{
  "annotation_id": "07a426f3-1cbe-402c-8267-3016d700fb87",
  "date_created": "2026-02-17T05:53:12.656000Z",
  "date_modified": "2026-02-17T05:53:12.656000Z",
  "file_hash": "630b3ce9d0ddbc05ff395d60f9bf62c11045d9055be1dff2e0df0916c03f7ca3",
  "private": false,
  "record": {
    "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\u0026F on ReVOS for referring video object segmentation, and 48.3 R1@0.7 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.",
    "arxiv_id": "2601.07290",
    "authors": [
      "Jiapeng Shi",
      "Junke Wang",
      "Zuyao You",
      "Bo He",
      "Zuxuan Wu"
    ],
    "categories": [
      "cs.CV"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "title": "VideoLoom: A Video Large Language Model for Joint Spatial-Temporal Understanding",
    "url": "https://arxiv.org/abs/2601.07290",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "f724c117-1c7f-48cb-b077-27ca54cb98ef",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}