Scenes

no code implementations16 Oct 2020 Li Yuan, Yichen Zhou, Shuning Chang, Ziyuan Huang, Yunpeng Chen, Xuecheng Nie, Tao Wang, Jiashi Feng, Shuicheng Yan

Prior works always fail to deal with this problem in two aspects: (1) lacking utilizing information of the scenes; (2) lacking training data in the crowd and complex scenes.

Action Recognition Action Recognition In Videos +3

Finding Action Tubes with a Sparse-to-Dense Framework

no code implementations30 Aug 2020 Yuxi Li, Weiyao Lin, Tao Wang, John See, Rui Qian, Ning Xu, Li-Min Wang, Shugong Xu

The task of spatial-temporal action detection has attracted increasing attention among researchers.

Action Detection

High Accurate Time-of-Arrival Estimation with Fine-Grained Feature Generation for Internet-of-Things Applications

no code implementations18 Aug 2020 Guangjin Pan, Tao Wang, Shunqing Zhang, Shugong Xu

Conventional schemes often require extra reference signals or more complicated algorithms to improve the time-of-arrival (TOA) estimation accuracy.

Object-aware Multimodal Named Entity Recognition in Social Media Posts with Adversarial Learning

1 code implementation3 Aug 2020 Changmeng Zheng, Zhiwei Wu, Tao Wang, Cai Yi, Qing Li

To better exploit visual and textual information in NER, we propose an adversarial gated bilinear attention neural network (AGBAN).

Named Entity Recognition NER

The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentation

1 code implementation ECCV 2020 Tao Wang, Yu Li, Bingyi Kang, Junnan Li, Junhao Liew, Sheng Tang, Steven Hoi, Jiashi Feng

Specifically, we systematically investigate performance drop of the state-of-the-art two-stage instance segmentation model Mask R-CNN on the recent long-tail LVIS dataset, and unveil that a major cause is the inaccurate classification of object proposals.

General Classification Instance Segmentation +2

A Multi-Level Approach to Waste Object Segmentation

1 code implementation8 Jul 2020 Tao Wang, Yuanzheng Cai, Lingyu Liang, Dongyi Ye

We address the problem of localizing waste objects from a color image and an optional depth image, which is a key perception component for robotic interaction with such objects.

Semantic Segmentation

Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax

1 code implementation CVPR 2020 Yu Li, Tao Wang, Bingyi Kang, Sheng Tang, Chunfeng Wang, Jintao Li, Jiashi Feng

Solving long-tail large vocabulary object detection with deep learning based models is a challenging and demanding task, which is however under-explored. In this work, we provide the first systematic analysis on the underperformance of state-of-the-art models in front of long-tail distribution.

Image Classification Instance Segmentation +3

Learning Combinatorial Solver for Graph Matching

no code implementations CVPR 2020 Tao Wang, He Liu, Yidong Li, Yi Jin, Xiaohui Hou, Haibin Ling

Learning-based approaches to graph matching have been developed and explored for more than a decade, have grown rapidly in scope and popularity in recent years.

Combinatorial Optimization Graph Matching +1

Human in Events: A Large-Scale Benchmark for Human-centric Video Analysis in Complex Events

no code implementations9 May 2020 Weiyao Lin, Huabin Liu, Shizhan Liu, Yuxi Li, Rui Qian, Tao Wang, Ning Xu, Hongkai Xiong, Guo-Jun Qi, Nicu Sebe

We demonstrate that the proposed method is able to boost the performance of existing pose estimation pipelines on our HiEve dataset.

Pose Estimation

Automatic low-bit hybrid quantization of neural networks through meta learning

no code implementations24 Apr 2020 Tao Wang, Junsong Wang, Chang Xu, Chao Xue

With the best searched quantization policy, we subsequently retrain or finetune to further improve the performance of the quantized target network.

Meta-Learning Quantization

Deep Learning based OTDOA Positioning for NB-IoT Communication Systems

no code implementations10 Apr 2020 Guangjin Pan, Tao Wang, Xiufeng Jiang, Shunqing Zhang

Positioning is becoming a key component in many Internet of Things (IoT) applications.

CTM: Collaborative Temporal Modeling for Action Recognition

no code implementations8 Feb 2020 Qian Liu, Tao Wang, Jie Liu, Yang Guan, Qi Bu, Longfei Yang

In order to learn powerful feature of videos, we propose a Collaborative Temporal Modeling (CTM) block (Figure 1) to learn temporal information for action recognition.

Action Recognition Video Understanding

iqiyi Submission to ActivityNet Challenge 2019 Kinetics-700 challenge: Hierarchical Group-wise Attention

no code implementations7 Feb 2020 Qian Liu, Dongyang Cai, Jie Liu, Nan Ding, Tao Wang

The standard non-local (NL) module is effective in aggregating frame-level features on the task of video classification but presents low parameters efficiency and high computational cost.

Frame General Classification +1

Learning a Layout Transfer Network for Context Aware Object Detection

no code implementations9 Dec 2019 Tao Wang, Xuming He, Yuanzheng Cai, Guobao Xiao

We present a context aware object detection method based on a retrieve-and-transform scene layout model.

Autonomous Driving Object Detection

Merging External Bilingual Pairs into Neural Machine Translation

no code implementations2 Dec 2019 Tao Wang, Shaohui Kuang, Deyi Xiong, António Branco

As neural machine translation (NMT) is not easily amenable to explicit correction of errors, incorporating pre-specified translations into NMT is widely regarded as a non-trivial challenge.

Machine Translation Translation

Classification Calibration for Long-tail Instance Segmentation

1 code implementation29 Oct 2019 Tao Wang, Yu Li, Bingyi Kang, Junnan Li, Jun Hao Liew, Sheng Tang, Steven Hoi, Jiashi Feng

In this report, we investigate the performance drop phenomenon of state-of-the-art two-stage instance segmentation models when processing extreme long-tail training data based on the LVIS [5] dataset, and find a major cause is the inaccurate classification of object proposals.

Classification General Classification +2

Prototype Recalls for Continual Learning

no code implementations25 Sep 2019 Mengmi Zhang, Tao Wang, Joo Hwee Lim, Jiashi Feng

Without tampering with the performance on initial tasks, our method learns novel concepts given a few training examples of each class in new tasks.

Continual Learning Metric Learning

Revisiting Knowledge Distillation via Label Smoothing Regularization

2 code implementations CVPR 2020 Li Yuan, Francis E. H. Tay, Guilin Li, Tao Wang, Jiashi Feng

Without any extra computation cost, Tf-KD achieves up to 0. 65\% improvement on ImageNet over well-established baseline models, which is superior to label smoothing regularization.

Self-Knowledge Distillation

Scale MLPerf-0.6 models on Google TPU-v3 Pods

no code implementations21 Sep 2019 Sameer Kumar, Victor Bitorff, Dehao Chen, Chiachen Chou, Blake Hechtman, HyoukJoong Lee, Naveen Kumar, Peter Mattson, Shibo Wang, Tao Wang, Yuanzhong Xu, Zongwei Zhou

The recent submission of Google TPU-v3 Pods to the industry wide MLPerf v0. 6 training benchmark demonstrates the scalability of a suite of industry relevant ML models.

Trustable and Automated Machine Learning Running with Blockchain and Its Applications

no code implementations14 Aug 2019 Tao Wang, Xinmin Wu, Taiping He

Experiments show that this synthetic data generation is very effective in applications such as fraud detection in financial data.

Fraud Detection Synthetic Data Generation

Central Similarity Quantization for Efficient Image and Video Retrieval

1 code implementation CVPR 2020 Li Yuan, Tao Wang, Xiaopeng Zhang, Francis EH Tay, Zequn Jie, Wei Liu, Jiashi Feng

In this work, we propose a new \emph{global} similarity metric, termed as \emph{central similarity}, with which the hash codes of similar data pairs are encouraged to approach a common center and those for dissimilar pairs to converge to different centers, to improve hash learning efficiency and retrieval accuracy.

Quantization Video Retrieval

Distilling Object Detectors with Fine-grained Feature Imitation

3 code implementations CVPR 2019 Tao Wang, Li Yuan, Xiaopeng Zhang, Jiashi Feng

To address the challenge of distilling knowledge in detection model, we propose a fine-grained feature imitation method exploiting the cross-location discrepancy of feature response.

Knowledge Distillation Object Detection

Variational Prototype Replays for Continual Learning

1 code implementation23 May 2019 Mengmi Zhang, Tao Wang, Joo Hwee Lim, Gabriel Kreiman, Jiashi Feng

In each classification task, our method learns a set of variational prototypes with their means and variances, where embedding of the samples from the same class can be represented in a prototypical distribution and class-representative prototypes are separated apart.

Continual Learning General Classification +1

High-Performance Support Vector Machines and Its Applications

no code implementations1 May 2019 Taiping He, Tao Wang, Ralph Abbey, Joshua Griffin

The support vector machines (SVM) algorithm is a popular classification technique in data mining and machine learning.

Classification General Classification

Fully Automatic Brain Tumor Segmentation using a Normalized Gaussian Bayesian Classifier and 3D Fluid Vector Flow

no code implementations1 May 2019 Tao Wang, Irene Cheng, Anup Basu

This paper presents an automatic brain tumor segmentation method based on a Normalized Gaussian Bayesian classification and a new 3D Fluid Vector Flow (FVF) algorithm.

Brain Tumor Segmentation Tumor Segmentation

A note on 'A fully parallel 3D thinning algorithm and its applications'

no code implementations1 May 2019 Tao Wang, Anup Basu

A 3D thinning algorithm erodes a 3D binary image layer by layer to extract the skeletons.

Few-shot Adaptive Faster R-CNN

no code implementations CVPR 2019 Tao Wang, Xiaopeng Zhang, Li Yuan, Jiashi Feng

To address these challenges, we first introduce a pairing mechanism over source and target features to alleviate the issue of insufficient target domain samples.

Object Detection Unsupervised Domain Adaptation

A Unified Analytical Framework for Trustable Machine Learning and Automation Running with Blockchain

no code implementations21 Mar 2019 Tao Wang

Second, it proposes a unified analytical framework for trustable machine learning by using blockchain technology.

Flash: Efficient Dynamic Routing for Offchain Networks

2 code implementations14 Feb 2019 Peng Wang, Hong Xu, Xin Jin, Tao Wang

Mice payments are directly sent by looking up a routing table with a few precomputed paths to reduce probing overhead.

Networking and Internet Architecture

GM-PLL: Graph Matching based Partial Label Learning

no code implementations10 Jan 2019 Gengyu Lyu, Songhe Feng, Tao Wang, Congyan Lang, Yidong Li

Partial Label Learning (PLL) aims to learn from the data where each training example is associated with a set of candidate labels, among which only one is correct.

Graph Matching Partial Label Learning

Image Classification at Supercomputer Scale

no code implementations16 Nov 2018 Chris Ying, Sameer Kumar, Dehao Chen, Tao Wang, Youlong Cheng

Deep learning is extremely computationally intensive, and hardware vendors have responded by building faster accelerators in large clusters.

Classification General Classification +1

Onset of lasing in small devices: the identification of the first threshold

no code implementations1 Mar 2018 Tao Wang, Gian Piero Puccioni, Gian Luca Lippi

We present a simple and flexible technique for identifying the onset of coherent emission in lasers, from the mesoscale to the nanoscale, which makes use of photon counting and a small amplitude modulation added to the pump.


Driverseat: Crowdstrapping Learning Tasks for Autonomous Driving

no code implementations7 Dec 2015 Pranav Rajpurkar, Toki Migimatsu, Jeff Kiske, Royce Cheng-Yue, Sameep Tandon, Tao Wang, Andrew Ng

While emerging deep-learning systems have outclassed knowledge-based approaches in many tasks, their application to detection tasks for autonomous technologies remains an open field for scientific exploration.

Autonomous Driving Lane Detection

Convolutional Neural Networks over Tree Structures for Programming Language Processing

7 code implementations18 Sep 2014 Lili Mou, Ge Li, Lu Zhang, Tao Wang, Zhi Jin

Programming language processing (similar to natural language processing) is a hot research topic in the field of software engineering; it has also aroused growing interest in the artificial intelligence community.

Voting for Deceptive Opinion Spam Detection

no code implementations16 Sep 2014 Tao Wang, Hua Zhu

Consumers' purchase decisions are increasingly influenced by user-generated online reviews.

Deception Detection General Classification +1

A Multi-parent Memetic Algorithm for the Linear Ordering Problem

no code implementations18 May 2014 Tao Ye, Tao Wang, Zhipeng Lu, Jin-Kao Hao

In this paper, we present a multi-parent memetic algorithm (denoted by MPM) for solving the classic Linear Ordering Problem (LOP).

Modeling Attractiveness and Multiple Clicks in Sponsored Search Results

no code implementations1 Jan 2014 Dinesh Govindaraj, Tao Wang, S. V. N. Vishwanathan

Our model seamlessly incorporates the effect of externalities (quality of other search results displayed in response to a user query), user fatigue, as well as pre and post-click relevance of a sponsored search result.

Time-dependent Hierarchical Dirichlet Model for Timeline Generation

no code implementations8 Dec 2013 Rumeng Li, Tao Wang, Xun Wang

Existing approaches neglect such hierarchical topic structure involved in the news corpus in timeline generation.

Learning Structured Hough Voting for Joint Object Detection and Occlusion Reasoning

no code implementations CVPR 2013 Tao Wang, Xuming He, Nick Barnes

We propose a structured Hough voting method for detecting objects with heavy occlusion in indoor environments.

Object Detection

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