63 citations · 174 across the 15 of their papers we have counts for
15 papers
Long-Short Temporal Co-Teaching for Weakly Supervised Video Anomaly Detection
Shengyang Sun, Xiaojin Gong
Weakly supervised video anomaly detection (WS-VAD) is a challenging problem that aims to learn VAD models only with video-level annotations. In this work, we propose a Long-Short T…
Hierarchical Semantic Contrast for Scene-aware Video Anomaly Detection
Shengyang Sun, Xiaojin Gong
Increasing scene-awareness is a key challenge in video anomaly detection (VAD). In this work, we propose a hierarchical semantic contrast (HSC) method to learn a scene-aware VAD mo…
Transformer Based Multi-Grained Features for Unsupervised Person Re-Identification
Jiachen Li, Menglin Wang, Xiaojin Gong
Multi-grained features extracted from convolutional neural networks (CNNs) have demonstrated their strong discrimination ability in supervised person re-identification (Re-ID) task…
Online Convolutional Re-parameterization
Mu Hu, Junyi Feng, Jiashen Hua +4
Structural re-parameterization has drawn increasing attention in various computer vision tasks. It aims at improving the performance of deep models without introducing any inferenc…
Offline-Online Associated Camera-Aware Proxies for Unsupervised Person Re-identification
Menglin Wang, Jiachen Li, Baisheng Lai +2
Recently, unsupervised person re-identification (Re-ID) has received increasing research attention due to its potential for label-free applications. A promising way to address unsu…
PENet: Towards Precise and Efficient Image Guided Depth Completion
Mu Hu, Shuling Wang, Bin Li +3
Image guided depth completion is the task of generating a dense depth map from a sparse depth map and a high quality image. In this task, how to fuse the color and depth modalities…
Self-supervised Visual-LiDAR Odometry with Flip Consistency
Bin Li, Mu Hu, Shuling Wang +2
Most learning-based methods estimate ego-motion by utilizing visual sensors, which suffer from dramatic lighting variations and textureless scenarios. In this paper, we incorporate…
Camera-aware Proxies for Unsupervised Person Re-Identification
Menglin Wang, Baisheng Lai, Jianqiang Huang +2
This paper tackles the purely unsupervised person re-identification (Re-ID) problem that requires no annotations. Some previous methods adopt clustering techniques to generate pseu…
Towards Precise Intra-camera Supervised Person Re-identification
Menglin Wang, Baisheng Lai, Haokun Chen +3
Intra-camera supervision (ICS) for person re-identification (Re-ID) assumes that identity labels are independently annotated within each camera view and no inter-camera identity as…
Saliency Guided Self-attention Network for Weakly and Semi-supervised Semantic Segmentation
Qi Yao, Xiaojin Gong
Weakly supervised semantic segmentation (WSSS) using only image-level labels can greatly reduce the annotation cost and therefore has attracted considerable research interest. Howe…
Adaptive Fusion for RGB-D Salient Object Detection
Ningning Wang, Xiaojin Gong
RGB-D salient object detection aims to identify the most visually distinctive objects in a pair of color and depth images. Based upon an observation that most of the salient object…
Deep Active Learning for Video-based Person Re-identification
Menglin Wang, Baisheng Lai, Zhongming Jin +3
It is prohibitively expensive to annotate a large-scale video-based person re-identification (re-ID) dataset, which makes fully supervised methods inapplicable to real-world deploy…
Dynamic Spatio-temporal Graph-based CNNs for Traffic Prediction
Ken Chen, Fei Chen, Baisheng Lai +8
Forecasting future traffic flows from previous ones is a challenging problem because of their complex and dynamic nature of spatio-temporal structures. Most existing graph-based CN…
Saliency Guided End-to-End Learning for Weakly Supervised Object Detection
Baisheng Lai, Xiaojin Gong
Weakly supervised object detection (WSOD), which is the problem of learning detectors using only image-level labels, has been attracting more and more interest. However, this probl…
Fusion Based Holistic Road Scene Understanding
Wenqi Huang, Xiaojin Gong
This paper addresses the problem of holistic road scene understanding based on the integration of visual and range data. To achieve the grand goal, we propose an approach that join…