IDEA: Inverted Text with Cooperative Deformable Aggregation for Multi-modal Object Re-Identification
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912273585405952 |
|---|---|
| author | Wang, Yuhao Lv, Yongfeng Zhang, Pingping Lu, Huchuan |
| author_facet | Wang, Yuhao Lv, Yongfeng Zhang, Pingping Lu, Huchuan |
| contents | Multi-modal object Re-IDentification (ReID) aims to retrieve specific objects by utilizing complementary information from various modalities. However, existing methods focus on fusing heterogeneous visual features, neglecting the potential benefits of text-based semantic information. To address this issue, we first construct three text-enhanced multi-modal object ReID benchmarks. To be specific, we propose a standardized multi-modal caption generation pipeline for structured and concise text annotations with Multi-modal Large Language Models (MLLMs). Besides, current methods often directly aggregate multi-modal information without selecting representative local features, leading to redundancy and high complexity. To address the above issues, we introduce IDEA, a novel feature learning framework comprising the Inverted Multi-modal Feature Extractor (IMFE) and Cooperative Deformable Aggregation (CDA). The IMFE utilizes Modal Prefixes and an InverseNet to integrate multi-modal information with semantic guidance from inverted text. The CDA adaptively generates sampling positions, enabling the model to focus on the interplay between global features and discriminative local features. With the constructed benchmarks and the proposed modules, our framework can generate more robust multi-modal features under complex scenarios. Extensive experiments on three multi-modal object ReID benchmarks demonstrate the effectiveness of our proposed method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_10324 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | IDEA: Inverted Text with Cooperative Deformable Aggregation for Multi-modal Object Re-Identification Wang, Yuhao Lv, Yongfeng Zhang, Pingping Lu, Huchuan Computer Vision and Pattern Recognition Multimedia Multi-modal object Re-IDentification (ReID) aims to retrieve specific objects by utilizing complementary information from various modalities. However, existing methods focus on fusing heterogeneous visual features, neglecting the potential benefits of text-based semantic information. To address this issue, we first construct three text-enhanced multi-modal object ReID benchmarks. To be specific, we propose a standardized multi-modal caption generation pipeline for structured and concise text annotations with Multi-modal Large Language Models (MLLMs). Besides, current methods often directly aggregate multi-modal information without selecting representative local features, leading to redundancy and high complexity. To address the above issues, we introduce IDEA, a novel feature learning framework comprising the Inverted Multi-modal Feature Extractor (IMFE) and Cooperative Deformable Aggregation (CDA). The IMFE utilizes Modal Prefixes and an InverseNet to integrate multi-modal information with semantic guidance from inverted text. The CDA adaptively generates sampling positions, enabling the model to focus on the interplay between global features and discriminative local features. With the constructed benchmarks and the proposed modules, our framework can generate more robust multi-modal features under complex scenarios. Extensive experiments on three multi-modal object ReID benchmarks demonstrate the effectiveness of our proposed method. |
| title | IDEA: Inverted Text with Cooperative Deformable Aggregation for Multi-modal Object Re-Identification |
| topic | Computer Vision and Pattern Recognition Multimedia |
| url | https://arxiv.org/abs/2503.10324 |