paper-with-me

Papers

Multi-Scale Body-Part Mask Guided Attention for Person Re-identification

2019-04-24 · Honglong Cai, Zhiguan Wang, Jinxing Cheng

Person re-identification becomes a more and more important task due to its wide applications. In practice, person re-identification still remains challenging due to the variation of person pose, different lighting, occlusion, misalignment, background clutter, etc. In this paper, we propose a multi-scale body-part mask guided attention network (MMGA), which jointly learns whole-body and part body attention to help extract global and local features simultaneously. In MMGA, body-part masks are used to guide the training of corresponding attention. Experiments show that our proposed method can reduce the negative influence of variation of person pose, misalignment and background clutter. Our method achieves rank-1/mAP of 95.0%/87.2% on the Market1501 dataset, 89.5%/78.1% on the DukeMTMC-reID dataset, outperforming current state-of-the-art methods.

📄 PDF Abstract BibTeX arXiv:1904.11041

Code (0)

등록된 구현이 없습니다.

Tasks

Person Re-Identification

Similar Papers 제목 키워드 기반

PARE: Part Attention Regressor for 3D Human Body Estimation

2021-04-17 · ICCV 2021 10 · Muhammed Kocabas, Chun-Hao P. Huang, Otmar Hilliges, Michael J. Black

Despite significant progress, we show that state of the art 3D human pose and shape estimation methods remain sensitive to partial occlusion and can produce dramatically wrong predictions although much of the body is obs…

3D human pose and shape estimation3D Human Pose Estimation3D Multi-Person Pose Estimation

Graph-based Person Signature for Person Re-Identifications

2021-04-14 · Binh X. Nguyen, Binh D. Nguyen, Tuong Do, Erman Tjiputra 외

The task of person re-identification (ReID) is to match images of the same person over multiple non-overlapping camera views. Due to the variations in visual factors, previous works have investigated how the person ident…

AttributeMulti-Task LearningPerson Re-Identification

Human De-occlusion: Invisible Perception and Recovery for Humans

2021-03-22 · CVPR 2021 1 · Qiang Zhou, Shiyin Wang, Yitong Wang, Zilong Huang 외

In this paper, we tackle the problem of human de-occlusion which reasons about occluded segmentation masks and invisible appearance content of humans. In particular, a two-stage framework is proposed to estimate the invi…

Human ParsingInstance SegmentationSemantic Segmentation

Stereo-Talker: Audio-driven 3D Human Synthesis with Prior-Guided Mixture-of-Experts

2024-10-31 · Xiang Deng, Youxin Pang, Xiaochen Zhao, Chao Xu 외

This paper introduces Stereo-Talker, a novel one-shot audio-driven human video synthesis system that generates 3D talking videos with precise lip synchronization, expressive body gestures, temporally consistent photo-rea…

Language ModelingLanguage ModellingLarge Language ModelMixture-of-Experts+1

Learning 3D Texture-Aware Representations for Parsing Diverse Human Clothing and Body Parts

2025-08-08 · Kiran Chhatre, Christopher Peters, Srikrishna Karanam arxiv

Existing methods for human parsing into body parts and clothing often use fixed mask categories with broad labels that obscure fine-grained clothing types. Recent open-vocabulary segmentation approaches leverage pretrain…

Semantic SegmentationHuman Parsing