# Identity-Centric Video Summarization via Hierarchical Fusion of Biometric, Appearance, and 3D Body Features

arXiv: https://arxiv.org/abs/2609.25837 · HTML: https://mlsanity.com/paper/2609.25837/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 50 references that are in the map.
- First posted on arXiv 22 Sep 2026.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Simple Online and Realtime Tracking with a Deep Association Metric](https://mlsanity.com/paper/1703.07402/) (2017)
- [Simple Online and Realtime Tracking](https://mlsanity.com/paper/1602.00763/) (2016)
- [ByteTrack: Multi-Object Tracking by Associating Every Detection Box](https://mlsanity.com/paper/2110.06864/) (2021)
- [Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking](https://mlsanity.com/paper/1609.01775/) (2016)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking](https://mlsanity.com/paper/2009.07736/) (2020)
- [TransReID: Transformer-based Object Re-Identification](https://mlsanity.com/paper/2102.04378/) (2021)
- [AdaFace: Quality Adaptive Margin for Face Recognition](https://mlsanity.com/paper/2204.00964/) (2022)
- [Humans in 4D: Reconstructing and Tracking Humans with Transformers](https://mlsanity.com/paper/2305.20091/) (2023)
- [MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking](https://mlsanity.com/paper/2010.07548/) (2020)
- [Deep OC-SORT: Multi-Pedestrian Tracking by Adaptive Re-Identification](https://mlsanity.com/paper/2302.11813/) (2023)
- [CLIP-It! Language-Guided Video Summarization](https://mlsanity.com/paper/2107.00650/) (2021)
- [Sample and Computation Redistribution for Efficient Face Detection](https://mlsanity.com/paper/2105.04714/) (2021)
- [Video Summarization Using Deep Neural Networks: A Survey](https://mlsanity.com/paper/2101.06072/) (2021)
- [Rethinking the Evaluation of Video Summaries](https://mlsanity.com/paper/1903.11328/) (2019)
- [Query-Focused Video Summarization: Dataset, Evaluation, and A Memory Network Based Approach](https://mlsanity.com/paper/1707.04960/) (2017)
- [Video Summarization through Reinforcement Learning with a 3D Spatio-Temporal U-Net](https://mlsanity.com/paper/2106.10528/) (2021)
- [IntentVizor: Towards Generic Query Guided Interactive Video Summarization](https://mlsanity.com/paper/2109.14834/) (2021)
- [CHAD: Charlotte Anomaly Dataset](https://mlsanity.com/paper/2212.09258/) (2022)
- [Scaling Up Video Summarization Pretraining with Large Language Models](https://mlsanity.com/paper/2404.03398/) (2024)
- [Video Summarization with Large Language Models](https://mlsanity.com/paper/2504.11199/) (2025)
- [Unsupervised Video Summarization via Iterative Training and Simplified GAN](https://mlsanity.com/paper/2311.03745/) (2023)
- [Text-Driven Video Acceleration: A Weakly-Supervised Reinforcement Learning Method](https://mlsanity.com/paper/2203.15778/) (2022)

## Abstract (arXiv)

This work presents a video summarization algorithm based on multi-object tracking and person reidentification. We integrate facial embeddings, 3D body-shape features, and visual appearance into a unified tracking framework. These representations enable hierarchical identity assignment and tracking through bidirectional anchoring, which robustly recovers trajectories under severe occlusion or low visual quality. From these stable trajectories, we generate a compact set of summaries for each identity. We select keyframes using a multi-factor weighting scheme that optimizes biometric clarity, social interaction, and motion dynamics, while Adaptive Non-Maximum Suppression ensures temporal diversity. Evaluation on a custom dataset demonstrates tracking stability, achieving an IDF1 of 97.89% and a MOTA of 95.79%. Compared to Top-K selection, our algorithm also increases visual diversity by 146%, temporal coverage by 89%, and information retrievability by 3.5%.