paper-with-me

Papers

Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification

2021-07-27 · Zefeng Ding, Changxing Ding, Zhiyin Shao, DaCheng Tao

Text-to-image person re-identification (ReID) aims to search for images containing a person of interest using textual descriptions. However, due to the significant modality gap and the large intra-class variance in textual descriptions, text-to-image ReID remains a challenging problem. Accordingly, in this paper, we propose a Semantically Self-Aligned Network (SSAN) to handle the above problems. First, we propose a novel method that automatically extracts semantically aligned part-level features from the two modalities. Second, we design a multi-view non-local network that captures the relationships between body parts, thereby establishing better correspondences between body parts and noun phrases. Third, we introduce a Compound Ranking (CR) loss that makes use of textual descriptions for other images of the same identity to provide extra supervision, thereby effectively reducing the intra-class variance in textual features. Finally, to expedite future research in text-to-image ReID, we build a new database named ICFG-PEDES. Extensive experiments demonstrate that SSAN outperforms state-of-the-art approaches by significant margins. Both the new ICFG-PEDES database and the SSAN code are available at https://github.com/zifyloo/SSAN.

📄 PDF Abstract BibTeX arXiv:2107.12666

Code (1)

zifyloo/SSAN 공식 구현 pytorch

Tasks

Image RetrievalPerson Re-IdentificationText based Person RetrievalText-based Person Retrieval with Noisy Correspondence

Similar Papers 제목 키워드 기반

Densely Semantically Aligned Person Re-Identification

2018-12-21 · CVPR 2019 6 · Zhizheng Zhang, Cuiling Lan, Wen-Jun Zeng, Zhibo Chen

We propose a densely semantically aligned person re-identification framework. It fundamentally addresses the body misalignment problem caused by pose/viewpoint variations, imperfect person detection, occlusion, etc. By l…

Human DetectionPerson Re-Identification

Towards Transformer-Based Aligned Generation with Self-Coherence Guidance

2025-03-22 · CVPR 2025 1 · Shulei Wang, Wang Lin, Hai Huang, Hanting Wang 외

We introduce a novel, training-free approach for enhancing alignment in Transformer-based Text-Guided Diffusion Models (TGDMs). Existing TGDMs often struggle to generate semantically aligned images, particularly when dea…

AttributeDenoising

What You See is What You Read? Improving Text-Image Alignment Evaluation

2023-05-17 · NeurIPS 2023 11 · Michal Yarom, Yonatan Bitton, Soravit Changpinyo, Roee Aharoni 외

Automatically determining whether a text and a corresponding image are semantically aligned is a significant challenge for vision-language models, with applications in generative text-to-image and image-to-text tasks. In…

Image GenerationImage to textQuestion AnsweringQuestion Generation+6

Emphasizing Complementary Samples for Non-literal Cross-modal Retrieval

2022-06-25 · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2022 6 · Christopher Thomas, Adriana Kovashka

Existing cross-modal retrieval methods assume a straightforward relationship where images and text contain portrayals or mentions of the same objects. In contrast, real-world image-text pairs (e.g. an image and its capti…

Cross-Modal RetrievalRetrievalSemantic SimilaritySemantic Textual Similarity

Semantics-Aligned Representation Learning for Person Re-identification

2019-05-30 · Xin Jin, Cuiling Lan, Wen-Jun Zeng, Guoqiang Wei 외

Person re-identification (reID) aims to match person images to retrieve the ones with the same identity. This is a challenging task, as the images to be matched are generally semantically misaligned due to the diversity …

DecoderPerson Re-IdentificationRepresentation LearningTexture Synthesis+1