142 citations · 395 across the 21 of their papers we have counts for
21 papers
Generalized Semi-Supervised Learning via Self-Supervised Feature Adaptation
Jiachen Liang, Ruibing Hou, Hong Chang +3
Traditional semi-supervised learning (SSL) assumes that the feature distributions of labeled and unlabeled data are consistent which rarely holds in realistic scenarios. In this pa…
Clothes-Changing Person Re-Identification with Feasibility-Aware Intermediary Matching
Jiahe Zhao, Ruibing Hou, Hong Chang +4
Current clothes-changing person re-identification (re-id) approaches usually perform retrieval based on clothes-irrelevant features, while neglecting the potential of clothes-relev…
Task Attribute Distance for Few-Shot Learning: Theoretical Analysis and Applications
Minyang Hu, Hong Chang, Zong Guo +3
Few-shot learning (FSL) aims to learn novel tasks with very few labeled samples by leveraging experience from \emph{related} training tasks. In this paper, we try to understand FSL…
Dual Compensation Residual Networks for Class Imbalanced Learning
Ruibing Hou, Hong Chang, Bingpeng Ma +2
Learning generalizable representation and classifier for class-imbalanced data is challenging for data-driven deep models. Most studies attempt to re-balance the data distribution,…
Diversity-Measurable Anomaly Detection
Wenrui Liu, Hong Chang, Bingpeng Ma +2
Reconstruction-based anomaly detection models achieve their purpose by suppressing the generalization ability for anomaly. However, diverse normal patterns are consequently not wel…
Clothes-Changing Person Re-identification with RGB Modality Only
Xinqian Gu, Hong Chang, Bingpeng Ma +3
The key to address clothes-changing person re-identification (re-id) is to extract clothes-irrelevant features, e.g., face, hairstyle, body shape, and gait. Most current works main…
Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework
Botao Ye, Hong Chang, Bingpeng Ma +2
The current popular two-stream, two-stage tracking framework extracts the template and the search region features separately and then performs relation modeling, thus the extracted…
Feature Completion for Occluded Person Re-Identification
Ruibing Hou, Bingpeng Ma, Hong Chang +3
Person re-identification (reID) plays an important role in computer vision. However, existing methods suffer from performance degradation in occluded scenes. In this work, we propo…
BiCnet-TKS: Learning Efficient Spatial-Temporal Representation for Video Person Re-Identification
Ruibing Hou, Hong Chang, Bingpeng Ma +2
In this paper, we present an efficient spatial-temporal representation for video person re-identification (reID). Firstly, we propose a Bilateral Complementary Network (BiCnet) for…
Continuity-Discrimination Convolutional Neural Network for Visual Object Tracking
Shen Li, Bingpeng Ma, Hong Chang +2
This paper proposes a novel model, named Continuity-Discrimination Convolutional Neural Network (CD-CNN), for visual object tracking. Existing state-of-the-art tracking methods do…
IAUnet: Global Context-Aware Feature Learning for Person Re-Identification
Ruibing Hou, Bingpeng Ma, Hong Chang +3
Person re-identification (reID) by CNNs based networks has achieved favorable performance in recent years. However, most of existing CNNs based methods do not take full advantage o…
Appearance-Preserving 3D Convolution for Video-based Person Re-identification
Xinqian Gu, Hong Chang, Bingpeng Ma +2
Due to the imperfect person detection results and posture changes, temporal appearance misalignment is unavoidable in video-based person re-identification (ReID). In this case, 3D…
Temporal Complementary Learning for Video Person Re-Identification
Ruibing Hou, Hong Chang, Bingpeng Ma +2
This paper proposes a Temporal Complementary Learning Network that extracts complementary features of consecutive video frames for video person re-identification. Firstly, we intro…
Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training
Hongkai Zhang, Hong Chang, Bingpeng Ma +2
Although two-stage object detectors have continuously advanced the state-of-the-art performance in recent years, the training process itself is far from crystal. In this work, we f…
Cross Attention Network for Few-shot Classification
Ruibing Hou, Hong Chang, Bingpeng Ma +2
Few-shot classification aims to recognize unlabeled samples from unseen classes given only few labeled samples. The unseen classes and low-data problem make few-shot classification…
Temporal Knowledge Propagation for Image-to-Video Person Re-identification
Xinqian Gu, Bingpeng Ma, Hong Chang +2
In many scenarios of Person Re-identification (Re-ID), the gallery set consists of lots of surveillance videos and the query is just an image, thus Re-ID has to be conducted betwee…
Interaction-and-Aggregation Network for Person Re-identification
Ruibing Hou, Bingpeng Ma, Hong Chang +3
Person re-identification (reID) benefits greatly from deep convolutional neural networks (CNNs) which learn robust feature embeddings. However, CNNs are inherently limited in model…
VRSTC: Occlusion-Free Video Person Re-Identification
Ruibing Hou, Bingpeng Ma, Hong Chang +3
Video person re-identification (re-ID) plays an important role in surveillance video analysis. However, the performance of video re-ID degenerates severely under partial occlusion.…
Cascade RetinaNet: Maintaining Consistency for Single-Stage Object Detection
Hongkai Zhang, Hong Chang, Bingpeng Ma +2
Recent researches attempt to improve the detection performance by adopting the idea of cascade for single-stage detectors. In this paper, we analyze and discover that inconsistency…
WIDER Face and Pedestrian Challenge 2018: Methods and Results
Chen Change Loy, Dahua Lin, Wanli Ouyang +49
This paper presents a review of the 2018 WIDER Challenge on Face and Pedestrian. The challenge focuses on the problem of precise localization of human faces and bodies, and accurat…
Cross-pose Face Recognition by Canonical Correlation Analysis
Annan Li, Shiguang Shan, Xilin Chen +3
The pose problem is one of the bottlenecks in automatic face recognition. We argue that one of the diffculties in this problem is the severe misalignment in face images or feature…