AI Paper Atlas

Research map / Video / Video segmentation and tracking

Beyond Token Representations: Explicit Visual Object Grounding for Video Reasoning Segmentation

Jun Huang, zhangjunyang, Zijie Yue, Bingkun Wang, Yong Luo, Miaojing Shi

NeurIPS 2026 · Video › Video segmentation and tracking · approach: Matching-based video object segmentation · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes explicit visual object grounding for video reasoning segmentation, moving beyond segmentation tokens that are semantically monotonous and spatially ambiguous.

Problem

Video Reasoning Segmentation (VRS) must infer and segment target objects from reasoning queries in videos; existing methods compress the target into a few segmentation tokens that are semantically monotonous and spatially ambiguous, which is insufficient for mask decoding.

Approach

Replaces or augments implicit segmentation tokens with explicit visual object grounding, so the model grounds the target object visually rather than representing it only through token embeddings. Details beyond the abstract are not stated in the provided text.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add spatial-aware prompt generation and refinement (box and points) instead of segmentation tokens (ablation)EVOG · MeViSJ&F: 45.5 -> 60.1Improved
add point set prompts (ablation)EVOG · MeViSJ&F: 49.5 -> 60.1Improved
add bounding box prompts (ablation)EVOG · MeViSJ&F: 57.4 -> 60.1Improved
add multi-step point refinement (R=1 to trained R=4, test R=2) (ablation)EVOG · MeViSJ&F: 53.7 -> 60.1Improved
also apply multi-step refinement to bounding boxes (ablation)EVOG · MeViSJ&F: 60.1 -> 60.1No clear effect
add query diversification and alignment (training only) (ablation)EVOG · MeViSJ&F: 57.2 -> 60.1Improved
use Gaussian symmetric-KL point consistency instead of nearest-point matching (ablation)QDA · MeViSJ&F: 57.6 -> 60.1Improved
add prompt-based keyframe selection instead of image-text similarity (ablation)EVOG · MeViSJ&F: 57.0 -> 60.1Improved
replace SAM2 decoder with SAM3 (ablation)EVOG · MeViSJ&F: 60.1 -> 60.6No clear effect
scale MLLM backbone up (ablation)EVOG · MeViSJ&F: 58.5 -> 60.1Improved
increase number of predicted points K from 1 to 7 (ablation)SPGR · MeViSJ&F: 56.0 -> 60.1Improved
add full pipeline over UniPixel on ReVOS reasoning splitEVOG vs UniPixel · ReVOS reasoningJ&F: +1.8% J&FImproved

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