AI Paper Atlas

Research map / Detection and segmentation / Tracking

"FEAR: Fast, Efficient, Accurate and Robust Visual Tracker"

Vasyl Borsuk, Roman Vei, Orest Kupyn, Tetiana Martyniuk, Igor Krashenyi, Jiři Matas

ECCV 2022 · Detection and segmentation › Tracking · approach: Foundation-model and correlation-filter tracking · 103 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
add lower backbone spatial resolution (original stride) (ablation)FEAR-XS · VOT-ST2021 (FEAR-XS ablation)iPhone 11 FPS: 122.19 -> 208.41Improved
add lower backbone spatial resolution (original stride) (ablation)FEAR-XS · VOT-ST2021 (FEAR-XS ablation)EAO: 0.236 -> 0.234No clear effect
add pixel-wise fusion block (ablation)FEAR-XS · VOT-ST2021 (FEAR-XS ablation)EAO: 0.234 -> 0.264Improved
add pixel-wise fusion block (ablation)FEAR-XS · VOT-ST2021 (FEAR-XS ablation)iPhone 11 FPS: 208.41 -> 207.72No clear effect
add dynamic template update (ablation)FEAR-XS · VOT-ST2021 (FEAR-XS ablation)EAO: 0.264 -> 0.270Improved
add dynamic template update (ablation)FEAR-XS · VOT-ST2021 (FEAR-XS ablation)Robustness: 0.683 -> 0.708Improved
add dynamic template update (ablation)FEAR-XS · VOT-ST2021 (FEAR-XS ablation)iPhone 11 FPS: 207.72 -> 205.12No clear effect
evaluate tracker on 240 FPS frames instead of 30 FPS (ablation)FEAR-XS · NFSSuccess Score: 0.618 -> 0.655Improved
evaluate tracker on 240 FPS frames instead of 30 FPS (ablation)FEAR-XS · NFSPrecision Score: 0.753 -> 0.816Improved
run models in float16 instead of float32 (ablation)FEAR trackers · mobile inferenceaccuracy: ±0.5%No clear effect
keep original backbone resolution rather than upscaling (ablation)FEAR-XS · FLOPsbackbone GigaFLOPs: 0.840 -> 0.318Improved

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