AI Paper Atlas

Research map / Video / Video-language understanding

STAC: Selective Spatiotemporal Aggregation and Compression for Video Reasoning Segmentation

Hesham Syed, Yun Liu, Guolei Sun, Jing Yang, Henghui Ding, Xue Geng, Xudong Jiang

ECCV 2026 · Video › Video-language understanding · approach: Long video understanding · 0 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 unidirectional temporal scan to spatial scan (ablation)STAC SSA · ReasonVOS ablation (32 frames, 3K iterations)J&F: 44.1 -> 49.6Improved
add bidirectional spatial scan to temporal scan (ablation)STAC SSA · ReasonVOS ablation (32 frames, 3K iterations)J&F: 45.2 -> 49.6Improved
use bidirectional temporal scan instead of unidirectional (ablation)STAC SSA · ReasonVOS ablation (32 frames, 3K iterations)J&F: 42.7 vs 49.6Hurt
merge tokens by averaging instead of pruning (ablation)STAC HSC · ReasonVOS ablation (32 frames, 3K iterations)J&F: 47.9 -> 49.6Improved
compress temporally first instead of spatially first (ablation)STAC HSC · ReasonVOS ablation (32 frames, 3K iterations)J&F: 45.7 -> 49.6Improved
scan spatially first instead of temporally first (ablation)STAC SSA · ReasonVOS ablation (32 frames, 3K iterations)J&F: 31.3 -> 45.7Improved
add SSA enhancement plus compression to uncompressed baseline (ablation)STAC · ReasonVOS ablation (32 frames, 3K iterations)J&F: 48.1 -> 49.6Improved
causal online inference instead of offlineSTAC · Ref-DAVIS17J&F: 73.6 -> 72.5Hurt
causal online inference instead of offlineSTAC · ReasonVOSJ&F: 52.3 -> 48.8Hurt
compress 85% of visual tokens with STAC vs GLUS full tokensSTAC · ReasonVOSJ&F: 49.8 -> 52.3Improved
compress 85% of visual tokens with STAC vs GLUS full tokensSTAC · MeViSJ&F: 50.3 -> 49.9Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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