activity
20172020
most citedMotion-Aware Feature for Improved Video Anomaly Detection

116 citations · 157 across the 6 of their papers we have counts for

collaborators

18 papers

cs.CV202035 cited

Improving Semantic Segmentation via Self-Training

Yi Zhu, Zhongyue Zhang, Chongruo Wu +6

Deep learning usually achieves the best results with complete supervision. In the case of semantic segmentation, this means that large amounts of pixelwise annotations are required…

cs.CV2020

ResNeSt: Split-Attention Networks

Hang Zhang, Chongruo Wu, Zhongyue Zhang +9

It is well known that featuremap attention and multi-path representation are important for visual recognition. In this paper, we present a modularized architecture, which applies t…

cs.CV2020

Motion-Excited Sampler: Video Adversarial Attack with Sparked Prior

Hu Zhang, Linchao Zhu, Yi Zhu +1

Deep neural networks are known to be susceptible to adversarial noise, which are tiny and imperceptible perturbations. Most of previous work on adversarial attack mainly focus on i…

cs.CV2019116 cited

Motion-Aware Feature for Improved Video Anomaly Detection

Yi Zhu, Shawn Newsam

Motivated by our observation that motion information is the key to good anomaly detection performance in video, we propose a temporal augmented network to learn a motion-aware feat…

cs.LG2019

GluonCV and GluonNLP: Deep Learning in Computer Vision and Natural Language Processing

Jian Guo, He He, Tong He +13

We present GluonCV and GluonNLP, the deep learning toolkits for computer vision and natural language processing based on Apache MXNet (incubating). These toolkits provide state-of-…

cs.CV2019

Exploring Temporal Information for Improved Video Understanding

Yi Zhu

In this dissertation, I present my work towards exploring temporal information for better video understanding. Specifically, I have worked on two problems: action recognition and s…