W
Weigang Zhang
Researcher at Harbin Institute of Technology
Publications - 110
Citations - 2835
Weigang Zhang is an academic researcher from Harbin Institute of Technology. The author has contributed to research in topics: Vitiligo & Video tracking. The author has an hindex of 24, co-authored 105 publications receiving 1788 citations. Previous affiliations of Weigang Zhang include Fourth Military Medical University & Chinese Academy of Sciences.
Papers
More filters
Book ChapterDOI
The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking
Dawei Du,Yuankai Qi,Hongyang Yu,Yifan Yang,Kaiwen Duan,Guorong Li,Weigang Zhang,Qingming Huang,Qi Tian +8 more
TL;DR: In this article, a new unconstrained UAV benchmark dataset is proposed for object detection, single object tracking, and multiple object tracking with new level challenges, including high density, small object, and camera motion, and a detailed quantitative study is performed using most recent state-of-the-art algorithms for each task.
Book ChapterDOI
Less Is More: Picking Informative Frames for Video Captioning
TL;DR: In this article, a reinforcement learning-based method is proposed to select informative frame picking in video captioning, where the reward of each frame picking action is designed by maximizing visual diversity and minimizing discrepancy between generated caption and the ground truth.
Posted Content
The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking
Dawei Du,Yuankai Qi,Hongyang Yu,Yifan Yang,Kaiwen Duan,Guorong Li,Weigang Zhang,Qingming Huang,Qi Tian +8 more
TL;DR: In this article, a new unconstrained UAV benchmark is proposed for object detection, single object tracking, and multiple object tracking in complex scenarios with new level challenges, and the current state-of-the-art methods perform relative worse on the dataset, due to the new challenges appeared in UAV based real scenes, e.g., high density, small object, and camera motion.
Posted Content
Less Is More: Picking Informative Frames for Video Captioning
TL;DR: A reinforcement-learning-based procedure to train the network sequentially, where the reward of each frame picking action is designed by maximizing visual diversity and minimizing textual discrepancy, so that a compact frame subset can be selected to represent the visual information and perform video captioning without performance degradation.
Proceedings ArticleDOI
Deep Unsupervised Convolutional Domain Adaptation
TL;DR: Deep Unsupervised Convolutional Domain Adaptation DUCDA method is proposed, which jointly minimizes the supervised classification loss of labeled source data and the unsupervised correlation alignment loss measured on both convolutional layers and fully connected layers.