VideoLoom: A Video Large Language Model for Joint Spatial-Temporal Understanding

Jiapeng Shi, Junke Wang, Zuyao You, Bo He, Zuxuan Wu
1/12/2026
cs.CV

No official code found. Best implementation: JPShi12/VideoLoom (27 stars, last commit 2026-01-23).

Abstract

This paper presents VideoLoom, a unified Video Large Language Model (Video LLM) for joint spatial-temporal understanding. To facilitate the development of fine-grained spatial and temporal localization capabilities, we curate LoomData-8.7k, a human-centric video dataset with temporally grounded and spatially localized captions. With this, VideoLoom achieves state-of-the-art or highly competitive performance across a variety of spatial and temporal benchmarks (e.g., 63.1 J&F on ReVOS for referring video object segmentation, and 48.3 [email protected] on Charades-STA for temporal grounding). In addition, we introduce LoomBench, a novel benchmark consisting of temporal, spatial, and compositional video-question pairs, enabling a comprehensive evaluation of Video LLMs from diverse aspects. Collectively, these contributions offer a universal and effective suite for joint spatial-temporal video understanding, setting a new standard in multimodal intelligence.

View on arXivView PDF

Code Implementations(1)

JPShi12/VideoLoomCommunity62%

VideoLoom: A Video Large Language Model for Joint Spatial-Temporal Understanding

270Shell, PythonJan 13, 20269 months ago

Similar Papers

VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs

89% match2 repos1.3k2024

TimeMarker: A Versatile Video-LLM for Long and Short Video Understanding with Superior Temporal Localization Ability

89% match1 repo1092024

VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM

89% match1 repo3532025

Do Language Models Understand Time?

87% match1 repo112024

SIMS-V: Simulated Instruction-Tuning for Spatial Video Understanding

87% match2025

SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models

87% match1 repo2952024

Cite this paper

@article{shi2026videoloom,
  title  = {VideoLoom: A Video Large Language Model for Joint Spatial-Temporal Understanding},
  author = {Jiapeng Shi and Junke Wang and Zuyao You and Bo He and Zuxuan Wu},
  year   = {2026},
  eprint = {2601.07290},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2601.07290v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2601.07290.svg)](https://codeofpaper.com/paper/2601.07290)

Discussion