# Person Search in Videos with One Portrait Through Visual and Temporal Links

arXiv: https://arxiv.org/abs/1807.10510 · HTML: https://mlsanity.com/paper/1807.10510/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jul 2018.

## Built on by (most cited first, 14 of 14)

- [AutoAD: Movie Description in Context](https://mlsanity.com/paper/2303.16899/) (2023)
- [AutoAD II: The Sequel -- Who, When, and What in Movie Audio Description](https://mlsanity.com/paper/2310.06838/) (2023)
- [The One Where They Reconstructed 3D Humans and Environments in TV Shows](https://mlsanity.com/paper/2207.14279/) (2022)
- [MovieCuts: A New Dataset and Benchmark for Cut Type Recognition](https://mlsanity.com/paper/2109.05569/) (2021)
- [Face, Body, Voice: Video Person-Clustering with Multiple Modalities](https://mlsanity.com/paper/2105.09939/) (2021)
- [AutoAD-Zero: A Training-Free Framework for Zero-Shot Audio Description](https://mlsanity.com/paper/2407.15850/) (2024)
- [Learning to Cut by Watching Movies](https://mlsanity.com/paper/2108.04294/) (2021)
- [MEVID: Multi-view Extended Videos with Identities for Video Person Re-Identification](https://mlsanity.com/paper/2211.04656/) (2022)
- [Transformation vs Tradition: Artificial General Intelligence (AGI) for Arts and Humanities](https://mlsanity.com/paper/2310.19626/) (2023)
- [ScriptViz: A Visualization Tool to Aid Scriptwriting based on a Large Movie Database](https://mlsanity.com/paper/2410.03224/) (2024)
- [From Shots to Stories: LLM-Assisted Video Editing with Unified Language Representations](https://mlsanity.com/paper/2505.12237/) (2025)
- [APES: Audiovisual Person Search in Untrimmed Video](https://mlsanity.com/paper/2106.01667/) (2021)
- [FocusedAD: Character-centric Movie Audio Description](https://mlsanity.com/paper/2504.12157/) (2025)
- [Relation-Aware Distribution Representation Network for Person Clustering with Multiple Modalities](https://mlsanity.com/paper/2308.00588/) (2023)

## Abstract (arXiv)

In real-world applications, e.g. law enforcement and video retrieval, one often needs to search a certain person in long videos with just one portrait. This is much more challenging than the conventional settings for person re-identification, as the search may need to be carried out in the environments different from where the portrait was taken. In this paper, we aim to tackle this challenge and propose a novel framework, which takes into account the identity invariance along a tracklet, thus allowing person identities to be propagated via both the visual and the temporal links. We also develop a novel scheme called Progressive Propagation via Competitive Consensus, which significantly improves the reliability of the propagation process. To promote the study of person search, we construct a large-scale benchmark, which contains 127K manually annotated tracklets from 192 movies. Experiments show that our approach remarkably outperforms mainstream person re-id methods, raising the mAP from 42.16% to 62.27%.