AI Paper Atlas

Research map / Detection and segmentation / Tracking

360VOT: A New Benchmark Dataset for Omnidirectional Visual Object Tracking

Huajian Huang, Yinzhe Xu, Yingshu Chen, Sai-Kit Yeung

ICCV 2023 · Detection and segmentation › Tracking · approach: Transformer-based video object tracking · 14 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
integrate the 360 tracking framework (extended BFoV search region) into AiATrackAiATrack · 360VOT BBoxS_dual (AUC): 0.405 -> 0.534Improved
integrate the 360 tracking framework into SiamXSiamX · 360VOT BBoxS_dual (AUC): 0.302 -> 0.391Improved
use extended BFoV instead of tangent BFoV for search regions (ablation)AiATrack-360 · 360VOT BBoxS_dual (AUC): 0.449 -> 0.534Improved
evaluate with rBBox annotation instead of BBoxAiATrack-360 · 360VOTS_dual: 0.534 -> 0.362Hurt
evaluate on videos with crossing border and fast motion on sphere attributesperspective-trained trackers · 360VOT attribute subsetsP_dual: SimTrack -4.2% (CB), -5.3% (FMS)Hurt
transformer trackers vs Siamese and other deep trackersbaseline trackers · 360VOT BBoxS_dual (AUC): 0.405 (AiATrack) vs 0.341 (PrDiMP) vs 0.302 (SiamX)Improved

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