AI Paper Atlas

Research map / Video / Video-language understanding

Towards Long-Form Spatio-Temporal Video Grounding

Xin Gu, Bing Fan, Jiali Yao, Zhipeng Zhang, Yan Huang, Cheng Han, Heng Fan, Libo Zhang

ECCV 2026 · Video › Video-language understanding · approach: Long video understanding · 2 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 all temporal memories without selection (ablation)ART-STVG · LF-STVG-3minm_tIoU: 16.7 -> 9.6Hurt
add temporal memory selection on top of temporal memory (ablation)ART-STVG · LF-STVG-3minm_tIoU: 9.6 -> 23.0Improved
add selective temporal memory vs none (ablation)ART-STVG · LF-STVG-3minm_tIoU: 16.7 -> 23.0Improved
add all spatial memories without selection (ablation)ART-STVG · LF-STVG-3minm_tIoU: 21.3 -> 22.1Improved
add spatial memory selection (ablation)ART-STVG · LF-STVG-3minm_tIoU: 22.1 -> 23.0Improved
use cascaded instead of parallel spatial-temporal decoders (ablation)ART-STVG · LF-STVG-3minm_tIoU: 21.5 -> 23.0Improved
set N_s to 32 instead of 16 (ablation)ART-STVG · LF-STVG-3minm_tIoU: 22.7 -> 23.0Improved
increase N_s from 32 to 48 (ablation)ART-STVG · LF-STVG-3minm_tIoU: 23.0 -> 22.5Hurt
raise temporal similarity threshold from 0.8 to 0.9 (ablation)ART-STVG · LF-STVG-5minm_tIoU: 15.0 -> 14.4Hurt
lower temporal similarity threshold from 0.8 to 0.7 (ablation)ART-STVG · LF-STVG-1minm_tIoU: 39.1 -> 38.7Hurt
add memory modules to baselinebaseline · LF-STVG-3minm_tIoU: 16.2 -> 23.0Improved
add memory modules to baselinebaseline · LF-STVG-5minm_vIoU: 5.3 -> 10.0Improved

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