Video-Level Language-Driven Video-Based Visible-Infrared Person Re-Identification

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Li, Shuang, Leng, Jiaxu, Kuang, Changjiang, Tan, Mingpi, Gao, Xinbo
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915320587878400
author Li, Shuang
Leng, Jiaxu
Kuang, Changjiang
Tan, Mingpi
Gao, Xinbo
author_facet Li, Shuang
Leng, Jiaxu
Kuang, Changjiang
Tan, Mingpi
Gao, Xinbo
contents Video-based Visible-Infrared Person Re-Identification (VVI-ReID) aims to match pedestrian sequences across modalities by extracting modality-invariant sequence-level features. As a high-level semantic representation, language provides a consistent description of pedestrian characteristics in both infrared and visible modalities. Leveraging the Contrastive Language-Image Pre-training (CLIP) model to generate video-level language prompts and guide the learning of modality-invariant sequence-level features is theoretically feasible. However, the challenge of generating and utilizing modality-shared video-level language prompts to address modality gaps remains a critical problem. To address this problem, we propose a simple yet powerful framework, video-level language-driven VVI-ReID (VLD), which consists of two core modules: invariant-modality language prompting (IMLP) and spatial-temporal prompting (STP). IMLP employs a joint fine-tuning strategy for the visual encoder and the prompt learner to effectively generate modality-shared text prompts and align them with visual features from different modalities in CLIP's multimodal space, thereby mitigating modality differences. Additionally, STP models spatiotemporal information through two submodules, the spatial-temporal hub (STH) and spatial-temporal aggregation (STA), which further enhance IMLP by incorporating spatiotemporal information into text prompts. The STH aggregates and diffuses spatiotemporal information into the [CLS] token of each frame across the vision transformer (ViT) layers, whereas STA introduces dedicated identity-level loss and specialized multihead attention to ensure that the STH focuses on identity-relevant spatiotemporal feature aggregation. The VLD framework achieves state-of-the-art results on two VVI-ReID benchmarks. The code will be released at https://github.com/Visuang/VLD.
format Preprint
id arxiv_https___arxiv_org_abs_2506_02439
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Video-Level Language-Driven Video-Based Visible-Infrared Person Re-Identification
Li, Shuang
Leng, Jiaxu
Kuang, Changjiang
Tan, Mingpi
Gao, Xinbo
Computer Vision and Pattern Recognition
Video-based Visible-Infrared Person Re-Identification (VVI-ReID) aims to match pedestrian sequences across modalities by extracting modality-invariant sequence-level features. As a high-level semantic representation, language provides a consistent description of pedestrian characteristics in both infrared and visible modalities. Leveraging the Contrastive Language-Image Pre-training (CLIP) model to generate video-level language prompts and guide the learning of modality-invariant sequence-level features is theoretically feasible. However, the challenge of generating and utilizing modality-shared video-level language prompts to address modality gaps remains a critical problem. To address this problem, we propose a simple yet powerful framework, video-level language-driven VVI-ReID (VLD), which consists of two core modules: invariant-modality language prompting (IMLP) and spatial-temporal prompting (STP). IMLP employs a joint fine-tuning strategy for the visual encoder and the prompt learner to effectively generate modality-shared text prompts and align them with visual features from different modalities in CLIP's multimodal space, thereby mitigating modality differences. Additionally, STP models spatiotemporal information through two submodules, the spatial-temporal hub (STH) and spatial-temporal aggregation (STA), which further enhance IMLP by incorporating spatiotemporal information into text prompts. The STH aggregates and diffuses spatiotemporal information into the [CLS] token of each frame across the vision transformer (ViT) layers, whereas STA introduces dedicated identity-level loss and specialized multihead attention to ensure that the STH focuses on identity-relevant spatiotemporal feature aggregation. The VLD framework achieves state-of-the-art results on two VVI-ReID benchmarks. The code will be released at https://github.com/Visuang/VLD.
title Video-Level Language-Driven Video-Based Visible-Infrared Person Re-Identification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.02439