b'Wei-Shi Zheng'

research

∙ 01/18/2023

Adaptively Integrated Knowledge Distillation and Prediction Uncertainty for Continual Learning

Current deep learning models often suffer from catastrophic forgetting o...

Kanghao Chen, et al. ∙

research

∙ 09/22/2022

AcroFOD: An Adaptive Method for Cross-domain Few-shot Object Detection

Under the domain shift, cross-domain few-shot object detection aims to a...

Yipeng Gao, et al. ∙

research

∙ 07/14/2022

Learning Discriminative Representation via Metric Learning for Imbalanced Medical Image Classification

Data imbalance between common and rare diseases during model training of...

Chenghua Zeng, et al. ∙

research

∙ 07/11/2022

PCCT: Progressive Class-Center Triplet Loss for Imbalanced Medical Image Classification

Imbalanced training data is a significant challenge for medical image cl...

Kanghao Chen, et al. ∙

research

∙ 07/06/2022

STVGFormer: Spatio-Temporal Video Grounding with Static-Dynamic Cross-Modal Understanding

In this technical report, we introduce our solution to human-centric spa...

Zihang Lin, et al. ∙

research

∙ 07/04/2022

Task-oriented Self-supervised Learning for Anomaly Detection in Electroencephalography

Accurate automated analysis of electroencephalography (EEG) would largel...

Yaojia Zheng, et al. ∙

research

∙ 06/22/2022

Weakly-supervised Action Localization via Hierarchical Mining

Weakly-supervised action localization aims to localize and classify acti...

Jia-Chang Feng, et al. ∙

research

∙ 06/19/2022

SNN2ANN: A Fast and Memory-Efficient Training Framework for Spiking Neural Networks

Spiking neural networks are efficient computation models for low-power e...

Jianxiong Tang, et al. ∙

research

∙ 04/27/2022

Global Trajectory Helps Person Retrieval in a Camera Network

We are concerned about retrieving a query person from the videos taken b...

Xin Zhang, et al. ∙

research

∙ 04/19/2022

Learning to Imagine: Diversify Memory for Incremental Learning using Unlabeled Data

Deep neural network (DNN) suffers from catastrophic forgetting when lear...

Yu-Ming Tang, et al. ∙

research

∙ 03/29/2022

SIOD: Single Instance Annotated Per Category Per Image for Object Detection

Object detection under imperfect data receives great attention recently....

Hanjun Li, et al. ∙

research

∙ 03/07/2022

Unpaired Image Captioning by Image-level Weakly-Supervised Visual Concept Recognition

The goal of unpaired image captioning (UIC) is to describe images withou...

Peipei Zhu, et al. ∙

research

∙ 12/06/2021

Letter-level Online Writer Identification

Writer identification (writer-id), an important field in biometrics, aim...

Zelin Chen, et al. ∙

research

∙ 08/25/2021

Understanding of Kernels in CNN Models by Suppressing Irrelevant Visual Features in Images

Deep learning models have shown their superior performance in various vi...

Jia-Xin Zhuang, et al. ∙

research

∙ 08/11/2021

Discriminative Distillation to Reduce Class Confusion in Continual Learning

Successful continual learning of new knowledge would enable intelligent ...

Changhong Zhong, et al. ∙

research

∙ 07/29/2021

Cross-Camera Feature Prediction for Intra-Camera Supervised Person Re-identification across Distant Scenes

Person re-identification (Re-ID) aims to match person images across non-...

Wenhang Ge, et al. ∙

research

∙ 07/27/2021

Cross-modal Consensus Network for Weakly Supervised Temporal Action Localization

Weakly supervised temporal action localization (WS-TAL) is a challenging...

Fa-Ting Hong, et al. ∙

research

∙ 07/20/2021

Discriminator-Free Generative Adversarial Attack

The Deep Neural Networks are vulnerable toadversarial exam-ples(Figure 1...

Shaohao Lu, et al. ∙

research

∙ 04/29/2021

Learning Multi-Attention Context Graph for Group-Based Re-Identification

Learning to re-identify or retrieve a group of people across non-overlap...

Yichao Yan, et al. ∙

research

∙ 04/28/2021

Preserving Earlier Knowledge in Continual Learning with the Help of All Previous Feature Extractors

Continual learning of new knowledge over time is one desirable capabilit...

Zhuoyun Li, et al. ∙

research

∙ 04/09/2021

Combined Depth Space based Architecture Search For Person Re-identification

Most works on person re-identification (ReID) take advantage of large ba...

Hanjun Li, et al. ∙

research

∙ 04/04/2021

MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection

Weakly supervised video anomaly detection (WS-VAD) is to distinguish ano...

Jia-Chang Feng, et al. ∙

research

∙ 12/10/2020

One for More: Selecting Generalizable Samples for Generalizable ReID Model

Current training objectives of existing person Re-IDentification (ReID) ...

Enwei Zhang, et al. ∙

research

∙ 10/20/2020

Contextual Heterogeneous Graph Network for Human-Object Interaction Detection

Human-object interaction(HOI) detection is an important task for underst...

Hai Wang, et al. ∙

research

∙ 09/11/2020

Devil's in the Detail: Graph-based Key-point Alignment and Embedding for Person Re-ID

Although Person Re-Identification has made impressive progress, difficul...

Xinyang Jiang, et al. ∙

research

∙ 08/16/2020

Do Not Disturb Me: Person Re-identification Under the Interference of Other Pedestrians

In the conventional person Re-ID setting, it is widely assumed that crop...

Shizhen Zhao, et al. ∙

research

∙ 08/13/2020

Hybrid Dynamic-static Context-aware Attention Network for Action Assessment in Long Videos

The objective of action quality assessment is to score sports videos. Ho...

Ling-An Zeng, et al. ∙

research

∙ 07/20/2020

MINI-Net: Multiple Instance Ranking Network for Video Highlight Detection

We address the weakly supervised video highlight detection problem for l...

Fa-Ting Hong, et al. ∙

research

∙ 05/05/2020

Adaptive Interaction Modeling via Graph Operations Search

Interaction modeling is important for video action analysis. Recently, s...

Haoxin Li, et al. ∙

research

∙ 04/16/2020

Learning to Detect Important People in Unlabelled Images for Semi-supervised Important People Detection

Important people detection is to automatically detect the individuals wh...

Fa-Ting Hong, et al. ∙

research

∙ 02/27/2020

Weakly supervised discriminative feature learning with state information for person identification

Unsupervised learning of identity-discriminative visual feature is appea...

Hong-Xing Yu, et al. ∙

research

∙ 02/06/2020

Person Re-identification by Contour Sketch under Moderate Clothing Change

Person re-identification (re-id), the process of matching pedestrian ima...

Qize Yang, et al. ∙

research

∙ 10/31/2019

Weakly Supervised Tracklet Person Re-Identification by Deep Feature-wise Mutual Learning

The scalability problem caused by the difficulty in annotating Person Re...

Zhirui Chen, et al. ∙

research

∙ 10/30/2019

Dual Illumination Estimation for Robust Exposure Correction

Exposure correction is one of the fundamental tasks in image processing ...

Qing Zhang, et al. ∙

research

∙ 10/21/2019

Batch Face Alignment using a Low-rank GAN

This paper studies the problem of aligning a set of face images of the s...

Jiabo Huang, et al. ∙

research

∙ 09/30/2019

DSRGAN: Explicitly Learning Disentangled Representation of Underlying Structure and Rendering for Image Generation without Tuple Supervision

We focus on explicitly learning disentangled representation for natural ...

Guang-Yuan Hao, et al. ∙

research

∙ 07/26/2019

Unsupervised Learning for Optical Flow Estimation Using Pyramid Convolution LSTM

Most of current Convolution Neural Network (CNN) based methods for optic...

Shuosen Guan, et al. ∙

research

∙ 07/25/2019

Enhancing Underexposed Photos using Perceptually Bidirectional Similarity

This paper addresses the problem of enhancing underexposed photos. Exist...

Qing Zhang, et al. ∙

research

∙ 07/01/2019

Cross-view Relation Networks for Mammogram Mass Detection

Mammogram is the most effective imaging modality for the mass lesion det...

Jiechao Ma, et al. ∙

research

∙ 05/31/2019

Deep Dual Relation Modeling for Egocentric Interaction Recognition

Egocentric interaction recognition aims to recognize the camera wearer's...

Haoxin Li, et al. ∙

research

∙ 05/30/2019

Towards Photo-Realistic Visible Watermark Removal with Conditional Generative Adversarial Networks

Visible watermark plays an important role in image copyright protection ...

Xiang Li, et al. ∙

research

∙ 05/27/2019

A Block Decomposition Algorithm for Sparse Optimization

Sparse optimization is a central problem in machine learning and compute...

Ganzhao Yuan, et al. ∙

research

∙ 04/30/2019

Weakly Supervised Open-set Domain Adaptation by Dual-domain Collaboration

In conventional domain adaptation, a critical assumption is that there e...

Shuhan Tan, et al. ∙

research

∙ 04/24/2019

A Large-scale Varying-view RGB-D Action Dataset for Arbitrary-view Human Action Recognition

Current researches of action recognition mainly focus on single-view and...

Yanli Ji, et al. ∙

research

∙ 04/08/2019

Weakly Supervised Person Re-Identification

In the conventional person re-id setting, it is assumed that the labeled...

Jingke Meng, et al. ∙

research

∙ 04/07/2019

Learning to Learn Relation for Important People Detection in Still Images

Humans can easily recognize the importance of people in social event ima...

Wei-Hong Li, et al. ∙

research

∙ 03/15/2019

Unsupervised Person Re-identification by Soft Multilabel Learning

Although unsupervised person re-identification (RE-ID) has drawn increas...

Hong-Xing Yu, et al. ∙

research

∙ 01/29/2019

Unsupervised Person Re-identification by Deep Asymmetric Metric Embedding

Person re-identification (Re-ID) aims to match identities across non-ove...

Hong-Xing Yu, et al. ∙

research

∙ 12/18/2018

Group-Attention Single-Shot Detector (GA-SSD): Finding Pulmonary Nodules in Large-Scale CT Images

Early diagnosis of pulmonary nodules (PNs) can improve the survival rate...

Jiechao Ma, et al. ∙

research

∙ 10/19/2018

Improving Fast Segmentation With Teacher-student Learning

Recently, segmentation neural networks have been significantly improved ...

Jiafeng Xie, et al. ∙

Wei-Shi Zheng

Featured Co-authors