# Learning Language-Driven Sequence-Level Modal-Invariant Representations for Video-Based Visible-Infrared Person Re-Identification

arXiv: https://arxiv.org/abs/2601.12062 · HTML: https://mlsanity.com/paper/2601.12062/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 40 references that are in the map.
- First posted on arXiv 17 Jan 2026.

## Builds on (most cited first, 20 of 20)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Deep Learning for Person Re-identification: A Survey and Outlook](https://mlsanity.com/paper/2001.04193/) (2020)
- [CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels](https://mlsanity.com/paper/2211.13977/) (2022)
- [Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2007.09314/) (2020)
- [Diverse Embedding Expansion Network and Low-Light Cross-Modality Benchmark for Visible-Infrared Person Re-identification](https://mlsanity.com/paper/2303.14481/) (2023)
- [Learning by Aligning: Visible-Infrared Person Re-identification using Cross-Modal Correspondences](https://mlsanity.com/paper/2108.07422/) (2021)
- [Farewell to Mutual Information: Variational Distillation for Cross-Modal Person Re-Identification](https://mlsanity.com/paper/2104.02862/) (2021)
- [Learning Progressive Modality-shared Transformers for Effective Visible-Infrared Person Re-identification](https://mlsanity.com/paper/2212.00226/) (2022)
- [TF-CLIP: Learning Text-free CLIP for Video-based Person Re-Identification](https://mlsanity.com/paper/2312.09627/) (2023)
- [Learning Modal-Invariant and Temporal-Memory for Video-based Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2208.02450/) (2022)
- [Building an Open-Vocabulary Video CLIP Model with Better Architectures, Optimization and Data](https://mlsanity.com/paper/2310.05010/) (2023)
- [CLIP-Driven Semantic Discovery Network for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2401.05806/) (2024)
- [High-Order Structure Based Middle-Feature Learning for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2312.07853/) (2023)
- [Spatiotemporal Self-attention Modeling with Temporal Patch Shift for Action Recognition](https://mlsanity.com/paper/2207.13259/) (2022)
- [ZeroI2V: Zero-Cost Adaptation of Pre-trained Transformers from Image to Video](https://mlsanity.com/paper/2310.01324/) (2023)
- [Video-based Visible-Infrared Person Re-Identification with Auxiliary Samples](https://mlsanity.com/paper/2311.15571/) (2023)
- [Video-Level Language-Driven Video-Based Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2506.02439/) (2025)
- [X-ReID: Multi-granularity Information Interaction for Video-Based Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2511.17964/) (2025)
- [Image Re-Identification: Where Self-supervision Meets Vision-Language Learning](https://mlsanity.com/paper/2407.20647/) (2024)
- [CLIP4VI-ReID: Learning Modality-shared Representations via CLIP Semantic Bridge for Visible-Infrared Person Re-identification](https://mlsanity.com/paper/2511.10309/) (2025)

## Abstract (arXiv)

The core of video-based visible-infrared person re-identification (VVI-ReID) lies in learning sequence-level modal-invariant representations across different modalities. Recent research tends to use modality-shared language prompts generated by CLIP to guide the learning of modal-invariant representations. Despite achieving optimal performance, such methods still face limitations in efficient spatial-temporal modeling, sufficient cross-modal interaction, and explicit modality-level loss guidance. To address these issues, we propose the language-driven sequence-level modal-invariant representation learning (LSMRL) method, which includes spatial-temporal feature learning (STFL) module, semantic diffusion (SD) module and cross-modal interaction (CMI) module. To enable parameter- and computation-efficient spatial-temporal modeling, the STFL module is built upon CLIP with minimal modifications. To achieve sufficient cross-modal interaction and enhance the learning of modal-invariant features, the SD module is proposed to diffuse modality-shared language prompts into visible and infrared features to establish preliminary modal consistency. The CMI module is further developed to leverage bidirectional cross-modal self-attention to eliminate residual modality gaps and refine modal-invariant representations. To explicitly enhance the learning of modal-invariant representations, two modality-level losses are introduced to improve the features' discriminative ability and their generalization to unseen categories. Extensive experiments on large-scale VVI-ReID datasets demonstrate the superiority of LSMRL over AOTA methods.