D
Dan Xu
Researcher at Hong Kong University of Science and Technology
Publications - 143
Citations - 5755
Dan Xu is an academic researcher from Hong Kong University of Science and Technology. The author has contributed to research in topics: Computer science & Convolutional neural network. The author has an hindex of 30, co-authored 125 publications receiving 3693 citations. Previous affiliations of Dan Xu include University of Texas at Austin & Chinese Academy of Sciences.
Papers
More filters
Proceedings ArticleDOI
Learning Deep Representations of Appearance and Motion for Anomalous Event Detection
TL;DR: This work proposes Appearance and Motion DeepNet (AMDN) which utilizes deep neural networks to automatically learn feature representations, and introduces a novel double fusion framework, combining both the benefits of traditional early fusion and late fusion strategies.
Proceedings ArticleDOI
Multi-scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimation
TL;DR: In this article, a deep model which fuses complementary information derived from multiple CNN side outputs is proposed, which is obtained by means of continuous Conditional Random Fields (CRFs).
Journal ArticleDOI
Detecting anomalous events in videos by learning deep representations of appearance and motion
TL;DR: A novel double fusion framework is introduced, combining the benefits of traditional early fusion and late fusion strategies, which is extensively evaluated on publicly available video surveillance datasets including UCSD pedestian, Subway, and Train, showing competitive performance with respect to state of the art approaches.
Proceedings ArticleDOI
PAD-Net: Multi-tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing
TL;DR: This paper proposes a novel multi-task guided prediction-and-distillation network (PAD-Net), which first predicts a set of intermediate auxiliary tasks ranging from low level to high level, and then the predictions from these intermediate Auxiliary tasks are utilized as multi-modal input via the authors' proposed multi- modal distillation modules for the final tasks.
Proceedings ArticleDOI
Group Consistent Similarity Learning via Deep CRF for Person Re-identification
TL;DR: This paper incorporates constraints on large image groups by combining the CRF with deep neural networks to learn the "local similarity" metrics for image pairs while taking into account the dependencies from all the images in a group, forming "group similarities".