116 citations · 386 across the 29 of their papers we have counts for
29 papers
Fast Segment Anything
Xu Zhao, Wenchao Ding, Yongqi An +5
The recently proposed segment anything model (SAM) has made a significant influence in many computer vision tasks. It is becoming a foundation step for many high-level tasks, like…
FreConv: Frequency Branch-and-Integration Convolutional Networks
Zhaowen Li, Xu Zhao, Peigeng Ding +4
Recent researches indicate that utilizing the frequency information of input data can enhance the performance of networks. However, the existing popular convolutional structure is…
ZBS: Zero-shot Background Subtraction via Instance-level Background Modeling and Foreground Selection
Yongqi An, Xu Zhao, Tao Yu +4
Background subtraction (BGS) aims to extract all moving objects in the video frames to obtain binary foreground segmentation masks. Deep learning has been widely used in this field…
Temporal-Channel Topology Enhanced Network for Skeleton-Based Action Recognition
Jinzhao Luo, Lu Zhou, Guibo Zhu +3
Skeleton-based action recognition has become popular in recent years due to its efficiency and robustness. Most current methods adopt graph convolutional network (GCN) for topology…
Efficient Masked Autoencoders with Self-Consistency
Zhaowen Li, Yousong Zhu, Zhiyang Chen +5
Inspired by the masked language modeling (MLM) in natural language processing tasks, the masked image modeling (MIM) has been recognized as a strong self-supervised pre-training me…
Masked Contrastive Pre-Training for Efficient Video-Text Retrieval
Fangxun Shu, Biaolong Chen, Yue Liao +6
We present a simple yet effective end-to-end Video-language Pre-training (VidLP) framework, Masked Contrastive Video-language Pretraining (MAC), for video-text retrieval tasks. Our…
Obj2Seq: Formatting Objects as Sequences with Class Prompt for Visual Tasks
Zhiyang Chen, Yousong Zhu, Zhaowen Li +8
Visual tasks vary a lot in their output formats and concerned contents, therefore it is hard to process them with an identical structure. One main obstacle lies in the high-dimensi…
Transfering Low-Frequency Features for Domain Adaptation
Zhaowen Li, Xu Zhao, Chaoyang Zhao +2
Previous unsupervised domain adaptation methods did not handle the cross-domain problem from the perspective of frequency for computer vision. The images or feature maps of differe…
Plug-and-Play Pseudo Label Correction Network for Unsupervised Person Re-identification
Tianyi Yan, Kuan Zhu, Haiyun guo +3
Clustering-based methods, which alternate between the generation of pseudo labels and the optimization of the feature extraction network, play a dominant role in both unsupervised…
UniVIP: A Unified Framework for Self-Supervised Visual Pre-training
Zhaowen Li, Yousong Zhu, Fan Yang +9
Self-supervised learning (SSL) holds promise in leveraging large amounts of unlabeled data. However, the success of popular SSL methods has limited on single-centric-object images…
PASS: Part-Aware Self-Supervised Pre-Training for Person Re-Identification
Kuan Zhu, Haiyun Guo, Tianyi Yan +3
In person re-identification (ReID), very recent researches have validated pre-training the models on unlabelled person images is much better than on ImageNet. However, these resear…
Pruning-aware Sparse Regularization for Network Pruning
Nanfei Jiang, Xu Zhao, Chaoyang Zhao +3
Structural neural network pruning aims to remove the redundant channels in the deep convolutional neural networks (CNNs) by pruning the filters of less importance to the final outp…
Multi-initialization Optimization Network for Accurate 3D Human Pose and Shape Estimation
Zhiwei Liu, Xiangyu Zhu, Lu Yang +7
3D human pose and shape recovery from a monocular RGB image is a challenging task. Existing learning based methods highly depend on weak supervision signals, e.g. 2D and 3D joint l…
DPT: Deformable Patch-based Transformer for Visual Recognition
Zhiyang Chen, Yousong Zhu, Chaoyang Zhao +4
Transformer has achieved great success in computer vision, while how to split patches in an image remains a problem. Existing methods usually use a fixed-size patch embedding which…
OPT: Omni-Perception Pre-Trainer for Cross-Modal Understanding and Generation
Jing Liu, Xinxin Zhu, Fei Liu +8
In this paper, we propose an Omni-perception Pre-Trainer (OPT) for cross-modal understanding and generation, by jointly modeling visual, text and audio resources. OPT is constructe…
MST: Masked Self-Supervised Transformer for Visual Representation
Zhaowen Li, Zhiyang Chen, Fan Yang +8
Transformer has been widely used for self-supervised pre-training in Natural Language Processing (NLP) and achieved great success. However, it has not been fully explored in visual…
Adaptive Class Suppression Loss for Long-Tail Object Detection
Tong Wang, Yousong Zhu, Chaoyang Zhao +3
To address the problem of long-tail distribution for the large vocabulary object detection task, existing methods usually divide the whole categories into several groups and treat…
AAformer: Auto-Aligned Transformer for Person Re-Identification
Kuan Zhu, Haiyun Guo, Shiliang Zhang +4
In person re-identification (re-ID), extracting part-level features from person images has been verified to be crucial to offer fine-grained information. Most of the existing CNN-b…
Identity-Guided Human Semantic Parsing for Person Re-Identification
Kuan Zhu, Haiyun Guo, Zhiwei Liu +2
Existing alignment-based methods have to employ the pretrained human parsing models to achieve the pixel-level alignment, and cannot identify the personal belongings (e.g., backpac…
Learning Feature Embeddings for Discriminant Model based Tracking
Linyu Zheng, Ming Tang, Yingying Chen +2
After observing that the features used in most online discriminatively trained trackers are not optimal, in this paper, we propose a novel and effective architecture to learn optim…
Semantic Alignment: Finding Semantically Consistent Ground-truth for Facial Landmark Detection
Zhiwei Liu, Xiangyu Zhu, Guosheng Hu +5
Recently, deep learning based facial landmark detection has achieved great success. Despite this, we notice that the semantic ambiguity greatly degrades the detection performance.…
Recurrent Calibration Network for Irregular Text Recognition
Yunze Gao, Yingying Chen, Jinqiao Wang +3
Scene text recognition has received increased attention in the research community. Text in the wild often possesses irregular arrangements, typically including perspective text, cu…
High-speed Tracking with Multi-kernel Correlation Filters
Ming Tang, Bin Yu, Fan Zhang +1
Correlation filter (CF) based trackers are currently ranked top in terms of their performances. Nevertheless, only some of them, such as KCF~\cite{henriques15} and MKCF~\cite{tangm…
Fast Kernelized Correlation Filters without Boundary Effect
Ming Tang, Linyu Zheng, Bin Yu +1
In recent years, correlation filter based trackers (CF trackers) have attracted much attention from the vision community because of their top performance in both localization accur…