1.6k citations · 3.7k across the 93 of their papers we have counts for
27 papers · 1 filter
SelectAugment: Hierarchical Deterministic Sample Selection for Data Augmentation
Shiqi Lin, Zhizheng Zhang, Xin Li +2
Data augmentation (DA) has been widely investigated to facilitate model optimization in many tasks. However, in most cases, data augmentation is randomly performed for each trainin…
Learning Tracking Representations via Dual-Branch Fully Transformer Networks
Fei Xie, Chunyu Wang, Guangting Wang +2
We present a Siamese-like Dual-branch network based on solely Transformers for tracking. Given a template and a search image, we divide them into non-overlapping patches and extrac…
Lifelong Unsupervised Domain Adaptive Person Re-identification with Coordinated Anti-forgetting and Adaptation
Zhipeng Huang, Zhizheng Zhang, Cuiling Lan +6
Unsupervised domain adaptive person re-identification (ReID) has been extensively investigated to mitigate the adverse effects of domain gaps. Those works assume the target domain…
Multi-Scale Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition
Pengfei Zhang, Cuiling Lan, Wenjun Zeng +3
Skeleton data is of low dimension. However, there is a trend of using very deep and complicated feedforward neural networks to model the skeleton sequence without considering the c…
Confounder Identification-free Causal Visual Feature Learning
Xin Li, Zhizheng Zhang, Guoqiang Wei +4
Confounders in deep learning are in general detrimental to model's generalization where they infiltrate feature representations. Therefore, learning causal features that are free o…
Skeleton-Based Mutually Assisted Interacted Object Localization and Human Action Recognition
Liang Xu, Cuiling Lan, Wenjun Zeng +1
Skeleton data carries valuable motion information and is widely explored in human action recognition. However, not only the motion information but also the interaction with the env…
Zero-Shot Text-to-Speech for Text-Based Insertion in Audio Narration
Chuanxin Tang, Chong Luo, Zhiyuan Zhao +3
Given a piece of speech and its transcript text, text-based speech editing aims to generate speech that can be seamlessly inserted into the given speech by editing the transcript.…
WEDGE: Web-Image Assisted Domain Generalization for Semantic Segmentation
Namyup Kim, Taeyoung Son, Jaehyun Pahk +3
Domain generalization for semantic segmentation is highly demanded in real applications, where a trained model is expected to work well in previously unseen domains. One challenge…
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…
Pose-Guided Feature Learning with Knowledge Distillation for Occluded Person Re-Identification
Kecheng Zheng, Cuiling Lan, Wenjun Zeng +3
Occluded person re-identification (ReID) aims to match person images with occlusion. It is fundamentally challenging because of the serious occlusion which aggravates the misalignm…
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…
VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wild
Yifu Zhang, Chunyu Wang, Xinggang Wang +2
We present VoxelTrack for multi-person 3D pose estimation and tracking from a few cameras which are separated by wide baselines. It employs a multi-branch network to jointly estima…
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…
ToAlign: Task-oriented Alignment for Unsupervised Domain Adaptation
Guoqiang Wei, Cuiling Lan, Wenjun Zeng +2
Unsupervised domain adaptive classifcation intends to improve the classifcation performance on unlabeled target domain. To alleviate the adverse effect of domain shift, many approa…
PlayVirtual: Augmenting Cycle-Consistent Virtual Trajectories for Reinforcement Learning
Tao Yu, Cuiling Lan, Wenjun Zeng +3
Learning good feature representations is important for deep reinforcement learning (RL). However, with limited experience, RL often suffers from data inefficiency for training. For…
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…
Understanding Mobile GUI: from Pixel-Words to Screen-Sentences
Jingwen Fu, Xiaoyi Zhang, Yuwang Wang +3
The ubiquity of mobile phones makes mobile GUI understanding an important task. Most previous works in this domain require human-created metadata of screens (e.g. View Hierarchy) d…
S2R-DepthNet: Learning a Generalizable Depth-specific Structural Representation
Xiaotian Chen, Yuwang Wang, Xuejin Chen +1
Human can infer the 3D geometry of a scene from a sketch instead of a realistic image, which indicates that the spatial structure plays a fundamental role in understanding the dept…
Disentanglement-based Cross-Domain Feature Augmentation for Effective Unsupervised Domain Adaptive Person Re-identification
Zhizheng Zhang, Cuiling Lan, Wenjun Zeng +4
Unsupervised domain adaptive (UDA) person re-identification (ReID) aims to transfer the knowledge from the labeled source domain to the unlabeled target domain for person matching.…
MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptation
Guoqiang Wei, Cuiling Lan, Wenjun Zeng +1
For unsupervised domain adaptation (UDA), to alleviate the effect of domain shift, many approaches align the source and target domains in the feature space by adversarial learning…
Re-energizing Domain Discriminator with Sample Relabeling for Adversarial Domain Adaptation
Xin Jin, Cuiling Lan, Wenjun Zeng +1
Many unsupervised domain adaptation (UDA) methods exploit domain adversarial training to align the features to reduce domain gap, where a feature extractor is trained to fool a dom…
Generalizing to Unseen Domains: A Survey on Domain Generalization
Jindong Wang, Cuiling Lan, Chang Liu +6
Machine learning systems generally assume that the training and testing distributions are the same. To this end, a key requirement is to develop models that can generalize to unsee…
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…
Rethinking Content and Style: Exploring Bias for Unsupervised Disentanglement
Xuanchi Ren, Tao Yang, Yuwang Wang +1
Content and style (C-S) disentanglement intends to decompose the underlying explanatory factors of objects into two independent subspaces. From the unsupervised disentanglement per…