Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox
Picture for Gaoang Wang

Gaoang Wang
Alert button

Zhejiang University-University of Illinois at Urbana-Champaign Institute, Zhejiang University

STSC-SNN: Spatio-Temporal Synaptic Connection with Temporal Convolution and Attention for Spiking Neural Networks


Oct 11, 2022
Chengting Yu, Zheming Gu, Da Li, Gaoang Wang, Aili Wang, Erping Li

Add code
Alert button

Figure 1 for STSC-SNN: Spatio-Temporal Synaptic Connection with Temporal Convolution and Attention for Spiking Neural Networks
Figure 2 for STSC-SNN: Spatio-Temporal Synaptic Connection with Temporal Convolution and Attention for Spiking Neural Networks
Figure 3 for STSC-SNN: Spatio-Temporal Synaptic Connection with Temporal Convolution and Attention for Spiking Neural Networks
Figure 4 for STSC-SNN: Spatio-Temporal Synaptic Connection with Temporal Convolution and Attention for Spiking Neural Networks

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Missing Modality meets Meta Sampling (M3S): An Efficient Universal Approach for Multimodal Sentiment Analysis with Missing Modality


Oct 07, 2022
Haozhe Chi, Minghua Yang, Junhao Zhu, Guanhong Wang, Gaoang Wang

Add code
Alert button

Figure 1 for Missing Modality meets Meta Sampling (M3S): An Efficient Universal Approach for Multimodal Sentiment Analysis with Missing Modality
Figure 2 for Missing Modality meets Meta Sampling (M3S): An Efficient Universal Approach for Multimodal Sentiment Analysis with Missing Modality
Figure 3 for Missing Modality meets Meta Sampling (M3S): An Efficient Universal Approach for Multimodal Sentiment Analysis with Missing Modality
Figure 4 for Missing Modality meets Meta Sampling (M3S): An Efficient Universal Approach for Multimodal Sentiment Analysis with Missing Modality

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Hierarchical Semi-Supervised Contrastive Learning for Contamination-Resistant Anomaly Detection


Jul 24, 2022
Gaoang Wang, Yibing Zhan, Xinchao Wang, Mingli Song, Klara Nahrstedt

Add code
Alert button

Figure 1 for Hierarchical Semi-Supervised Contrastive Learning for Contamination-Resistant Anomaly Detection
Figure 2 for Hierarchical Semi-Supervised Contrastive Learning for Contamination-Resistant Anomaly Detection
Figure 3 for Hierarchical Semi-Supervised Contrastive Learning for Contamination-Resistant Anomaly Detection
Figure 4 for Hierarchical Semi-Supervised Contrastive Learning for Contamination-Resistant Anomaly Detection

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey


May 22, 2022
Gaoang Wang, Mingli Song, Jenq-Neng Hwang

Add code
Alert button

Figure 1 for Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey
Figure 2 for Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey
Figure 3 for Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey
Figure 4 for Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Preserve Pre-trained Knowledge: Transfer Learning With Self-Distillation For Action Recognition


May 01, 2022
Yang Zhou, Zhanhao He, Keyu Lu, Guanhong Wang, Gaoang Wang

Add code
Alert button

Figure 1 for Preserve Pre-trained Knowledge: Transfer Learning With Self-Distillation For Action Recognition
Figure 2 for Preserve Pre-trained Knowledge: Transfer Learning With Self-Distillation For Action Recognition
Figure 3 for Preserve Pre-trained Knowledge: Transfer Learning With Self-Distillation For Action Recognition

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Human-Centered Prior-Guided and Task-Dependent Multi-Task Representation Learning for Action Recognition Pre-Training


Apr 27, 2022
Guanhong Wang, Keyu Lu, Yang Zhou, Zhanhao He, Gaoang Wang

Add code
Alert button

Figure 1 for Human-Centered Prior-Guided and Task-Dependent Multi-Task Representation Learning for Action Recognition Pre-Training
Figure 2 for Human-Centered Prior-Guided and Task-Dependent Multi-Task Representation Learning for Action Recognition Pre-Training
Figure 3 for Human-Centered Prior-Guided and Task-Dependent Multi-Task Representation Learning for Action Recognition Pre-Training
Figure 4 for Human-Centered Prior-Guided and Task-Dependent Multi-Task Representation Learning for Action Recognition Pre-Training
* This paper has been accepted by ICME 2022 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

MAP-SNN: Mapping Spike Activities with Multiplicity, Adaptability, and Plasticity into Bio-Plausible Spiking Neural Networks


Apr 21, 2022
Chengting Yu, Yangkai Du, Mufeng Chen, Aili Wang, Gaoang Wang, Erping Li

Add code
Alert button

Figure 1 for MAP-SNN: Mapping Spike Activities with Multiplicity, Adaptability, and Plasticity into Bio-Plausible Spiking Neural Networks
Figure 2 for MAP-SNN: Mapping Spike Activities with Multiplicity, Adaptability, and Plasticity into Bio-Plausible Spiking Neural Networks
Figure 3 for MAP-SNN: Mapping Spike Activities with Multiplicity, Adaptability, and Plasticity into Bio-Plausible Spiking Neural Networks
Figure 4 for MAP-SNN: Mapping Spike Activities with Multiplicity, Adaptability, and Plasticity into Bio-Plausible Spiking Neural Networks

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Disjoint Contrastive Regression Learning for Multi-Sourced Annotations


Dec 31, 2021
Xiaoqian Ruan, Gaoang Wang

Add code
Alert button

Figure 1 for Disjoint Contrastive Regression Learning for Multi-Sourced Annotations
Figure 2 for Disjoint Contrastive Regression Learning for Multi-Sourced Annotations
Figure 3 for Disjoint Contrastive Regression Learning for Multi-Sourced Annotations
Figure 4 for Disjoint Contrastive Regression Learning for Multi-Sourced Annotations

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

ActiveMatch: End-to-end Semi-supervised Active Representation Learning


Oct 06, 2021
Xinkai Yuan, Zilinghan Li, Gaoang Wang

Add code
Alert button

Figure 1 for ActiveMatch: End-to-end Semi-supervised Active Representation Learning
Figure 2 for ActiveMatch: End-to-end Semi-supervised Active Representation Learning
Figure 3 for ActiveMatch: End-to-end Semi-supervised Active Representation Learning
Figure 4 for ActiveMatch: End-to-end Semi-supervised Active Representation Learning
* 5 pages, 2 figures, submitted to ICASSP 2022 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Track without Appearance: Learn Box and Tracklet Embedding with Local and Global Motion Patterns for Vehicle Tracking


Aug 13, 2021
Gaoang Wang, Renshu Gu, Zuozhu Liu, Weijie Hu, Mingli Song, Jenq-Neng Hwang

Add code
Alert button

Figure 1 for Track without Appearance: Learn Box and Tracklet Embedding with Local and Global Motion Patterns for Vehicle Tracking
Figure 2 for Track without Appearance: Learn Box and Tracklet Embedding with Local and Global Motion Patterns for Vehicle Tracking
Figure 3 for Track without Appearance: Learn Box and Tracklet Embedding with Local and Global Motion Patterns for Vehicle Tracking
Figure 4 for Track without Appearance: Learn Box and Tracklet Embedding with Local and Global Motion Patterns for Vehicle Tracking

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
>>