AI Paper Atlas

Research map / Video / Video-language understanding

SPOT: Spatiotemporal Prompt Optimization for Motion-Stabilized MLLM-Guided Video Segmentation

Jiayi Fan, Zheyun Qin, Xiaoming Xi, Xiushan Nie, Yilong Yin

CVPR 2026 · Video › Video-language understanding · approach: Long video understanding

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 Brownian bridge loss (ablation)SPOT-7B · Ref-YouTube-VOSJ&F: 65.2 -> 70.5Improved
add prompt quality-aware loss (ablation)SPOT-7B · Ref-YouTube-VOSJ&F: 62.7 -> 70.5Improved
add text alignment loss (ablation)SPOT-7B · Ref-YouTube-VOSJ&F: 67.8 -> 70.5Improved
original SAM with SPOT losses vs SAM 2 baseline (ablation)MLLM + SAM · Ref-YouTube-VOSJ&F: 66.9 -> 70.5Improved
variance-adaptive weighting instead of constant weighting (ablation)Brownian bridge loss · Ref-YouTube-VOSJ&F: 68.7 -> 70.5Improved
supervise intermediate frames instead of endpoints only (ablation)Brownian bridge loss · Ref-YouTube-VOSJ&F: 67.3 -> 70.5Improved
add geometric (BCE) point supervision (ablation)prompt quality loss · Ref-YouTube-VOSJ&F: 67.8 -> 70.5Improved
add bounding box loss (ablation)prompt quality loss · Ref-YouTube-VOSJ&F: 68.3 -> 70.5Improved
scale SPOT from 7B to 13BSPOT · ReVOS overallJ&F: 52.7 -> 54.8Improved
SPOT vs prior best on Ref-YouTube-VOSSPOT-7B · Ref-YouTube-VOSJ&F: 69.2 -> 70.5Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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