AI Paper Atlas

Research map / Video / Video segmentation and tracking

MoT3DVG: A Benchmark for Outdoor 3D Visual Grounding with Motion-Aware Descriptions and Temporal Cues

Shijia Zhao, Xusheng Guo, Qiming Xia, Xun Huang, KeZheng Xiong, Zhihong Liu, Chenglu Wen

NeurIPS 2026 · Video › Video segmentation and tracking · approach: Layered video decomposition and dynamics · 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.

Introduces MoT3DVG, a benchmark for outdoor 3D visual grounding that uses motion-aware language descriptions and temporal cues to address static-object limitations of existing indoor 3DVG research.

Problem

Existing 3D visual grounding research focuses on static indoor objects, which limits its use in dynamic outdoor autonomous driving scenes where motion descriptions capture the temporal dynamics of moving objects.

Approach

A benchmark pairing outdoor 3D scenes with motion-aware referring descriptions and temporal cues for grounding moving objects; the abstract is truncated so the specific method details are not stated.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add SLIDE temporal encoding of historical point clouds3EED-style grounder · MoT3DVG overallAcc@0.5m: 54.94 -> 57.34Improved
add SLIDE temporal encoding3EED-style grounder · MoT3DVG Unique subset 0-20mAcc@1.0m: 57.08 -> 50.68Hurt
add SLIDE temporal encoding3EED-style grounder · MoT3DVG Multiple subsetAcc@0.5m: 47.96 -> 60.25Improved
add short-term window encoding only (ablation)DynaVG · MoT3DVG overallAcc@0.5m: 54.94 -> 55.20Improved
add long-term window shifting on top of STWE (ablation)DynaVG · MoT3DVG overallAcc@0.5m: 55.20 -> 57.34Improved
use SLIDE instead of concatenating historical frames (ablation)3EED · MoT3DVG overallAcc@0.5m: 56.04 -> 57.34Improved
use fine-grained temporal motion descriptions instead of coarse motion (ablation)DynaVG · MoT3DVG overallAcc@0.5m: 54.76 -> 57.34Improved
remove motion attributes from prompts (ablation)DynaVG · MoT3DVG overallAcc@0.5m: 57.34 -> 54.33Hurt
remove appearance attributes from prompts (ablation)DynaVG · MoT3DVG overallAcc@0.5m: 57.34 -> 58.63 (Acc@1.0 69.66 -> 69.15)No clear effect
add RGB image semantics to LiDAR input (ablation)DynaVG · MoT3DVG overallAcc@0.5m: 57.34 -> 58.20Improved
add adaptive temporal gating (ablation)DynaVG · MoT3DVG Unique and long rangeAcc/mIoU: 0-20m overall Acc@0.5 64.87 -> 66.40; Unique 0-20m mIoU 19.02 -> 18.93Mixed
apply DynaVG on 3EED Vehicle dataset3EED · 3EED VehicleAcc@0.5 IoU: 45.72 -> 46.97Improved

Limitations

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