AI Paper Atlas

Research map / Detection and segmentation / Tracking

Efficient Track Anything

Yunyang Xiong, Chong Zhou, Xiaoyu Xiang, Lemeng Wu, Chenchen Zhu, Zechun Liu, Saksham Suri, Balakrishnan Varadarajan, Ramya Akula, Forrest Iandola, Raghuraman Krishnamoorthi, Bilge Soran and 1 more

ICCV 2025 · Detection and segmentation › Tracking · approach: Unified transformer tracking · 25 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace hierarchical Hiera image encoder with plain ViT-SmallSAM 2 architecture · SA-V testJ&F: 74.7 -> 74.5; FPS 43.8 -> 85.0No clear effect
add average-pooled efficient memory cross-attention (2x2 window)EfficientTAM-S · SA-V test / iPhone 15J&F and latency: J&F 74.5 -> 74.0; latency 1010.8 -> 450 msMixed
add object pointer tokens to cross-attention (ablation)EfficientTAM · SA-V testJ&F: 72.1 -> 74.5Improved
pool only spatial memory tokens rather than all memory tokens (ablation)efficient cross-attention · SA-V testJ&F: 71.7 -> 74.0Improved
use 4x4 pooling window instead of 2x2 (ablation)efficient cross-attention · SA-V testJ&F: about 1 J&F drop with marginal speed gainHurt
use linear attention (associative property) instead of pooled cross-attention (ablation)efficient cross-attention · SA-V testJ&F: >10 J&F dropHurt
use average pooling with log-window constant instead of Linformer-style variant without constant (ablation)efficient cross-attention · SA-V testJ&F: 73.4 -> 74Improved
use average pooling instead of local windowed cross-attention (ablation)efficient cross-attention · SA-V testJ&F: 72.4 -> 74.0Improved
reduce input resolution from 1024x1024 to 512x512 (ablation)EfficientTAM-S · SA-V testJ&F: 74.5 -> 71.5; iPhone latency 1010.8 -> 80.6 msHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy