70 citations · 219 across the 14 of their papers we have counts for
15 papers
When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanism
Guangting Wang, Yucheng Zhao, Chuanxin Tang +2
Attention mechanism has been widely believed as the key to success of vision transformers (ViTs), since it provides a flexible and powerful way to model spatial relationships. Howe…
Sparse MLP for Image Recognition: Is Self-Attention Really Necessary?
Chuanxin Tang, Yucheng Zhao, Guangting Wang +3
Transformers have sprung up in the field of computer vision. In this work, we explore whether the core self-attention module in Transformer is the key to achieving excellent perfor…
Self-Supervised Visual Representations Learning by Contrastive Mask Prediction
Yucheng Zhao, Guangting Wang, Chong Luo +2
Advanced self-supervised visual representation learning methods rely on the instance discrimination (ID) pretext task. We point out that the ID task has an implicit semantic consis…
A Battle of Network Structures: An Empirical Study of CNN, Transformer, and MLP
Yucheng Zhao, Guangting Wang, Chuanxin Tang +3
Convolutional neural networks (CNN) are the dominant deep neural network (DNN) architecture for computer vision. Recently, Transformer and multi-layer perceptron (MLP)-based models…
Unsupervised Visual Representation Learning by Tracking Patches in Video
Guangting Wang, Yizhou Zhou, Chong Luo +3
Inspired by the fact that human eyes continue to develop tracking ability in early and middle childhood, we propose to use tracking as a proxy task for a computer vision system to…
General-Purpose Speech Representation Learning through a Self-Supervised Multi-Granularity Framework
Yucheng Zhao, Dacheng Yin, Chong Luo +4
This paper presents a self-supervised learning framework, named MGF, for general-purpose speech representation learning. In the design of MGF, speech hierarchy is taken into consid…
VAE^2: Preventing Posterior Collapse of Variational Video Predictions in the Wild
Yizhou Zhou, Chong Luo, Xiaoyan Sun +2
Predicting future frames of video sequences is challenging due to the complex and stochastic nature of the problem. Video prediction methods based on variational auto-encoders (VAE…
Online Speaker Diarization with Relation Network
Xiang Li, Yucheng Zhao, Chong Luo +1
In this paper, we propose an online speaker diarization system based on Relation Network, named RenoSD. Unlike conventional diariztion systems which consist of several independentl…
Spatiotemporal Fusion in 3D CNNs: A Probabilistic View
Yizhou Zhou, Xiaoyan Sun, Chong Luo +2
Despite the success in still image recognition, deep neural networks for spatiotemporal signal tasks (such as human action recognition in videos) still suffers from low efficacy an…
Tracking by Instance Detection: A Meta-Learning Approach
Guangting Wang, Chong Luo, Xiaoyan Sun +2
We consider the tracking problem as a special type of object detection problem, which we call instance detection. With proper initialization, a detector can be quickly converted in…
PHASEN: A Phase-and-Harmonics-Aware Speech Enhancement Network
Dacheng Yin, Chong Luo, Zhiwei Xiong +1
Time-frequency (T-F) domain masking is a mainstream approach for single-channel speech enhancement. Recently, focuses have been put to phase prediction in addition to amplitude pre…
Posterior-Guided Neural Architecture Search
Yizhou Zhou, Xiaoyan Sun, Chong Luo +2
The emergence of neural architecture search (NAS) has greatly advanced the research on network design. Recent proposals such as gradient-based methods or one-shot approaches signif…
SPM-Tracker: Series-Parallel Matching for Real-Time Visual Object Tracking
Guangting Wang, Chong Luo, Zhiwei Xiong +1
The greatest challenge facing visual object tracking is the simultaneous requirements on robustness and discrimination power. In this paper, we propose a SiamFC-based tracker, name…
Towards a Better Match in Siamese Network Based Visual Object Tracker
Anfeng He, Chong Luo, Xinmei Tian +1
Recently, Siamese network based trackers have received tremendous interest for their fast tracking speed and high performance. Despite the great success, this tracking framework st…
A Twofold Siamese Network for Real-Time Object Tracking
Anfeng He, Chong Luo, Xinmei Tian +1
Observing that Semantic features learned in an image classification task and Appearance features learned in a similarity matching task complement each other, we build a twofold Sia…