activity
20152021
most citedReal-Time and Accurate Object Detection in Compressed Video by Long Short-term Feature Aggregation

26 citations · 104 across the 9 of their papers we have counts for

collaborators
Showing cs.CVShow all

12 papers · 1 filter

cs.CV202126 cited

Real-Time and Accurate Object Detection in Compressed Video by Long Short-term Feature Aggregation

Xinggang Wang, Zhaojin Huang, Bencheng Liao +3

Video object detection is a fundamental problem in computer vision and has a wide spectrum of applications. Based on deep networks, video object detection is actively studied for p…

cs.CV202012 cited

Boundary-preserving Mask R-CNN

Tianheng Cheng, Xinggang Wang, Lichao Huang +1

Tremendous efforts have been made to improve mask localization accuracy in instance segmentation. Modern instance segmentation methods relying on fully convolutional networks perfo…

cs.CV20208 cited

Multi-object Tracking via End-to-end Tracklet Searching and Ranking

Tao Hu, Lichao Huang, Han Shen

Recent works in multiple object tracking use sequence model to calculate the similarity score between the detections and the previous tracklets. However, the forced exposure to gro…

cs.CV201916 cited

RDSNet: A New Deep Architecture for Reciprocal Object Detection and Instance Segmentation

Shaoru Wang, Yongchao Gong, Junliang Xing +3

Object detection and instance segmentation are two fundamental computer vision tasks. They are closely correlated but their relations have not yet been fully explored in most previ…

cs.CV2019

Context-Aware Dynamic Feature Extraction for 3D Object Detection in Point Clouds

Yonglin Tian, Lichao Huang, Xuesong Li +3

Varying density of point clouds increases the difficulty of 3D detection. In this paper, we present a context-aware dynamic network (CADNet) to capture the variance of density by c…

cs.CV2019

Real Time Visual Tracking using Spatial-Aware Temporal Aggregation Network

Tao Hu, Lichao Huang, Xianming Liu +1

More powerful feature representations derived from deep neural networks benefit visual tracking algorithms widely. However, the lack of exploitation on temporal information prevent…