60 citations · 203 across the 22 of their papers we have counts for
22 papers
DEBATE: A Dataset for Disentangling Textual Ambiguity in Mandarin Through Speech
Haotian Guo, Jing Han, Yongfeng Tu +5
Despite extensive research on textual and visual disambiguation, disambiguation through speech (DTS) remains underexplored. This is largely due to the lack of high-quality datasets…
Adaptive Rotated Convolution for Rotated Object Detection
Yifan Pu, Yiru Wang, Zhuofan Xia +6
Rotated object detection aims to identify and locate objects in images with arbitrary orientation. In this scenario, the oriented directions of objects vary considerably across dif…
Cross Domain Object Detection by Target-Perceived Dual Branch Distillation
Mengzhe He, Yali Wang, Jiaxi Wu +6
Cross domain object detection is a realistic and challenging task in the wild. It suffers from performance degradation due to large shift of data distributions and lack of instance…
Target-Relevant Knowledge Preservation for Multi-Source Domain Adaptive Object Detection
Jiaxi Wu, Jiaxin Chen, Mengzhe He +7
Domain adaptive object detection (DAOD) is a promising way to alleviate performance drop of detectors in new scenes. Albeit great effort made in single source domain adaptation, a…
Unsupervised Learning of Accurate Siamese Tracking
Qiuhong Shen, Lei Qiao, Jinyang Guo +7
Unsupervised learning has been popular in various computer vision tasks, including visual object tracking. However, prior unsupervised tracking approaches rely heavily on spatial s…
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…
Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking
Boyu Chen, Peixia Li, Lei Bai +6
Exploiting a general-purpose neural architecture to replace hand-wired designs or inductive biases has recently drawn extensive interest. However, existing tracking approaches rely…
Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection
Shoubin Yu, Zhongyin Zhao, Haoshu Fang +6
Anomaly detection in surveillance videos is challenging and important for ensuring public security. Different from pixel-based anomaly detection methods, pose-based methods utilize…
Transferable Knowledge-Based Multi-Granularity Aggregation Network for Temporal Action Localization: Submission to ActivityNet Challenge 2021
Haisheng Su, Peiqin Zhuang, Yukun Li +4
This technical report presents an overview of our solution used in the submission to 2021 HACS Temporal Action Localization Challenge on both Supervised Learning Track and Weakly-S…
TSI: Temporal Saliency Integration for Video Action Recognition
Haisheng Su, Kunchang Li, Jinyuan Feng +4
Efficient spatiotemporal modeling is an important yet challenging problem for video action recognition. Existing state-of-the-art methods exploit neighboring feature differences to…
Temporal Context Aggregation Network for Temporal Action Proposal Refinement
Zhiwu Qing, Haisheng Su, Weihao Gan +7
Temporal action proposal generation aims to estimate temporal intervals of actions in untrimmed videos, which is a challenging yet important task in the video understanding field.…
Real-Time Visual Object Tracking via Few-Shot Learning
Jinghao Zhou, Bo Li, Peng Wang +5
Visual Object Tracking (VOT) can be seen as an extended task of Few-Shot Learning (FSL). While the concept of FSL is not new in tracking and has been previously applied by prior wo…
Higher Performance Visual Tracking with Dual-Modal Localization
Jinghao Zhou, Bo Li, Lei Qiao +5
Visual Object Tracking (VOT) has synchronous needs for both robustness and accuracy. While most existing works fail to operate simultaneously on both, we investigate in this work t…
Learning Statistical Texture for Semantic Segmentation
Lanyun Zhu, Deyi Ji, Shiping Zhu +3
Existing semantic segmentation works mainly focus on learning the contextual information in high-level semantic features with CNNs. In order to maintain a precise boundary, low-lev…
Context-Aware Graph Convolution Network for Target Re-identification
Deyi Ji, Haoran Wang, Hanzhe Hu +3
Most existing re-identification methods focus on learning robust and discriminative features with deep convolution networks. However, many of them consider content similarity separ…
SAMOT: Switcher-Aware Multi-Object Tracking and Still Another MOT Measure
Weitao Feng, Zhihao Hu, Baopu Li +3
Multi-Object Tracking (MOT) is a popular topic in computer vision. However, identity issue, i.e., an object is wrongly associated with another object of a different identity, still…
Collaborative Distillation in the Parameter and Spectrum Domains for Video Action Recognition
Haisheng Su, Jing Su, Dongliang Wang +5
Recent years have witnessed the significant progress of action recognition task with deep networks. However, most of current video networks require large memory and computational r…
BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation
Haisheng Su, Weihao Gan, Wei Wu +2
Generating human action proposals in untrimmed videos is an important yet challenging task with wide applications. Current methods often suffer from the noisy boundary locations an…
Class-wise Dynamic Graph Convolution for Semantic Segmentation
Hanzhe Hu, Deyi Ji, Weihao Gan +3
Recent works have made great progress in semantic segmentation by exploiting contextual information in a local or global manner with dilated convolutions, pyramid pooling or self-a…
Hierarchical Feature Embedding for Attribute Recognition
Jie Yang, Jiarou Fan, Yiru Wang +4
Attribute recognition is a crucial but challenging task due to viewpoint changes, illumination variations and appearance diversities, etc. Most of previous work only consider the a…
STM: SpatioTemporal and Motion Encoding for Action Recognition
Boyuan Jiang, Mengmeng Wang, Weihao Gan +2
Spatiotemporal and motion features are two complementary and crucial information for video action recognition. Recent state-of-the-art methods adopt a 3D CNN stream to learn spatio…
Dynamic Curriculum Learning for Imbalanced Data Classification
Yiru Wang, Weihao Gan, Jie Yang +2
Human attribute analysis is a challenging task in the field of computer vision, since the data is largely imbalance-distributed. Common techniques such as re-sampling and cost-sens…