Search Results for author: Weihua Chen

Found 26 papers, 16 papers with code

RealisHuman: A Two-Stage Approach for Refining Malformed Human Parts in Generated Images

no code implementations5 Sep 2024 Benzhi Wang, Jingkai Zhou, Jingqi Bai, Yang Yang, Weihua Chen, Fan Wang, Zhen Lei

First, it generates realistic human parts, such as hands or faces, using the original malformed parts as references, ensuring consistent details with the original image.

MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequence

no code implementations23 Jul 2024 Canyu Zhao, MingYu Liu, Wen Wang, Weihua Chen, Fan Wang, Hao Chen, Bo Zhang, Chunhua Shen

Our approach utilizes autoregressive models for global narrative coherence, predicting sequences of visual tokens that are subsequently transformed into high-quality video frames through diffusion rendering.

Video Generation

Towards Effective Usage of Human-Centric Priors in Diffusion Models for Text-based Human Image Generation

no code implementations CVPR 2024 Junyan Wang, Zhenhong Sun, Zhiyu Tan, Xuanbai Chen, Weihua Chen, Hao Li, Cheng Zhang, Yang song

Vanilla text-to-image diffusion models struggle with generating accurate human images, commonly resulting in imperfect anatomies such as unnatural postures or disproportionate limbs. Existing methods address this issue mostly by fine-tuning the model with extra images or adding additional controls -- human-centric priors such as pose or depth maps -- during the image generation phase.

Image Generation

Region Generation and Assessment Network for Occluded Person Re-Identification

no code implementations7 Sep 2023 Shuting He, Weihua Chen, Kai Wang, Hao Luo, Fan Wang, Wei Jiang, Henghui Ding

Then, to measure the importance of each generated region, we introduce a Region Assessment Module (RAM) that assigns confidence scores to different regions and reduces the negative impact of the occlusion regions by lower scores.

Occluded Person Re-Identification

Graph Convolution Based Efficient Re-Ranking for Visual Retrieval

1 code implementation15 Jun 2023 Yuqi Zhang, Qi Qian, Hongsong Wang, Chong Liu, Weihua Chen, Fan Wang

In particular, the plain GCR is extended for cross-camera retrieval and an improved feature propagation formulation is presented to leverage affinity relationships across different cameras.

Distributed Computing Image Retrieval +3

Efficient Token-Guided Image-Text Retrieval with Consistent Multimodal Contrastive Training

1 code implementation15 Jun 2023 Chong Liu, Yuqi Zhang, Hongsong Wang, Weihua Chen, Fan Wang, Yan Huang, Yi-Dong Shen, Liang Wang

Most previous works either simply learn coarse-grained representations of the overall image and text, or elaborately establish the correspondence between image regions or pixels and text words.

Image-text Retrieval Representation Learning +1

Avatar Knowledge Distillation: Self-ensemble Teacher Paradigm with Uncertainty

1 code implementation4 May 2023 Yuan Zhang, Weihua Chen, Yichen Lu, Tao Huang, Xiuyu Sun, Jian Cao

Knowledge distillation is an effective paradigm for boosting the performance of pocket-size model, especially when multiple teacher models are available, the student would break the upper limit again.

Knowledge Distillation object-detection +3

Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks

4 code implementations CVPR 2023 Weihua Chen, Xianzhe Xu, Jian Jia, Hao Luo, Yaohua Wang, Fan Wang, Rong Jin, Xiuyu Sun

Unlike the existing self-supervised learning methods, prior knowledge from human images is utilized in SOLIDER to build pseudo semantic labels and import more semantic information into the learned representation.

Human Parsing Pedestrian Attribute Recognition +6

Reliability-Aware Prediction via Uncertainty Learning for Person Image Retrieval

1 code implementation24 Oct 2022 Zhaopeng Dou, Zhongdao Wang, Weihua Chen, YaLi Li, Shengjin Wang

(3) the data uncertainty and the model uncertainty are jointly learned in a unified network, and they serve as two fundamental criteria for the reliability assessment: if a probe is high-quality (low data uncertainty) and the model is confident in the prediction of the probe (low model uncertainty), the final ranking will be assessed as reliable.

Image Retrieval Retrieval

Dynamic Gradient Reactivation for Backward Compatible Person Re-identification

no code implementations12 Jul 2022 Xiao Pan, Hao Luo, Weihua Chen, Fan Wang, Hao Li, Wei Jiang, Jianming Zhang, Jianyang Gu, Peike Li

To address this issue, we propose the Ranking-based Backward Compatible Learning (RBCL), which directly optimizes the ranking metric between new features and old features.

Person Re-Identification Retrieval

TAGPerson: A Target-Aware Generation Pipeline for Person Re-identification

1 code implementation28 Dec 2021 Kai Chen, Weihua Chen, Tao He, Rong Du, Fan Wang, Xiuyu Sun, Yuchen Guo, Guiguang Ding

In TAGPerson, we extract information from target scenes and use them to control our parameterized rendering process to generate target-aware synthetic images, which would hold a smaller gap to the real images in the target domain.

Person Re-Identification

Camera Bias Regularization for Person Re-identification

no code implementations29 Sep 2021 Tao He, Tongkun Xu, Weihua Chen, Yuchen Guo, Guiguang Ding, Zhenhua Guo

Due to the discrepancies between cameras caused by illumination, background, or viewpoint, the underlying difficulty for Re-ID is the camera bias problem, which leads to the large gap of within-identity features from different cameras.

Person Re-Identification

CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation

2 code implementations ICLR 2022 Tongkun Xu, Weihua Chen, Pichao Wang, Fan Wang, Hao Li, Rong Jin

Along with the pseudo labels, a weight-sharing triple-branch transformer framework is proposed to apply self-attention and cross-attention for source/target feature learning and source-target domain alignment, respectively.

Unsupervised Domain Adaptation

Exploring the Quality of GAN Generated Images for Person Re-Identification

no code implementations23 Aug 2021 Yiqi Jiang, Weihua Chen, Xiuyu Sun, Xiaoyu Shi, Fan Wang, Hao Li

Recently, GAN based method has demonstrated strong effectiveness in generating augmentation data for person re-identification (ReID), on account of its ability to bridge the gap between domains and enrich the data variety in feature space.

Diversity Person Re-Identification +1

Graph Convolution for Re-ranking in Person Re-identification

1 code implementation5 Jul 2021 Yuqi Zhang, Qian Qi, Chong Liu, Weihua Chen, Fan Wang, Hao Li, Rong Jin

In this work, we propose a graph-based re-ranking method to improve learned features while still keeping Euclidean distance as the similarity metric.

Person Re-Identification Re-Ranking +1

An Empirical Study of Vehicle Re-Identification on the AI City Challenge

1 code implementation20 May 2021 Hao Luo, Weihua Chen, Xianzhe Xu, Jianyang Gu, Yuqi Zhang, Chong Liu, Yiqi Jiang, Shuting He, Fan Wang, Hao Li

We mainly focus on four points, i. e. training data, unsupervised domain-adaptive (UDA) training, post-processing, model ensembling in this challenge.

Diversity Re-Ranking +2

City-Scale Multi-Camera Vehicle Tracking Guided by Crossroad Zones

1 code implementation14 May 2021 Chong Liu, Yuqi Zhang, Hao Luo, Jiasheng Tang, Weihua Chen, Xianzhe Xu, Fan Wang, Hao Li, Yi-Dong Shen

Multi-Target Multi-Camera Tracking has a wide range of applications and is the basis for many advanced inferences and predictions.

Clustering Vehicle Re-Identification

1st Place Solution to VisDA-2020: Bias Elimination for Domain Adaptive Pedestrian Re-identification

1 code implementation25 Dec 2020 Jianyang Gu, Hao Luo, Weihua Chen, Yiqi Jiang, Yuqi Zhang, Shuting He, Fan Wang, Hao Li, Wei Jiang

Considering the large gap between the source domain and target domain, we focused on solving two biases that influenced the performance on domain adaptive pedestrian Re-ID and proposed a two-stage training procedure.

Domain Adaptation Pseudo Label

Beyond triplet loss: a deep quadruplet network for person re-identification

3 code implementations CVPR 2017 Weihua Chen, Xiaotang Chen, Jian-Guo Zhang, Kaiqi Huang

In particular, a quadruplet deep network using a margin-based online hard negative mining is proposed based on the quadruplet loss for the person ReID.

Person Re-Identification Triplet

A Multi-task Deep Network for Person Re-identification

no code implementations19 Jul 2016 Weihua Chen, Xiaotang Chen, Jian-Guo Zhang, Kaiqi Huang

Person re-identification (ReID) focuses on identifying people across different scenes in video surveillance, which is usually formulated as a binary classification task or a ranking task in current person ReID approaches.

Binary Classification Person Re-Identification

An equalised global graphical model-based approach for multi-camera object tracking

1 code implementation12 Feb 2015 Weihua Chen, Lijun Cao, Xiaotang Chen, Kaiqi Huang

Non-overlapping multi-camera visual object tracking typically consists of two steps: single camera object tracking and inter-camera object tracking.

Object Visual Object Tracking

Cannot find the paper you are looking for? You can Submit a new open access paper.