Ahmed Doghri Logo Image
Ahmed Doghri

distractrack

Recency memory swaps identities when two objects cross. distractrack keeps motion and identity in memory, lifting tracking accuracy from 73.8% to 100%.

distractrack reproduced benchmark result

The Nearest Blob Is The Wrong Blob

A tracker that remembers only the last location looks excellent until a distractor crosses the target. Then recency becomes an identity-swap machine.

distractrack generates a 42-frame crossing sequence with measurement noise and a deliberate occlusion jump. Both trackers receive the same candidates.

Memory Needs Identity And Motion

The baseline selects the candidate nearest its last position. The distractor-aware tracker predicts motion and penalizes candidates that disagree with the target identity.

The implementation is intentionally coordinate-level. It isolates memory policy from segmentation quality, which is the exact question the benchmark is trying to answer.

The Number

Recency memory tracks 73.8% of frames correctly after the crossing. Distractor-aware memory tracks all frames, a 26.2-point gain.

The generated timeline is committed with the benchmark result. One test reproduces the identity crossing across the CI matrix.

Research Basis

Inspired by CVPR 2025's distractor-aware SAM2 memory paper. The portfolio number above comes from this repository's own controlled benchmark, not from the paper.

Tools Used

Python
Computer Vision
Object Tracking
Video Memory
Motion Models
unittest
GitHub Actions CI