21 citations · 78 across the 8 of their papers we have counts for
11 papers
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…
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…
Learned Video Compression via Joint Spatial-Temporal Correlation Exploration
Haojie Liu, Han shen, Lichao Huang +3
Traditional video compression technologies have been developed over decades in pursuit of higher coding efficiency. Efficient temporal information representation plays a key role i…
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…
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…
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…