activity
20092022
most citedMulti-label Learning Based Deep Transfer Neural Network for Facial Attribute Classification

79 citations · 639 across the 41 of their papers we have counts for

collaborators
Showing 2020Show all

11 papers · 1 filter

cs.CV2020★ 14 cited

Hierarchical Representation via Message Propagation for Robust Model Fitting

Shuyuan Lin, Xing Wang, Guobao Xiao +2

In this paper, we propose a novel hierarchical representation via message propagation (HRMP) method for robust model fitting, which simultaneously takes advantages of both the cons…

cs.CV2020★ 2 cited

Robust Visual Tracking via Statistical Positive Sample Generation and Gradient Aware Learning

Lijian Lin, Haosheng Chen, Yanjie Liang +2

In recent years, Convolutional Neural Network (CNN) based trackers have achieved state-of-the-art performance on multiple benchmark datasets. Most of these trackers train a binary…

cs.CV2020★ 29 cited

Dual Semantic Fusion Network for Video Object Detection

Lijian Lin, Haosheng Chen, Honglun Zhang +4

Video object detection is a tough task due to the deteriorated quality of video sequences captured under complex environments. Currently, this area is dominated by a series of feat…

cs.CV2020★ 4 cited

Correlation filter tracking with adaptive proposal selection for accurate scale estimation

Luo Xiong, Yanjie Liang, Yan Yan +1

Recently, some correlation filter based trackers with detection proposals have achieved state-of-the-art tracking results. However, a large number of redundant proposals given by t…

cs.CV2020★ 12 cited

Real-Time High-Performance Semantic Image Segmentation of Urban Street Scenes

Genshun Dong, Yan Yan, Chunhua Shen +1

Deep Convolutional Neural Networks (DCNNs) have recently shown outstanding performance in semantic image segmentation. However, state-of-the-art DCNN-based semantic segmentation me…

cs.CV2020

Learning Object Scale With Click Supervision for Object Detection

Liao Zhang, Yan Yan, Lin Cheng +1

Weakly-supervised object detection has recently attracted increasing attention since it only requires image-levelannotations. However, the performance obtained by existingmethods i…