# Efficient Tracking and Understanding Object Transformations

arXiv: https://arxiv.org/abs/2607.19743 · HTML: https://mlsanity.com/paper/2607.19743/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 43 of its 50 references that are in the map.
- First posted on arXiv 22 Jul 2026.

## Builds on (most cited first, 30 of 43)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [Rescaling Egocentric Vision](https://mlsanity.com/paper/2006.13256/) (2020)
- [XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model](https://mlsanity.com/paper/2207.07115/) (2022)
- [Video Object Segmentation using Space-Time Memory Networks](https://mlsanity.com/paper/1904.00607/) (2019)
- [LaSOT: A High-quality Benchmark for Large-scale Single Object Tracking](https://mlsanity.com/paper/1809.07845/) (2018)
- [One-Shot Video Object Segmentation](https://mlsanity.com/paper/1611.05198/) (2016)
- [MOSE: A New Dataset for Video Object Segmentation in Complex Scenes](https://mlsanity.com/paper/2302.01872/) (2023)
- [YouTube-VOS: Sequence-to-Sequence Video Object Segmentation](https://mlsanity.com/paper/1809.00461/) (2018)
- [MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions](https://mlsanity.com/paper/2308.08544/) (2023)
- [Associating Objects with Transformers for Video Object Segmentation](https://mlsanity.com/paper/2106.02638/) (2021)
- [Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP](https://mlsanity.com/paper/2308.02487/) (2023)
- [Putting the Object Back into Video Object Segmentation](https://mlsanity.com/paper/2310.12982/) (2023)
- [FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation](https://mlsanity.com/paper/1902.09513/) (2019)
- [Collaborative Video Object Segmentation by Foreground-Background Integration](https://mlsanity.com/paper/2003.08333/) (2020)
- [AdaFrame: Adaptive Frame Selection for Fast Video Recognition](https://mlsanity.com/paper/1811.12432/) (2018)
- [SCSampler: Sampling Salient Clips from Video for Efficient Action Recognition](https://mlsanity.com/paper/1904.04289/) (2019)
- [Efficient Video Object Segmentation via Network Modulation](https://mlsanity.com/paper/1802.01218/) (2018)
- [SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory](https://mlsanity.com/paper/2411.11922/) (2024)
- [Video Object Segmentation Without Temporal Information](https://mlsanity.com/paper/1709.06031/) (2017)
- [High-Quality Entity Segmentation](https://mlsanity.com/paper/2211.05776/) (2022)
- [VideoMatch: Matching based Video Object Segmentation](https://mlsanity.com/paper/1809.01123/) (2018)
- [Learning What to Learn for Video Object Segmentation](https://mlsanity.com/paper/2003.11540/) (2020)
- [SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree](https://mlsanity.com/paper/2410.16268/) (2024)
- [Adaptive Focus for Efficient Video Recognition](https://mlsanity.com/paper/2105.03245/) (2021)
- [LVOS: A Benchmark for Long-term Video Object Segmentation](https://mlsanity.com/paper/2211.10181/) (2022)
- [A Distractor-Aware Memory for Visual Object Tracking with SAM2](https://mlsanity.com/paper/2411.17576/) (2024)

## Abstract (arXiv)

Tracking objects through state transformations is essential for understanding real-world dynamics. However, existing methods are computationally expensive. TubeletGraph recently showed impressive capabilities, but its inference cost (~4.4 seconds per object-frame on VOST) precludes any real-time deployment possibilities. We observe that TubeletGraph's overhead arises from building a spatiotemporal partition of the input video: (1) entity segmentation is computed densely for every frame regardless of whether a transformation occurs, and (2) every entity in the scene is tracked, scaling cost with scene complexity rather than the number of transformations of interest. To address both, we propose FluxGraph, a reactive variant that uses SAM2's internal multi-mask disagreement as a lightweight trigger for transformation detection, and removes the need for tracking all entities in the given video. FluxGraph is ~3.3× faster than TubeletGraph on VOST while improving tracking performance and preserving state graph quality. Furthermore, we also observe consistent speedups of 3.7-10.7× across VSCOS, M3-VOS, and DAVIS17 while maintaining performance. Code is publicly available at https://github.com/YihongSun/FluxGraph.