Kecheng Zheng
Kecheng Zheng is currently a researcher at Ant Research working with Yujun Shen. My research focuses on computer vision and deep learning, particularly on multi-modal learning.
From Nov. 2018 to Jan. 2019, I was under the supervision of Wei Wei who is a research scientist in GOOGLE cloud.
From Sep. 2019 to May. 2020, I was an intern at JD AI Lab, working with Wu Liu.
From Jul. 2020 to Jan. 2021, I worked at Intelligent Multimedia Group (IMG) in MSRA as a research intern, under the supervision of Cuiling Lan.
From Mar. 2022 to Jul. 2022, I worked at Ant Research as a research intern working with Deli Zhao.
Email: zkechengzk@gmail.com  / 
Google Scholar  / 
Github
|
|
News
[06/2024] Four paper accepted by ECCV 2024~
[03/2024] Two paper accepted by CVPR 2024
[10/2023] Two paper accepted by NeurIPS 2023.
[08/2023] Two paper accepted by ICCV 2023.
[04/2023] Two paper accepted by ICML 2023.
[02/2023] Two paper accepted by CVPR 2023.
-->
|
Research
I'm interested in computer vision, representation learning and multi-modal learning.
|
|
CoDeF: Content Deformation Fields for Temporally Consistent Video Processing
Arxiv, 2023  
|
|
Benchmarking and Analyzing 3D-aware Image Synthesis with a Modularized Codebase
NeurIPS, 2023  
|
|
Cones 2: Customizable Image Synthesis with Multiple Subjects
NeurIPS, 2023  
|
|
Cones: Concept Neurons in Diffusion Models for Customized Generation.
ICML, 2023   Oral Presentation!
|
|
RLEG: Vision-Language Representation Learning with Diffusion-based Embedding Generation.
ICML, 2023  
|
|
Self-Organizing Pathway Expansion for Non-Exemplar Class-Incremental Learning
ICCV, 2023  
|
|
Regularized Mask Tuning: Uncovering Hidden Knowledge in Pre-trained Vision-Language Models
ICCV, 2023  
|
|
Neural Dependencies Emerging from Learning Massive Categories
CVPR, 2023  
|
|
Uncertainty-Aware Optimal Transport for Semantically Coherent Out-of-Distribution Detection
Fan Lu,
Kai Zhu,
Wei Zhai,
Kecheng Zheng,
Yang Cao
CVPR, 2023  
|
|
Rank Diminishing in Deep Neural Networks
NeurIPS, 2022  
|
|
Uncertainty-Aware Hierarchical Refinement for Incremental Implicitly-Refined Classification
Jian Yang,
Kai Zhu,
Kecheng Zheng,
Yang Cao
NeurIPS, 2022  
|
|
Unleashing the Potential of Unsupervised Pre-Training with Intra-Identity Regularization for Person Re-Identification
Zizheng Yang,
Xin Jin,
Kecheng Zheng,
Feng Zhao
CVPR, 2022  
ArXiv /
Code /
bibtex
We design an Unsupervised Pre-training framework for ReID based on the contrastive learning (CL) pipeline, dubbed UP-ReID.
|
|
Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularization
Xin Jin,
Tianyu He,
Kecheng Zheng,
Zhiheng Ying,
Xu Shen,
Zhen Huang ,
Ruoyu Feng ,
Jianqiang Huang ,
Xian-Sheng Hua ,
Zhibo Chen
CVPR, 2022  
ArXiv /
Code /
bibtex
We focus on handling well the CC-ReID problem under a more challenging setting, i.e., just from a single image, which enables high-efficiency and latency-free pedestrian identify for real-time surveillance applications.
|
|
Calibrated Feature Decomposition for Generalizable Person Re-Identification
Kecheng Zheng,
Jiawei Liu,
Wei Wu,
Liang Li,
Zheng-jun Zha
Arxiv, 2022  
ArXiv /
Code /
bibtex
We propose a simple yet effective Calibrated Feature Decomposition (CFD) module that focuses on improving the generalization capacity for person re-identification through a more judicious feature decomposition and reinforcement strategy.
|
|
Debiased Batch Normalization via Gaussian Process for Generalizable Person Re-Identification
Jiawei Liu,
Zhipeng Huang,
Kecheng Zheng,
Liang Li,
Zheng-jun Zha
AAAI, 2022  
Arxiv
We propose a novel Debiased Batch Normalization via Gaussian Process approach (GDNorm) for generalizable person re-identification, which models the feature statistic estimation from BN layers as a dynamically self-refining Gaussian process to alleviate the bias to unseen domain for improving the generalization.
|
|
Modality-Adaptive Mixup and Invariant Decomposition for RGB-Infrared Person Re-Identification
Zhipeng Huang,
Jiawei Liu,
Kecheng Zheng,
Liang Li,
Zheng-jun Zha
AAAI, 2022  
arxiv
We propose a novel modality-adaptive mixup and invariant decomposition (MID) approach for RGB-infrared person re-identification towards learning modality-invariant and discriminative representations.
|
|
Pose-Guided Feature Learning with Knowledge Distillation for Occluded Person Re-Identification
Kecheng Zheng,
Cuiling Lan,
Jiawei Liu,
Wenjun Zeng,
Zhizheng Zhang,
Zheng-jun Zha
ACM MM, 2021  
ArXiv /
bibtex
We propose a network named Pose-Guided Feature Learning with Knowledge Distillation (PGFL-KD), where the pose information is exploited to regularize the learning of semantics aligned features but is discarded in testing.
|
|
Group-aware Label Transfer for Domain Adaptive Person Re-identification
Kecheng Zheng,
Wu Liu,
Lingxiao He,
Jiebo Luo,
Tao Mei,
Zheng-jun Zha
CVPR, 2021  
ArXiv /
Code /
bibtex
We propose a Group-aware Label Transfer (GLT) algorithm, which enables the online interaction and mutual promotion of pseudo-label prediction and representation learning.
|
|
Spatial-Temporal Correlation and Topology Learning for Person Re-Identification in Videos
Jiawei Liu,
Zheng-jun Zha,
Wei Wu,
Kecheng Zheng,
Qibin Sun
CVPR, 2021   Oral Presentation!
ArXiv /
bibtex
We propose a novel Spatial-Temporal Correlation and Topology Learning framework (CTL) to pursue discriminative and robust representation by modeling cross-scale spatial-temporal correlation.
|
|
Disentanglement-based Cross-Domain Feature Augmentation for Effective Unsupervised Domain Adaptive Person Re-identification
Zhizheng Zhang ,
Cuiling Lan,
Wenjun Zeng,
Quanzeng You ,
Zicheng Liu ,
Kecheng Zheng,
Zhibo Chen
ArXiv, 2021  
ArXiv /
code(coming soon) /
bibtex
We propose a Disentanglement-based Cross-Domain Feature Augmentation (DCDFA) strategy, where the augmented features characterize well the target and source domain data distributions while inheriting reliable identity labels.
|
|
Exploiting Sample Uncertainty for Domain Adaptive Person Re-Identification
Kecheng Zheng,
Cuiling Lan,
Wenjun Zeng,
Zhizheng Zhang,
Zheng-jun Zha
AAAI, 2021  
ArXiv /
Code /
bibtex
We propose to estimate and exploit the credibility of the assigned pseudo-label of each sample to alleviate the influence of noisy labels.
|
|
Memory Enhanced Embedding Learning for Cross-Modal Video-Text Retrieval
Rui Zhao*,
Kecheng Zheng*,
Zheng-jun Zha,
Hongtao Xie,
Jiebo Luo
*Equal Contribution
ArXiv, 2020  
ArXiv /
bibtex
We propose a novel memory enhanced embedding learning (MEEL) method for video-text retrieval.
|
|
Hierarchical Gumbel Attention Network for Text-based Person Search
Kecheng Zheng,
Wu Liu,
Jiawei Liu,
Tao Mei,
Zheng-jun Zha
ACM MM, 2020  
Acm /
bibtex
We propose a novel hierarchical Gumbel attention network for text-based person search via Gumbel top-k re-parameterization algorithm.
|
|
Abstract Reasoning with Distracting Features
Kecheng Zheng,
Wei Wei,
Zheng-jun Zha
NeurIPS, 2019  
ArXiv /
Code /
bibtex
We first illustrate that one of the main challenges in such a reasoning task is the presence of distracting features, which requires the learning algorithm to leverage counterevidence
and to reject any of the false hypotheses in order to learn the true patterns.
|
|
STACKED CONVOLUTIONAL DEEP ENCODING NETWORK FOR VIDEO-TEXT RETRIEVAL
Rui Zhao*,
Kecheng Zheng*,
Zheng-jun Zha
*Equal Contribution
ICME, 2020  
ArXiv /
bibtex
We propose a stacked convolutional deep encoding network for video-text retrieval task, which considers to simultaneously encode long-range and short-range dependency in the videos and texts.
|
|
LA-Net: Layout-Aware Dense Network for Monocular Depth Estimation
Kecheng Zheng,
Zheng-jun Zha,
Yang Cao,
Xuejin Chen,
Feng Wu
ACM MM, 2018   Oral Presentation!
Acm /
bibtex
We propose a novel Layout-Aware Convolutional Neural Network (LA-Net) for accurate monocular depth estimation by simultaneously perceiving scene layout and local depth details.
|
Journal reviewer: IJCV, TNNLS, TMM, YCSVT
Conference reviewer: CVPR, ICCV, ECCV, NeurIPS, ICML, ACM MM, AAAI
|
|