# Solution for Point Tracking Task of ECCV 2nd Perception Test Challenge 2024

arXiv: https://arxiv.org/abs/2410.16286 · HTML: https://mlsanity.com/paper/2410.16286/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 19 references that are in the map.
- First posted on arXiv 5 Oct 2024.

## Builds on (most cited first, 11 of 11)

- [TrackFormer: Multi-Object Tracking with Transformers](https://mlsanity.com/paper/2101.02702/) (2021)
- [TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement](https://mlsanity.com/paper/2306.08637/) (2023)
- [TAP-Vid: A Benchmark for Tracking Any Point in a Video](https://mlsanity.com/paper/2211.03726/) (2022)
- [Real-Time Intermediate Flow Estimation for Video Frame Interpolation](https://mlsanity.com/paper/2011.06294/) (2020)
- [AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation](https://mlsanity.com/paper/2304.09790/) (2023)
- [Understanding SSIM](https://mlsanity.com/paper/2006.13846/) (2020)
- [MFT: Long-Term Tracking of Every Pixel](https://mlsanity.com/paper/2305.12998/) (2023)
- [Dense Optical Tracking: Connecting the Dots](https://mlsanity.com/paper/2312.00786/) (2023)
- [TAPTR: Tracking Any Point with Transformers as Detection](https://mlsanity.com/paper/2403.13042/) (2024)
- [Semi-Supervised Multi-Modal Multi-Instance Multi-Label Deep Network with Optimal Transport](https://mlsanity.com/paper/2104.08489/) (2021)
- [Solution for Point Tracking Task of ICCV 1st Perception Test Challenge 2023](https://mlsanity.com/paper/2403.17994/) (2024)

## Abstract (arXiv)

This report introduces an improved method for the Tracking Any Point~(TAP), focusing on monitoring physical surfaces in video footage. Despite their success with short-sequence scenarios, TAP methods still face performance degradation and resource overhead in long-sequence situations. To address these issues, we propose a simple yet effective approach called Fine-grained Point Discrimination~(FPD), which focuses on perceiving and rectifying point tracking at multiple granularities in zero-shot manner, especially for static points in the videos shot by a static camera. The proposed FPD contains two key components: (1) Multi-granularity point perception, which can detect static sequences in video and points. (2) Dynamic trajectory correction, which replaces point trajectories based on the type of tracked point. Our approach achieved the second highest score in the final test with a score of 0.4720.