# Multi-Object Tracking Retrieval with LLaVA-Video: A Training-Free Solution to MOT25-StAG Challenge

arXiv: https://arxiv.org/abs/2511.03332 · HTML: https://mlsanity.com/paper/2511.03332/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 15 references that are in the map.
- First posted on arXiv 5 Nov 2025.

## Builds on (most cited first, 15 of 15)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [ByteTrack: Multi-Object Tracking by Associating Every Detection Box](https://mlsanity.com/paper/2110.06864/) (2021)
- [LLaVA-Video: Video Instruction Tuning With Synthetic Data](https://mlsanity.com/paper/2410.02713/) (2024)
- [HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking](https://mlsanity.com/paper/2009.07736/) (2020)
- [MOT20: A benchmark for multi object tracking in crowded scenes](https://mlsanity.com/paper/2003.09003/) (2020)
- [Occluded Video Instance Segmentation: A Benchmark](https://mlsanity.com/paper/2102.01558/) (2021)
- [MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking](https://mlsanity.com/paper/1504.01942/) (2015)
- [FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Grounding](https://mlsanity.com/paper/2412.13441/) (2024)
- [Bootstrapping Referring Multi-Object Tracking](https://mlsanity.com/paper/2406.05039/) (2024)
- [ReferGPT: Towards Zero-Shot Referring Multi-Object Tracking](https://mlsanity.com/paper/2504.09195/) (2025)
- [FastTracker: Real-Time and Accurate Visual Tracking](https://mlsanity.com/paper/2508.14370/) (2025)
- [SVAG-Bench: A Large-Scale Benchmark for Multi-Instance Spatio-temporal Video Action Grounding](https://mlsanity.com/paper/2510.13016/) (2025)

## Built on by (most cited first, 1 of 1)

- [Efficient Spatio-Temporal Grounding with Multimodal Large Models via Second-Level Tracking and RL Verification](https://mlsanity.com/paper/2606.29023/) (2026)

## Abstract (arXiv)

In this report, we present our solution to the MOT25-Spatiotemporal Action Grounding (MOT25-StAG) Challenge. The aim of this challenge is to accurately localize and track multiple objects that match specific and free-form language queries, using video data of complex real-world scenes as input. We model the underlying task as a video retrieval problem and present a two-stage, zero-shot approach, combining the advantages of the SOTA tracking model FastTracker and Multi-modal Large Language Model LLaVA-Video. On the MOT25-StAG test set, our method achieves m-HIoU and HOTA scores of 20.68 and 10.73 respectively, which won second place in the challenge.