AI Paper Atlas

Research map / Video / Video segmentation and tracking

Scanpath Prediction in Panoramic Videos via Expected Code Length Minimization

Mu Li, Kanglong Fan, Kede Ma

TPAMI 2026 · Video › Video segmentation and tracking · approach: Layered video decomposition and dynamics · 6 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 historical path context to visual-only model (ablation)Ours · CVPR18maxTC: 0.517 -> 0.623Improved
add causal path context (ablation)Ours (Visual + H-Path) · CVPR18maxTC: 0.623 -> 0.708Improved
add causal path context (ablation)Ours (Visual + H-Path) · VRW23maxTC: 0.712 -> 0.796Improved
add visual context to path-only model (ablation)Ours · VRW23maxTC: 0.687 -> 0.712Improved
use expected code length instead of MSE (relative uv) (ablation)Ours · CVPR18maxTC: 0.449 -> 0.708Improved
use expected code length instead of MAE (relative uv) (ablation)Ours · VRW23maxTC: 0.707 -> 0.796Improved
use relative uv instead of spherical coordinates (expected code length loss) (ablation)Ours · CVPR18maxTC: 0.656 -> 0.708Improved
use relative uv instead of 3D Euclidean (expected code length loss) (ablation)Ours · VRW23maxTC: 0.748 -> 0.796Improved
use PID controller sampler instead of beam search (Visual + H-Path + C-Path) (ablation)Ours · one-second videosmaxTC: 0.349 -> 0.844Improved
use PID controller sampler instead of max sampler (Visual + H-Path + C-Path) (ablation)Ours · one-second videosmaxTC: 0.360 -> 0.844Improved
add causal path context under max sampler (ablation)Ours (Visual + H-Path) · one-second videosmaxTC: 0.451 -> 0.360Hurt
add causal path context under PID sampler (ablation)Ours (Visual + H-Path) · one-second videosmaxTC: 0.786 -> 0.844Improved

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