AI Paper Atlas

Research map / Video / Video-language understanding

Object-centric Video Question Answering with Visual Grounding and Referring

Haochen Wang, Qirui Chen, Cilin Yan, Jiayin Cai, Xiaolong Jiang, Yao Hu, Weidi Xie, Stratis Gavves

ICCV 2025 · Video › Video-language understanding · approach: Video question answering · 11 citations (OpenAlex)

Read the paper

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 STOM (track and overlay visual prompts on all frames) (ablation)RGA3-7B · VideoInfer testGPT-4o accuracy / score: 43.6 / 2.46 -> 46.7 / 2.60Improved
add STOM (ablation)RGA3-7B · VideoRefer-Bench-Qaccuracy (%): 72.2 -> 74.0Improved
propagate prompts with ground-truth masks (oracle) instead of tracker (ablation)RGA3-7B · VideoInfer testGPT-4o accuracy: 46.7 -> 44.8Hurt
replace SAM decoder with SAM2 as grounding module (ablation)RGA3-7B · ReVOSJ&F: 55.4 -> 58.0Improved
replace SAM decoder with SAM2 (ablation)RGA3-7B · ReasonSeg valgIoU: 68.5 -> 68.7No clear effect
co-train segmentation and QA data instead of segmentation only (ablation)RGA3-3B · ReasonVOSJ&F: 48.7 -> 51.7Improved
use alpha-blended visual prompt overlay instead of region features via mask poolingRGA3 · VideoRefer-Bench-Qaverage accuracy (%): 71.9 -> 74.0Improved
scale RGA3 from 3B to 7BRGA3 · ReVOS overallJ&F: 56.1 -> 58.0Improved
multi-task joint training of all tasksRGA3 · individual taskstask performanceHurt
increase video duration in LongVideoBench evaluationRGA3-7B · LongVideoBench valaccuracy (%): 72.5 -> 46.3Hurt

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