# Beyond Pedestrians: Caption-Guided CLIP Framework for High-Difficulty Video-based Person Re-Identification

arXiv: https://arxiv.org/abs/2604.07740 · HTML: https://mlsanity.com/paper/2604.07740/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 47 of its 67 references that are in the map.
- First posted on arXiv 9 Apr 2026.

## Builds on (most cited first, 30 of 47)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs](https://mlsanity.com/paper/2503.01743/) (2025)
- [FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking](https://mlsanity.com/paper/2004.01888/) (2020)
- [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017)
- [TransReID: Transformer-based Object Re-Identification](https://mlsanity.com/paper/2102.04378/) (2021)
- [Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks](https://mlsanity.com/paper/2311.06242/) (2023)
- [Omni-Scale Feature Learning for Person Re-Identification](https://mlsanity.com/paper/1905.00953/) (2019)
- [Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro](https://mlsanity.com/paper/1701.07717/) (2017)
- [DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion](https://mlsanity.com/paper/2111.14690/) (2021)
- [CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels](https://mlsanity.com/paper/2211.13977/) (2022)
- [SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes](https://mlsanity.com/paper/2304.05170/) (2023)
- [Appearance-Preserving 3D Convolution for Video-based Person Re-identification](https://mlsanity.com/paper/2007.08434/) (2020)
- [Learning Multi-Granular Hypergraphs for Video-Based Person Re-Identification](https://mlsanity.com/paper/2104.14913/) (2021)
- [Temporal Complementary Learning for Video Person Re-Identification](https://mlsanity.com/paper/2007.09357/) (2020)
- [STA: Spatial-Temporal Attention for Large-Scale Video-based Person Re-Identification](https://mlsanity.com/paper/1811.04129/) (2018)
- [Watching You: Global-guided Reciprocal Learning for Video-based Person Re-identification](https://mlsanity.com/paper/2103.04337/) (2021)
- [BiCnet-TKS: Learning Efficient Spatial-Temporal Representation for Video Person Re-Identification](https://mlsanity.com/paper/2104.14783/) (2021)
- [Multi-Granularity Reference-Aided Attentive Feature Aggregation for Video-based Person Re-identification](https://mlsanity.com/paper/2003.12224/) (2020)
- [Multi-scale 3D Convolution Network for Video Based Person Re-Identification](https://mlsanity.com/paper/1811.07468/) (2018)
- [TF-CLIP: Learning Text-free CLIP for Video-based Person Re-Identification](https://mlsanity.com/paper/2312.09627/) (2023)
- [DeepSportradar-v1: Computer Vision Dataset for Sports Understanding with High Quality Annotations](https://mlsanity.com/paper/2208.08190/) (2022)
- [Video-based Person Re-identification with Spatial and Temporal Memory Networks](https://mlsanity.com/paper/2108.09039/) (2021)
- [TOP-ReID: Multi-spectral Object Re-Identification with Token Permutation](https://mlsanity.com/paper/2312.09612/) (2023)

## Abstract (arXiv)

In recent years, video-based person Re-Identification (ReID) has gained attention for its ability to leverage spatiotemporal cues to match individuals across non-overlapping cameras. However, current methods struggle with high-difficulty scenarios, such as sports and dance performances, where multiple individuals wear similar clothing while performing dynamic movements. To overcome these challenges, we propose CG-CLIP, a novel caption-guided CLIP framework that leverages explicit textual descriptions and learnable tokens. Our method introduces two key components: Caption-guided Memory Refinement (CMR) and Token-based Feature Extraction (TFE). CMR utilizes captions generated by Multi-modal Large Language Models (MLLMs) to refine identity-specific features, capturing fine-grained details. TFE employs a cross-attention mechanism with fixed-length learnable tokens to efficiently aggregate spatiotemporal features, reducing computational overhead. We evaluate our approach on two standard datasets (MARS and iLIDS-VID) and two newly constructed high-difficulty datasets (SportsVReID and DanceVReID). Experimental results demonstrate that our method outperforms current state-of-the-art approaches, achieving significant improvements across all benchmarks.