Search Results for author: Sheng Li

Found 117 papers, 14 papers with code

CAN-GRU: a Hierarchical Model for Emotion Recognition in Dialogue

no code implementations CCL 2020 Ting Jiang, Bing Xu, Tiejun Zhao, Sheng Li

In the first layer, in order to extract textual features of utterances, we propose a convolutional self-attention network(CAN).

Emotion Recognition Opinion Mining

Adversarial Speech Generation and Natural Speech Recovery for Speech Content Protection

no code implementations LREC 2022 Sheng Li, Jiyi Li, Qianying Liu, Zhuo Gong

Moreover, based on the speech collection, we proposed a neural network-based frame-by-frame mapping method to recover the speech content by converting from the adversarial speech to the human speech.

speech-recognition Speech Recognition

Exploiting Auxiliary Data for Offensive Language Detection with Bidirectional Transformers

no code implementations ACL (WOAH) 2021 Sumer Singh, Sheng Li

Our approach introduces domain adaptation (DA) training procedures to ALBERT, such that it can effectively exploit auxiliary data from source domains to improve the OLD performance in a target domain.

Domain Adaptation

Securing Fixed Neural Network Steganography

no code implementations18 Sep 2023 Zicong Luo, Sheng Li, Guobiao Li, Zhenxing Qian, Xinpeng Zhang

To deal with this issue, we propose a key-based FNNS scheme to improve the security of the FNNS, where we generate key-controlled perturbations from the FNN for data embedding.

Image Steganography

Towards Artificial General Intelligence (AGI) in the Internet of Things (IoT): Opportunities and Challenges

no code implementations14 Sep 2023 Fei Dou, Jin Ye, Geng Yuan, Qin Lu, Wei Niu, Haijian Sun, Le Guan, Guoyu Lu, Gengchen Mai, Ninghao Liu, Jin Lu, Zhengliang Liu, Zihao Wu, Chenjiao Tan, Shaochen Xu, Xianqiao Wang, Guoming Li, Lilong Chai, Sheng Li, Jin Sun, Hongyue Sun, Yunli Shao, Changying Li, Tianming Liu, WenZhan Song

Artificial General Intelligence (AGI), possessing the capacity to comprehend, learn, and execute tasks with human cognitive abilities, engenders significant anticipation and intrigue across scientific, commercial, and societal arenas.

Decision Making

Trustworthy Representation Learning Across Domains

no code implementations23 Aug 2023 Ronghang Zhu, Dongliang Guo, Daiqing Qi, Zhixuan Chu, Xiang Yu, Sheng Li

Inspired by the concepts in trustworthy AI, we proposed the first trustworthy representation learning across domains framework which includes four concepts, i. e, robustness, privacy, fairness, and explainability, to give a comprehensive literature review on this research direction.

Fairness Representation Learning

Experts Weights Averaging: A New General Training Scheme for Vision Transformers

no code implementations11 Aug 2023 Yongqi Huang, Peng Ye, Xiaoshui Huang, Sheng Li, Tao Chen, Tong He, Wanli Ouyang

As Vision Transformers (ViTs) are gradually surpassing CNNs in various visual tasks, one may question: if a training scheme specifically for ViTs exists that can also achieve performance improvement without increasing inference cost?

FLIQS: One-Shot Mixed-Precision Floating-Point and Integer Quantization Search

no code implementations7 Aug 2023 Jordan Dotzel, Gang Wu, Andrew Li, Muhammad Umar, Yun Ni, Mohamed S. Abdelfattah, Zhiru Zhang, Liqun Cheng, Martin G. Dixon, Norman P. Jouppi, Quoc V. Le, Sheng Li

With the proposed integer quantization search, we increase the accuracy of ResNet-18 on ImageNet by 1. 31% points and ResNet-50 by 0. 90% points with equivalent model cost over previous methods.


DRAW: Defending Camera-shooted RAW against Image Manipulation

no code implementations ICCV 2023 Xiaoxiao Hu, Qichao Ying, Zhenxing Qian, Sheng Li, Xinpeng Zhang

RAW files are the initial measurement of scene radiance widely used in most cameras, and the ubiquitously-used RGB images are converted from RAW data through Image Signal Processing (ISP) pipelines.

Image Manipulation

RetouchingFFHQ: A Large-scale Dataset for Fine-grained Face Retouching Detection

no code implementations20 Jul 2023 Qichao Ying, Jiaxin Liu, Sheng Li, Haisheng Xu, Zhenxing Qian, Xinpeng Zhang

However, the lack of large-scale and fine-grained face retouching datasets has been a major obstacle to progress in this field.

Representation Learning

PharmacyGPT: The AI Pharmacist

no code implementations19 Jul 2023 Zhengliang Liu, Zihao Wu, Mengxuan Hu, Bokai Zhao, Lin Zhao, Tianyi Zhang, Haixing Dai, Xianyan Chen, Ye Shen, Sheng Li, Brian Murray, Tianming Liu, Andrea Sikora

In this study, we introduce PharmacyGPT, a novel framework to assess the capabilities of large language models (LLMs) such as ChatGPT and GPT-4 in emulating the role of clinical pharmacists.

Towards Deep Network Steganography: From Networks to Networks

no code implementations7 Jul 2023 Guobiao Li, Sheng Li, Meiling Li, Zhenxing Qian, Xinpeng Zhang

In this paper, we propose deep network steganography for the covert communication of DNN models.

Exploring New Frontiers in Agricultural NLP: Investigating the Potential of Large Language Models for Food Applications

no code implementations20 Jun 2023 Saed Rezayi, Zhengliang Liu, Zihao Wu, Chandra Dhakal, Bao Ge, Haixing Dai, Gengchen Mai, Ninghao Liu, Chen Zhen, Tianming Liu, Sheng Li

ChatGPT has shown to be a strong baseline in many NLP tasks, and we believe it has the potential to improve our model in the task of semantic matching and enhance our model's understanding of food-related concepts and relationships.

Language Modelling Nutrition

AD-AutoGPT: An Autonomous GPT for Alzheimer's Disease Infodemiology

no code implementations16 Jun 2023 Haixing Dai, Yiwei Li, Zhengliang Liu, Lin Zhao, Zihao Wu, Suhang Song, Ye Shen, Dajiang Zhu, Xiang Li, Sheng Li, Xiaobai Yao, Lu Shi, Quanzheng Li, Zhuo Chen, Donglan Zhang, Gengchen Mai, Tianming Liu

In this pioneering study, inspired by AutoGPT, the state-of-the-art open-source application based on the GPT-4 large language model, we develop a novel tool called AD-AutoGPT which can conduct data collection, processing, and analysis about complex health narratives of Alzheimer's Disease in an autonomous manner via users' textual prompts.

Language Modelling Large Language Model

pTSE: A Multi-model Ensemble Method for Probabilistic Time Series Forecasting

no code implementations16 May 2023 Yunyi Zhou, Zhixuan Chu, Yijia Ruan, Ge Jin, Yuchen Huang, Sheng Li

However, the choice of model highly relies on the characteristics of the input time series and the fixed distribution that the model is based on.

Probabilistic Time Series Forecasting Time Series

Towards Speech Dialogue Translation Mediating Speakers of Different Languages

1 code implementation16 May 2023 Shuichiro Shimizu, Chenhui Chu, Sheng Li, Sadao Kurohashi

We present a new task, speech dialogue translation mediating speakers of different languages.


Generative Steganographic Flow

no code implementations10 May 2023 Ping Wei, Ge Luo, Qi Song, Xinpeng Zhang, Zhenxing Qian, Sheng Li

In the forward mapping, secret data is hidden in the input latent of Glow model to generate stego images.

Image Generation

Generative Steganography Diffusion

no code implementations5 May 2023 Ping Wei, Qing Zhou, Zichi Wang, Zhenxing Qian, Xinpeng Zhang, Sheng Li

However, existing GAN-based GS methods cannot completely recover the hidden secret data due to the lack of network invertibility, while Flow-based methods produce poor image quality due to the stringent reversibility restriction in each module.

Image Generation

BadSAM: Exploring Security Vulnerabilities of SAM via Backdoor Attacks

no code implementations5 May 2023 Zihan Guan, Mengxuan Hu, Zhongliang Zhou, Jielu Zhang, Sheng Li, Ninghao Liu

Recently, the Segment Anything Model (SAM) has gained significant attention as an image segmentation foundation model due to its strong performance on various downstream tasks.

Backdoor Attack Image Segmentation +1

Artificial General Intelligence (AGI) for Education

no code implementations24 Apr 2023 Ehsan Latif, Gengchen Mai, Matthew Nyaaba, Xuansheng Wu, Ninghao Liu, Guoyu Lu, Sheng Li, Tianming Liu, Xiaoming Zhai

Artificial general intelligence (AGI) has gained global recognition as a future technology due to the emergence of breakthrough large language models and chatbots such as GPT-4 and ChatGPT, respectively.

Decision Making

Text2Seg: Remote Sensing Image Semantic Segmentation via Text-Guided Visual Foundation Models

1 code implementation20 Apr 2023 Jielu Zhang, Zhongliang Zhou, Gengchen Mai, Lan Mu, Mengxuan Hu, Sheng Li

We developed a pipeline that leverages multiple FMs to facilitate remote sensing image semantic segmentation tasks guided by text prompt, which we denote as Text2Seg.

Instance Segmentation Segmentation Of Remote Sensing Imagery +2

AGI for Agriculture

no code implementations12 Apr 2023 Guoyu Lu, Sheng Li, Gengchen Mai, Jin Sun, Dajiang Zhu, Lilong Chai, Haijian Sun, Xianqiao Wang, Haixing Dai, Ninghao Liu, Rui Xu, Daniel Petti, Tianming Liu, Changying Li

Artificial General Intelligence (AGI) is poised to revolutionize a variety of sectors, including healthcare, finance, transportation, and education.

Decision Making Knowledge Graphs +1

Frame Flexible Network

1 code implementation CVPR 2023 Yitian Zhang, Yue Bai, Chang Liu, Huan Wang, Sheng Li, Yun Fu

To fix this issue, we propose a general framework, named Frame Flexible Network (FFN), which not only enables the model to be evaluated at different frames to adjust its computation, but also reduces the memory costs of storing multiple models significantly.

Video Recognition

Continual Causal Inference with Incremental Observational Data

no code implementations3 Mar 2023 Zhixuan Chu, Ruopeng Li, Stephen Rathbun, Sheng Li

We propose a Continual Causal Effect Representation Learning method for estimating causal effects with observational data, which are incrementally available from non-stationary data distributions.

Causal Inference Marketing +2

Steganography of Steganographic Networks

no code implementations28 Feb 2023 Guobiao Li, Sheng Li, Meiling Li, Xinpeng Zhang, Zhenxing Qian

We propose to disguise a steganographic network (termed as the secret DNN model) into a stego DNN model which performs an ordinary machine learning task (termed as the stego task).

Better Generative Replay for Continual Federated Learning

no code implementations25 Feb 2023 Daiqing Qi, Handong Zhao, Sheng Li

Federated learning is a technique that enables a centralized server to learn from distributed clients via communications without accessing the client local data.

Continual Learning Federated Learning

Fair Attribute Completion on Graph with Missing Attributes

1 code implementation25 Feb 2023 Dongliang Guo, Zhixuan Chu, Sheng Li

To our best knowledge, FairAC is the first method that jointly addresses the graph attribution completion and graph unfairness problems.

Fairness Graph Learning

Towards Explainable Visual Anomaly Detection

no code implementations13 Feb 2023 Yizhou Wang, Dongliang Guo, Sheng Li, Yun Fu

Anomaly detection and localization of visual data, including images and videos, are of great significance in both machine learning academia and applied real-world scenarios.

Anomaly Detection

Causal Effect Estimation: Recent Advances, Challenges, and Opportunities

no code implementations2 Feb 2023 Zhixuan Chu, Jianmin Huang, Ruopeng Li, Wei Chu, Sheng Li

Causal inference has numerous real-world applications in many domains, such as health care, marketing, political science, and online advertising.

Causal Inference Marketing +1

Continual Causal Effect Estimation: Challenges and Opportunities

no code implementations3 Jan 2023 Zhixuan Chu, Sheng Li

A further understanding of cause and effect within observational data is critical across many domains, such as economics, health care, public policy, web mining, online advertising, and marketing campaigns.

Causal Inference Domain Adaptation +2

TripLe: Revisiting Pretrained Model Reuse and Progressive Learning for Efficient Vision Transformer Scaling and Searching

no code implementations ICCV 2023 Cheng Fu, Hanxian Huang, Zixuan Jiang, Yun Ni, Lifeng Nai, Gang Wu, Liqun Cheng, Yanqi Zhou, Sheng Li, Andrew Li, Jishen Zhao

One promising way to accelerate transformer training is to reuse small pretrained models to initialize the transformer, as their existing representation power facilitates faster model convergence.

Knowledge Distillation Neural Architecture Search

Exploring Depth Information for Face Manipulation Detection

no code implementations29 Dec 2022 Haoyue Wang, Meiling Li, Sheng Li, Zhenxing Qian, Xinpeng Zhang

As one of the important face features, the face depth map, which has shown to be effective in other areas such as the face recognition or face detection, is unfortunately paid little attention to in literature for detecting the manipulated face images.

Face Detection Face Recognition

Frozen CLIP Model is An Efficient Point Cloud Backbone

1 code implementation8 Dec 2022 Xiaoshui Huang, Sheng Li, Wentao Qu, Tong He, Yifan Zuo, Wanli Ouyang

This paper introduces Efficient Point Cloud Learning (EPCL), an effective and efficient point cloud learner for directly training high-quality point cloud models with a frozen CLIP model.

Few-Shot Learning Semantic Segmentation

Semi-supervised Local Cluster Extraction by Compressive Sensing

no code implementations20 Nov 2022 Zhaiming Shen, Ming-Jun Lai, Sheng Li

Local clustering problem aims at extracting a small local structure inside a graph without the necessity of knowing the entire graph structure.

Compressive Sensing

Speech-text based multi-modal training with bidirectional attention for improved speech recognition

1 code implementation1 Nov 2022 Yuhang Yang, HaiHua Xu, Hao Huang, Eng Siong Chng, Sheng Li

To let the state-of-the-art end-to-end ASR model enjoy data efficiency, as well as much more unpaired text data by multi-modal training, one needs to address two problems: 1) the synchronicity of feature sampling rates between speech and language (aka text data); 2) the homogeneity of the learned representations from two encoders.

speech-recognition Speech Recognition

Learning to Immunize Images for Tamper Localization and Self-Recovery

no code implementations28 Oct 2022 Qichao Ying, Hang Zhou, Zhenxing Qian, Sheng Li, Xinpeng Zhang

Image immunization (Imuge) is a technology of protecting the images by introducing trivial perturbation, so that the protected images are immune to the viruses in that the tampered contents can be auto-recovered.

Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training

1 code implementation22 Sep 2022 Geng Yuan, Yanyu Li, Sheng Li, Zhenglun Kong, Sergey Tulyakov, Xulong Tang, Yanzhi Wang, Jian Ren

Therefore, we analyze the feasibility and potentiality of using the layer freezing technique in sparse training and find it has the potential to save considerable training costs.

Hierarchical Capsule Prediction Network for Marketing Campaigns Effect

no code implementations22 Aug 2022 Zhixuan Chu, Hui Ding, Guang Zeng, Yuchen Huang, Tan Yan, Yulin kang, Sheng Li

In this paper, we provide an in-depth analysis of the underlying parse tree-like structure involved in the effect prediction task and we further establish a Hierarchical Capsule Prediction Network (HapNet) for predicting the effects of marketing campaigns.


Generative Steganography Network

no code implementations28 Jul 2022 Ping Wei, Sheng Li, Xinpeng Zhang, Ge Luo, Zhenxing Qian, Qing Zhou

A new steganographic approach called generative steganography (GS) has emerged recently, in which stego images (images containing secret data) are generated from secret data directly without cover media.

Image Generation Steganalysis

Image Generation Network for Covert Transmission in Online Social Network

no code implementations21 Jul 2022 Zhengxin You, Qichao Ying, Sheng Li, Zhenxing Qian, Xinpeng Zhang

Online social networks have stimulated communications over the Internet more than ever, making it possible for secret message transmission over such noisy channels.

Image Generation Image Steganography +2

Sustainable AI Processing at the Edge

no code implementations4 Jul 2022 Sébastien Ollivier, Sheng Li, Yue Tang, Chayanika Chaudhuri, Peipei Zhou, Xulong Tang, Jingtong Hu, Alex K. Jones

In particular, we explore the use of processing-in-memory (PIM) approaches, mobile GPU accelerators, and recently released FPGAs, and compare them with novel Racetrack memory PIM.

BIG-bench Machine Learning Edge-computing

Coupling Visual Semantics of Artificial Neural Networks and Human Brain Function via Synchronized Activations

no code implementations22 Jun 2022 Lin Zhao, Haixing Dai, Zihao Wu, Zhenxiang Xiao, Lu Zhang, David Weizhong Liu, Xintao Hu, Xi Jiang, Sheng Li, Dajiang Zhu, Tianming Liu

However, whether there exists semantic correlations/connections between the visual representations in ANNs and those in BNNs remains largely unexplored due to both the lack of an effective tool to link and couple two different domains, and the lack of a general and effective framework of representing the visual semantics in BNNs such as human functional brain networks (FBNs).

Image Classification Representation Learning

Image Protection for Robust Cropping Localization and Recovery

no code implementations6 Jun 2022 Qichao Ying, Hang Zhou, Xiaoxiao Hu, Zhenxing Qian, Sheng Li, Xinpeng Zhang

Existing image cropping detection schemes ignore that recovering the cropped-out contents can unveil the purpose of the behaved cropping attack.

Image Cropping

A DTCWT-SVD Based Video Watermarking resistant to frame rate conversion

no code implementations2 Jun 2022 Yifei Wang, Qichao Ying, Zhenxing Qian, Sheng Li, Xinpeng Zhang

To address this issue, we present a new video watermarking based on joint Dual-Tree Cosine Wavelet Transformation (DTCWT) and Singular Value Decomposition (SVD), which is resistant to frame rate conversion.

Multimodal Fake News Detection via CLIP-Guided Learning

no code implementations28 May 2022 Yangming Zhou, Qichao Ying, Zhenxing Qian, Sheng Li, Xinpeng Zhang

The results indicate that the proposed framework has a better capability in mining crucial features for fake news detection.

Decision Making Fake News Detection +1

Fusion of Self-supervised Learned Models for MOS Prediction

no code implementations11 Apr 2022 Zhengdong Yang, Wangjin Zhou, Chenhui Chu, Sheng Li, Raj Dabre, Raphael Rubino, Yi Zhao

This challenge aims to predict MOS scores of synthetic speech on two tracks, the main track and a more challenging sub-track: out-of-domain (OOD).

Multi-Task Adversarial Learning for Treatment Effect Estimation in Basket Trials

no code implementations10 Mar 2022 Zhixuan Chu, Stephen L. Rathbun, Sheng Li

In our paper, the basket trial is employed as an intuitive example to present this new causal inference setting.

Causal Inference feature selection +2

Learning Infomax and Domain-Independent Representations for Causal Effect Inference with Real-World Data

no code implementations22 Feb 2022 Zhixuan Chu, Stephen Rathbun, Sheng Li

In this paper, we reveal the weaknesses of these strategies, i. e., they lead to the loss of predictive information when enforcing the domain invariance; and the treatment effect estimation performance is unstable, which heavily relies on the characteristics of the domain distributions and the choice of domain divergence metrics.

Causal Inference Representation Learning +1

Invertible Image Dataset Protection

no code implementations29 Dec 2021 Kejiang Chen, Xianhan Zeng, Qichao Ying, Sheng Li, Zhenxing Qian, Xinpeng Zhang

We develop a reversible adversarial example generator (RAEG) that introduces slight changes to the images to fool traditional classification models.

Adversarial Defense

GenReg: Deep Generative Method for Fast Point Cloud Registration

no code implementations23 Nov 2021 Xiaoshui Huang, Zongyi Xu, Guofeng Mei, Sheng Li, Jian Zhang, Yifan Zuo, Yucheng Wang

To solve this challenge, we propose a new data-driven registration algorithm by investigating deep generative neural networks to point cloud registration.

Point Cloud Registration

Pairwise Adversarial Training for Unsupervised Class-imbalanced Domain Adaptation

no code implementations29 Sep 2021 Weili Shi, Ronghang Zhu, Sheng Li

In this paper, we propose a pairwise adversarial training approach to augment training data for unsupervised class-imbalanced domain adaptation.

Transfer Learning Unsupervised Domain Adaptation

CrossMatch: Cross-Classifier Consistency Regularization for Open-Set Single Domain Generalization

no code implementations ICLR 2022 Ronghang Zhu, Sheng Li

In this paper, we propose a challenging and untouched problem: \textit{Open-Set Single Domain Generalization} (OS-SDG), where target domains include unseen categories out of source label space.

Data Augmentation Domain Generalization

Automated Graph Learning via Population Based Self-Tuning GCN

no code implementations9 Jul 2021 Ronghang Zhu, Zhiqiang Tao, Yaliang Li, Sheng Li

Owing to the remarkable capability of extracting effective graph embeddings, graph convolutional network (GCN) and its variants have been successfully applied to a broad range of tasks, such as node classification, link prediction, and graph classification.

Graph Classification Graph Learning +3

Multi-Agent Cooperative Bidding Games for Multi-Objective Optimization in e-Commercial Sponsored Search

no code implementations8 Jun 2021 Ziyu Guan, Hongchang Wu, Qingyu Cao, Hao liu, Wei Zhao, Sheng Li, Cai Xu, Guang Qiu, Jian Xu, Bo Zheng

Although a few studies use multi-agent reinforcement learning to set up a cooperative game, they still suffer the following drawbacks: (1) They fail to avoid collusion solutions where all the advertisers involved in an auction collude to bid an extremely low price on purpose.

Model Optimization Multi-agent Reinforcement Learning

Safe reopening of university campuses is possible with COVID-19 vaccination

no code implementations13 May 2021 Matthew Junge, Sheng Li, Samitha Samaranayake, Matthew Zalesak

We construct an agent-based SEIR model to simulate COVID-19 spread at a 16000-student mostly non-residential urban university during the Fall 2021 Semester.

Searching for Fast Model Families on Datacenter Accelerators

no code implementations CVPR 2021 Sheng Li, Mingxing Tan, Ruoming Pang, Andrew Li, Liqun Cheng, Quoc Le, Norman P. Jouppi

On top of our DC accelerator optimized neural architecture search space, we further propose a latency-aware compound scaling (LACS), the first multi-objective compound scaling method optimizing both accuracy and latency.

Neural Architecture Search

Continual Lifelong Causal Effect Inference with Real World Evidence

no code implementations1 Jan 2021 Zhixuan Chu, Stephen Rathbun, Sheng Li

We propose a Continual Causal Effect Representation Learning method for estimating causal effect with observational data, which are incrementally available from non-stationary data distributions.

Representation Learning Selection bias

Transferable Feature Learning on Graphs Across Visual Domains

no code implementations1 Jan 2021 Ronghang Zhu, Xiaodong Jiang, Jiasen Lu, Sheng Li

In this paper, we propose a novel Transferable Feature Learning approach on Graphs (TFLG) for unsupervised adversarial domain adaptation, which jointly incorporates sample-level and class-level structure information across two domains.

Unsupervised Domain Adaptation

Co-embedding of Nodes and Edges with Graph Neural Networks

no code implementations25 Oct 2020 Xiaodong Jiang, Ronghang Zhu, Pengsheng Ji, Sheng Li

CensNet is a general graph embedding framework, which embeds both nodes and edges to a latent feature space.

BIG-bench Machine Learning Graph Classification +6

Matching in Selective and Balanced Representation Space for Treatment Effects Estimation

no code implementations15 Sep 2020 Zhixuan Chu, Stephen L. Rathbun, Sheng Li

The dramatically growing availability of observational data is being witnessed in various domains of science and technology, which facilitates the study of causal inference.

Causal Inference feature selection +2

Collaborative Attention Mechanism for Multi-View Action Recognition

no code implementations14 Sep 2020 Yue Bai, Zhiqiang Tao, Lichen Wang, Sheng Li, Yu Yin, Yun Fu

Extensive experiments on four action datasets illustrate the proposed CAM achieves better results for each view and also boosts multi-view performance.

Action Recognition Representation Learning

Stereotype-Free Classification of Fictitious Faces

no code implementations29 Apr 2020 Mohammadhossein Toutiaee, Soheyla Amirian, John A. Miller, Sheng Li

The proposed approach aids labeling new data (fictitious output images) by minimizing a penalized version of the least squares cost function between realistic pictures and target pictures.

Classification Fairness +2

A Survey on Causal Inference

1 code implementation5 Feb 2020 Liuyi Yao, Zhixuan Chu, Sheng Li, Yaliang Li, Jing Gao, Aidong Zhang

Embraced with the rapidly developed machine learning area, various causal effect estimation methods for observational data have sprung up.

BIG-bench Machine Learning Causal Inference

Cross-scale Attention Model for Acoustic Event Classification

no code implementations27 Dec 2019 Xugang Lu, Peng Shen, Sheng Li, Yu Tsao, Hisashi Kawai

However, a potential limitation of the network is that the discriminative features from the bottom layers (which can model the short-range dependency) are smoothed out in the final representation.

Classification General Classification

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

Optimizing Collision Avoidance in Dense Airspace using Deep Reinforcement Learning

no code implementations20 Dec 2019 Sheng Li, Maxim Egorov, Mykel Kochenderfer

New methodologies will be needed to ensure the airspace remains safe and efficient as traffic densities rise to accommodate new unmanned operations.

reinforcement-learning Reinforcement Learning (RL)

Correlative Channel-Aware Fusion for Multi-View Time Series Classification

no code implementations24 Nov 2019 Yue Bai, Lichen Wang, Zhiqiang Tao, Sheng Li, Yun Fu

Multi-view time series classification (MVTSC) aims to improve the performance by fusing the distinctive temporal information from multiple views.

Classification General Classification +3

Learning Robust Data Representation: A Knowledge Flow Perspective

no code implementations28 Sep 2019 Zhengming Ding, Ming Shao, Handong Zhao, Sheng Li

It is always demanding to learn robust visual representation for various learning problems; however, this learning and maintenance process usually suffers from noise, incompleteness or knowledge domain mismatch.

Representation Learning Transfer Learning

Flexible Auto-weighted Local-coordinate Concept Factorization: A Robust Framework for Unsupervised Clustering

no code implementations2 Sep 2019 Zhao Zhang, Yan Zhang, Sheng Li, Guangcan Liu, Dan Zeng, Shuicheng Yan, Meng Wang

For auto-weighting, RFA-LCF jointly preserves the manifold structures in the basis concept space and new coordinate space in an adaptive manner by minimizing the reconstruction errors on clean data, anchor points and coordinates.


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

CensNet: Convolution with Edge-Node Switching in Graph Neural Networks

no code implementations Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI-19) 2019 Xiaodong Jiang, Pengsheng Ji, Sheng Li

In this paper, we present CensNet, Convolution with Edge-Node Switching graph neural network, for semi-supervised classification and regression in graph-structured data with both node and edge features.

Graph Classification Graph Embedding +3

Robust Subspace Discovery by Block-diagonal Adaptive Locality-constrained Representation

no code implementations4 Aug 2019 Zhao Zhang, Jiahuan Ren, Sheng Li, Richang Hong, Zheng-Jun Zha, Meng Wang

Leveraging on the Frobenius-norm based latent low-rank representation model, rBDLR jointly learns the coding coefficients and salient features, and improves the results by enhancing the robustness to outliers and errors in given data, preserving local information of salient features adaptively and ensuring the block-diagonal structures of the coefficients.

Representation Learning

Scalable Block-Diagonal Locality-Constrained Projective Dictionary Learning

no code implementations25 May 2019 Zhao Zhang, Weiming Jiang, Zheng Zhang, Sheng Li, Guangcan Liu, Jie Qin

More importantly, LC-PDL avoids using the complementary data matrix to learn the sub-dictionary over each class.

Dictionary Learning

Robust Unsupervised Flexible Auto-weighted Local-Coordinate Concept Factorization for Image Clustering

no code implementations25 May 2019 Zhao Zhang, Yan Zhang, Sheng Li, Guangcan Liu, Meng Wang, Shuicheng Yan

RFA-LCF integrates the robust flexible CF, robust sparse local-coordinate coding and the adaptive reconstruction weighting learning into a unified model.

Clustering Image Clustering +1

SADIH: Semantic-Aware DIscrete Hashing

no code implementations3 Apr 2019 Zheng Zhang, Guo-Sen Xie, Yang Li, Sheng Li, Zi Huang

Due to its low storage cost and fast query speed, hashing has been recognized to accomplish similarity search in large-scale multimedia retrieval applications.


Scene Graph Generation with External Knowledge and Image Reconstruction

no code implementations CVPR 2019 Jiuxiang Gu, Handong Zhao, Zhe Lin, Sheng Li, Jianfei Cai, Mingyang Ling

Scene graph generation has received growing attention with the advancements in image understanding tasks such as object detection, attributes and relationship prediction,~\etc.

Graph Generation Image Reconstruction +5

Supervised Transfer Learning for Product Information Question Answering

no code implementations8 Jan 2019 Tuan Manh Lai, Trung Bui, Nedim Lipka, Sheng Li

Popular e-commerce websites such as Amazon offer community question answering systems for users to pose product related questions and experienced customers may provide answers voluntarily.

Community Question Answering Transfer Learning

Representation Learning for Treatment Effect Estimation from Observational Data

1 code implementation NeurIPS 2018 Liuyi Yao, Sheng Li, Yaliang Li, Mengdi Huai, Jing Gao, Aidong Zhang

Estimating individual treatment effect (ITE) is a challenging problem in causal inference, due to the missing counterfactuals and the selection bias.

Causal Inference Representation Learning +1

X-GANs: Image Reconstruction Made Easy for Extreme Cases

no code implementations6 Aug 2018 Longfei Liu, Sheng Li, Yisong Chen, Guoping Wang

Image reconstruction including image restoration and denoising is a challenging problem in the field of image computing.

Image Compression Image Denoising +3

A Review on Deep Learning Techniques Applied to Answer Selection

no code implementations COLING 2018 Tuan Manh Lai, Trung Bui, Sheng Li

Given a question and a set of candidate answers, answer selection is the task of identifying which of the candidates answers the question correctly.

Answer Selection Community Question Answering +3

Supervised Treebank Conversion: Data and Approaches

no code implementations ACL 2018 Xinzhou Jiang, Zhenghua Li, Bo Zhang, Min Zhang, Sheng Li, Luo Si

Treebank conversion is a straightforward and effective way to exploit various heterogeneous treebanks for boosting parsing performance.

Dependency Parsing Multi-Task Learning

Matching on Balanced Nonlinear Representations for Treatment Effects Estimation

no code implementations NeurIPS 2017 Sheng Li, Yun Fu

Estimating treatment effects from observational data is challenging due to the missing counterfactuals.

Domain Adaptation

Enabling Sparse Winograd Convolution by Native Pruning

1 code implementation28 Feb 2017 Sheng Li, Jongsoo Park, Ping Tak Peter Tang

Sparse methods and the use of Winograd convolutions are two orthogonal approaches, each of which significantly accelerates convolution computations in modern CNNs.

Parallelizing Word2Vec in Multi-Core and Many-Core Architectures

1 code implementation18 Nov 2016 Shihao Ji, Nadathur Satish, Sheng Li, Pradeep Dubey

Word2vec is a widely used algorithm for extracting low-dimensional vector representations of words.

Faster CNNs with Direct Sparse Convolutions and Guided Pruning

1 code implementation4 Aug 2016 Jongsoo Park, Sheng Li, Wei Wen, Ping Tak Peter Tang, Hai Li, Yiran Chen, Pradeep Dubey

Pruning CNNs in a way that increase inference speed often imposes specific sparsity structures, thus limiting the achievable sparsity levels.

Parallelizing Word2Vec in Shared and Distributed Memory

no code implementations15 Apr 2016 Shihao Ji, Nadathur Satish, Sheng Li, Pradeep Dubey

In combination, these techniques allow us to scale up the computation near linearly across cores and nodes, and process hundreds of millions of words per second, which is the fastest word2vec implementation to the best of our knowledge.

Machine Translation named-entity-recognition +5

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