5 citations · 28 across the 15 of their papers we have counts for
15 papers
Learning Restoration is Not Enough: Transfering Identical Mapping for Single-Image Shadow Removal
Xiaoguang Li, Qing Guo, Pingping Cai +3
Shadow removal is to restore shadow regions to their shadow-free counterparts while leaving non-shadow regions unchanged. State-of-the-art shadow removal methods train deep neural…
Leveraging Inpainting for Single-Image Shadow Removal
Xiaoguang Li, Qing Guo, Rabab Abdelfattah +4
Fully-supervised shadow removal methods achieve the best restoration qualities on public datasets but still generate some shadow remnants. One of the reasons is the lack of large-s…
From a Bird's Eye View to See: Joint Camera and Subject Registration without the Camera Calibration
Zekun Qian, Ruize Han, Wei Feng +2
We tackle a new problem of multi-view camera and subject registration in the bird's eye view (BEV) without pre-given camera calibration. This is a very challenging problem since it…
A Benchmark of Video-Based Clothes-Changing Person Re-Identification
Likai Wang, Xiangqun Zhang, Ruize Han +4
Person re-identification (Re-ID) is a classical computer vision task and has achieved great progress so far. Recently, long-term Re-ID with clothes-changing has attracted increasin…
From Indoor To Outdoor: Unsupervised Domain Adaptive Gait Recognition
Likai Wang, Ruize Han, Wei Feng +1
Gait recognition is an important AI task, which has been progressed rapidly with the development of deep learning. However, existing learning based gait recognition methods mainly…
View-Invariant Skeleton-based Action Recognition via Global-Local Contrastive Learning
Cunling Bian, Wei Feng, Fanbo Meng +1
Skeleton-based human action recognition has been drawing more interest recently due to its low sensitivity to appearance changes and the accessibility of more skeleton data. Howeve…
MISF: Multi-level Interactive Siamese Filtering for High-Fidelity Image Inpainting
Xiaoguang Li, Qing Guo, Di Lin +3
Although achieving significant progress, existing deep generative inpainting methods are far from real-world applications due to the low generalization across different scenes. As…
Self-supervised Social Relation Representation for Human Group Detection
Jiacheng Li, Ruize Han, Haomin Yan +3
Human group detection, which splits crowd of people into groups, is an important step for video-based human social activity analysis. The core of human group detection is the human…
Panoramic Human Activity Recognition
Ruize Han, Haomin Yan, Jiacheng Li +3
To obtain a more comprehensive activity understanding for a crowded scene, in this paper, we propose a new problem of panoramic human activity recognition (PAR), which aims to simu…
Uncertainty-Aware Cascaded Dilation Filtering for High-Efficiency Deraining
Qing Guo, Jingyang Sun, Felix Juefei-Xu +4
Deraining is a significant and fundamental computer vision task, aiming to remove the rain streaks and accumulations in an image or video captured under a rainy day. Existing derai…
Style Mixing and Patchwise Prototypical Matching for One-Shot Unsupervised Domain Adaptive Semantic Segmentation
Xinyi Wu, Zhenyao Wu, Yuhang Lu +2
In this paper, we tackle the problem of one-shot unsupervised domain adaptation (OSUDA) for semantic segmentation where the segmentors only see one unlabeled target image during tr…
Multi-Domain Multi-Task Rehearsal for Lifelong Learning
Fan Lyu, Shuai Wang, Wei Feng +3
Rehearsal, seeking to remind the model by storing old knowledge in lifelong learning, is one of the most effective ways to mitigate catastrophic forgetting, i.e., biased forgetting…
MUTATT: Visual-Textual Mutual Guidance for Referring Expression Comprehension
Shuai Wang, Fan Lyu, Wei Feng +1
Referring expression comprehension (REC) aims to localize a text-related region in a given image by a referring expression in natural language. Existing methods focus on how to bui…
Deep Poisoning: Towards Robust Image Data Sharing against Visual Disclosure
Hao Guo, Brian Dolhansky, Eric Hsin +3
Due to respectively limited training data, different entities addressing the same vision task based on certain sensitive images may not train a robust deep network. This paper intr…
Object Detection with Mask-based Feature Encoding
Xiaochuan Fan, Hao Guo, Kang Zheng +2
Region-based Convolutional Neural Networks (R-CNNs) have achieved great success in the field of object detection. The existing R-CNNs usually divide a Region-of-Interest (ROI) into…