1.6k citations · 3.7k across the 93 of their papers we have counts for
95 papers
Diffusion Models for Image Restoration and Enhancement: A Comprehensive Survey
Xin Li, Yulin Ren, Xin Jin +5
Image restoration (IR) has been an indispensable and challenging task in the low-level vision field, which strives to improve the subjective quality of images distorted by various…
Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning
Qi Wang, Junming Yang, Yunbo Wang +3
Training offline RL models using visual inputs poses two significant challenges, i.e., the overfitting problem in representation learning and the overestimation bias for expected f…
Inpaint Anything: Segment Anything Meets Image Inpainting
Tao Yu, Runseng Feng, Ruoyu Feng +4
Modern image inpainting systems, despite the significant progress, often struggle with mask selection and holes filling. Based on Segment-Anything Model (SAM), we make the first at…
[CLS] Token is All You Need for Zero-Shot Semantic Segmentation
Letian Wu, Wenyao Zhang, Tengping Jiang +3
In this paper, we propose an embarrassingly simple yet highly effective zero-shot semantic segmentation (ZS3) method, based on the pre-trained vision-language model CLIP. First, ou…
NaviNeRF: NeRF-based 3D Representation Disentanglement by Latent Semantic Navigation
Baao Xie, Bohan Li, Zequn Zhang +4
3D representation disentanglement aims to identify, decompose, and manipulate the underlying explanatory factors of 3D data, which helps AI fundamentally understand our 3D world. T…
Bridging Stereo Geometry and BEV Representation with Reliable Mutual Interaction for Semantic Scene Completion
Bohan Li, Yasheng Sun, Zhujin Liang +6
3D semantic scene completion (SSC) is an ill-posed perception task that requires inferring a dense 3D scene from limited observations. Previous camera-based methods struggle to pre…
Automatic Intrinsic Reward Shaping for Exploration in Deep Reinforcement Learning
Mingqi Yuan, Bo Li, Xin Jin +1
We present AIRS: Automatic Intrinsic Reward Shaping that intelligently and adaptively provides high-quality intrinsic rewards to enhance exploration in reinforcement learning (RL).…
Tackling Visual Control via Multi-View Exploration Maximization
Mingqi Yuan, Xin Jin, Bo Li +1
We present MEM: Multi-view Exploration Maximization for tackling complex visual control tasks. To the best of our knowledge, MEM is the first approach that combines multi-view repr…
Rewarding Episodic Visitation Discrepancy for Exploration in Reinforcement Learning
Mingqi Yuan, Bo Li, Xin Jin +1
Exploration is critical for deep reinforcement learning in complex environments with high-dimensional observations and sparse rewards. To address this problem, recent approaches pr…
Robust Multi-Object Tracking by Marginal Inference
Yifu Zhang, Chunyu Wang, Xinggang Wang +2
Multi-object tracking in videos requires to solve a fundamental problem of one-to-one assignment between objects in adjacent frames. Most methods address the problem by first disca…
VirtualPose: Learning Generalizable 3D Human Pose Models from Virtual Data
Jiajun Su, Chunyu Wang, Xiaoxuan Ma +2
While monocular 3D pose estimation seems to have achieved very accurate results on the public datasets, their generalization ability is largely overlooked. In this work, we perform…
ReSTR: Convolution-free Referring Image Segmentation Using Transformers
Namyup Kim, Dongwon Kim, Cuiling Lan +2
Referring image segmentation is an advanced semantic segmentation task where target is not a predefined class but is described in natural language. Most of existing methods for thi…
Correlation-Aware Deep Tracking
Fei Xie, Chunyu Wang, Guangting Wang +3
Robustness and discrimination power are two fundamental requirements in visual object tracking. In most tracking paradigms, we find that the features extracted by the popular Siame…
ActFormer: A GAN-based Transformer towards General Action-Conditioned 3D Human Motion Generation
Liang Xu, Ziyang Song, Dongliang Wang +9
We present a GAN-based Transformer for general action-conditioned 3D human motion generation, including not only single-person actions but also multi-person interactive actions. Ou…
Retriever: Learning Content-Style Representation as a Token-Level Bipartite Graph
Dacheng Yin, Xuanchi Ren, Chong Luo +3
This paper addresses the unsupervised learning of content-style decomposed representation. We first give a definition of style and then model the content-style representation as a…
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…
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…