571 citations · 2.9k across the 98 of their papers we have counts for
14 papers · 1 filter
Siamese Cascaded Region Proposal Networks for Real-Time Visual Tracking
Heng Fan, Haibin Ling
Region proposal networks (RPN) have been recently combined with the Siamese network for tracking, and shown excellent accuracy with high efficiency. Nevertheless, previously propos…
Scene Parsing via Dense Recurrent Neural Networks with Attentional Selection
Heng Fan, Peng Chu, Longin Jan Latecki +1
Recurrent neural networks (RNNs) have shown the ability to improve scene parsing through capturing long-range dependencies among image units. In this paper, we propose dense RNNs f…
M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network
Qijie Zhao, Tao Sheng, Yongtao Wang +4
Feature pyramids are widely exploited by both the state-of-the-art one-stage object detectors (e.g., DSSD, RetinaNet, RefineDet) and the two-stage object detectors (e.g., Mask R-CN…
StructVIO : Visual-inertial Odometry with Structural Regularity of Man-made Environments
Danping Zou, Yuanxin Wu, Ling Pei +2
We propose a novel visual-inertial odometry approach that adopts structural regularity in man-made environments. Instead of using Manhattan world assumption, we use Atlanta world m…
LaSOT: A High-quality Benchmark for Large-scale Single Object Tracking
Heng Fan, Liting Lin, Fan Yang +7
In this paper, we present LaSOT, a high-quality benchmark for Large-scale Single Object Tracking. LaSOT consists of 1,400 sequences with more than 3.5M frames in total. Each frame…
Privacy-Protective-GAN for Face De-identification
Yifan Wu, Fan Yang, Haibin Ling
Face de-identification has become increasingly important as the image sources are explosively growing and easily accessible. The advance of new face recognition techniques also ari…
Robust and Efficient Graph Correspondence Transfer for Person Re-identification
Qin Zhou, Heng Fan, Hua Yang +4
Spatial misalignment caused by variations in poses and viewpoints is one of the most critical issues that hinders the performance improvement in existing person re-identification (…
MTFH: A Matrix Tri-Factorization Hashing Framework for Efficient Cross-Modal Retrieval
Xin Liu, Zhikai Hu, Haibin Ling +1
Hashing has recently sparked a great revolution in cross-modal retrieval because of its low storage cost and high query speed. Recent cross-modal hashing methods often learn unifie…
Vision Meets Drones: A Challenge
Pengfei Zhu, Longyin Wen, Xiao Bian +2
In this paper we present a large-scale visual object detection and tracking benchmark, named VisDrone2018, aiming at advancing visual understanding tasks on the drone platform. The…
Graph Correspondence Transfer for Person Re-identification
Qin Zhou, Heng Fan, Shibao Zheng +4
In this paper, we propose a graph correspondence transfer (GCT) approach for person re-identification. Unlike existing methods, the GCT model formulates person re-identification as…
A Single-shot-per-pose Camera-Projector Calibration System For Imperfect Planar Targets
Bingyao Huang, Samed Ozdemir, Ying Tang +2
Existing camera-projector calibration methods typically warp feature points from a camera image to a projector image using estimated homographies, and often suffer from errors in c…
Weighted Bilinear Coding over Salient Body Parts for Person Re-identification
Zhigang Chang, Qin Zhou, Heng Fan +4
Deep convolutional neural networks (CNNs) have demonstrated dominant performance in person re-identification (Re-ID). Existing CNN based methods utilize global average pooling (GAP…
Parallel Tracking and Verifying
Heng Fan, Haibin Ling
Being intensively studied, visual object tracking has witnessed great advances in either speed (e.g., with correlation filters) or accuracy (e.g., with deep features). Real-time an…
Dense Recurrent Neural Networks for Scene Labeling
Heng Fan, Haibin Ling
Recently recurrent neural networks (RNNs) have demonstrated the ability to improve scene labeling through capturing long-range dependencies among image units. In this paper, we pro…