{
  "annotation_id": "962baeec-5373-4166-ae25-ca42fcad7a51",
  "date_created": "2026-02-17T05:53:11.557000Z",
  "date_modified": "2026-02-17T05:53:11.557000Z",
  "file_hash": "a5100c9be56516264965baa91f311cd067528f7c58e5ffd02b3765cd4c50f95b",
  "private": false,
  "record": {
    "abstract": "Video Question Answering (VideoQA) models enhance understanding and interaction with audiovisual content, making it more accessible, searchable, and useful for a wide range of fields such as education, surveillance, entertainment, and content creation. Due to heavy compute requirements, most large visual language models (VLMs) for VideoQA rely on a fixed number of frames by uniformly sampling the video. However, this process does not pick important frames or capture the context of the video. We present a novel query-based selection of frames relevant to the questions based on the submodular mutual Information (SMI) functions. By replacing uniform frame sampling with query-based selection, our method ensures that the chosen frames provide complementary and essential visual information for accurate VideoQA. We evaluate our approach on the MVBench dataset, which spans a diverse set of multi-action video tasks. VideoQA accuracy on this dataset was assessed using two VLMs, namely Video-LLaVA and LLaVA-NeXT, both of which originally employed uniform frame sampling. Experiments were conducted using both uniform and query-based sampling strategies. An accuracy improvement of up to \\textbf{4\\%} was observed when using query-based frame selection over uniform sampling. Qualitative analysis further highlights that query-based selection, using SMI functions, consistently picks frames better aligned with the question. We opine that such query-based frame selection can enhance accuracy in a wide range of tasks that rely on only a subset of video frames.",
    "arxiv_id": "2601.07459",
    "authors": [
      "Himanshu Patil",
      "Geo Jolly",
      "Ramana Raja Buddala",
      "Ganesh Ramakrishnan",
      "Rohit Saluja"
    ],
    "categories": [
      "cs.CV",
      "cs.LG"
    ],
    "doi": "10.1145/3774521.3774607",
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "title": "Improving Video Question Answering through query-based frame selection",
    "url": "https://arxiv.org/abs/2601.07459",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "e034a187-728b-4eec-b694-069a81dc97ef",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}