# TVPR: Text-to-Video Person Retrieval and a New Benchmark

arXiv: https://arxiv.org/abs/2307.07184 · HTML: https://mlsanity.com/paper/2307.07184/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 51 references that are in the map.
- First posted on arXiv 14 Jul 2023.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval](https://mlsanity.com/paper/2104.08860/) (2021)
- [Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification](https://mlsanity.com/paper/1712.04851/) (2017)
- [Multi-modal Transformer for Video Retrieval](https://mlsanity.com/paper/2007.10639/) (2020)
- [X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval](https://mlsanity.com/paper/2207.07285/) (2022)
- [Unmasked Teacher: Towards Training-Efficient Video Foundation Models](https://mlsanity.com/paper/2303.16058/) (2023)
- [Person Search with Natural Language Description](https://mlsanity.com/paper/1702.05729/) (2017)
- [Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval](https://mlsanity.com/paper/2303.12501/) (2023)
- [X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval](https://mlsanity.com/paper/2203.15086/) (2022)
- [DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval](https://mlsanity.com/paper/2109.05534/) (2021)
- [Improving Description-based Person Re-identification by Multi-granularity Image-text Alignments](https://mlsanity.com/paper/1906.09610/) (2019)
- [Learning Multi-Granular Hypergraphs for Video-Based Person Re-Identification](https://mlsanity.com/paper/2104.14913/) (2021)
- [Pose-Guided Multi-Granularity Attention Network for Text-Based Person Search](https://mlsanity.com/paper/1809.08440/) (2018)
- [Look Before You Leap: Improving Text-based Person Retrieval by Learning A Consistent Cross-modal Common Manifold](https://mlsanity.com/paper/2209.06209/) (2022)
- [A Video Is Worth Three Views: Trigeminal Transformers for Video-based Person Re-identification](https://mlsanity.com/paper/2104.01745/) (2021)
- [Video Person Re-identification by Temporal Residual Learning](https://mlsanity.com/paper/1802.07918/) (2018)
- [Person Re-Identification via Recurrent Feature Aggregation](https://mlsanity.com/paper/1701.06351/) (2017)
- [Spatiotemporal Transformer for Video-based Person Re-identification](https://mlsanity.com/paper/2103.16469/) (2021)

## Abstract (arXiv)

Most existing methods for text-based person retrieval focus on text-to-image person retrieval. Nevertheless, due to the lack of dynamic information provided by isolated frames, the performance is hampered when the person is obscured or variable motion details are missed in isolated frames. To overcome this, we propose a novel Text-to-Video Person Retrieval (TVPR) task. Since there is no dataset or benchmark that describes person videos with natural language, we construct a large-scale cross-modal person video dataset containing detailed natural language annotations, termed as Text-to-Video Person Re-identification (TVPReid) dataset. In this paper, we introduce a Multielement Feature Guided Fragments Learning (MFGF) strategy, which leverages the cross-modal text-video representations to provide strong text-visual and text-motion matching information to tackle uncertain occlusion conflicting and variable motion details. Specifically, we establish two potential cross-modal spaces for text and video feature collaborative learning to progressively reduce the semantic difference between text and video. To evaluate the effectiveness of the proposed MFGF, extensive experiments have been conducted on TVPReid dataset. To the best of our knowledge, MFGF is the first successful attempt to use video for text-based person retrieval task and has achieved state-of-the-art performance on TVPReid dataset. The TVPReid dataset will be publicly available to benefit future research.