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 2019Show all

7 papers · 1 filter

eess.IV20193 cited

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…

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…

cs.CV20199 cited

Object Detection in Video with Spatial-temporal Context Aggregation

Hao Luo, Lichao Huang, Han Shen +3

Recent cutting-edge feature aggregation paradigms for video object detection rely on inferring feature correspondence. The feature correspondence estimation problem is fundamentall…

cs.CV20194 cited

Proposal, Tracking and Segmentation (PTS): A Cascaded Network for Video Object Segmentation

Qiang Zhou, Zilong Huang, Lichao Huang +5

Video object segmentation (VOS) aims at pixel-level object tracking given only the annotations in the first frame. Due to the large visual variations of objects in video and the la…