# PolySmart @ TRECVid 2024 Medical Video Question Answering

Source: [PolySmart @ TRECVid 2024 Medical Video Question Answering](<https://www.sota2.com/research/paper/68fa764d1e209131cea6c419>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T03:50:30.323Z

Authors: Jiaxin Wu, Yiyang Jiang, Xiao-Yong Wei, Qing Li

Published: 2024-12-20T02:59:59.000Z

## Abstract

Video Corpus Visual Answer Localization (VCVAL) includes question-related video retrieval and visual answer localization in the videos. Specifically, we use text-to-text retrieval to find relevant videos for a medical question based on the similarity of video transcript and answers generated by GPT4. For the visual answer localization, the start and end timestamps of the answer are predicted by the alignments on both visual content and subtitles with queries. For the Query-Focused Instructional Step Captioning (QFISC) task, the step captions are generated by GPT4. Specifically, we provide the video captions generated by the LLaVA-Next-Video model and the video subtitles with timestamps as context, and ask GPT4 to generate step captions for the given medical query. We only submit one run for evaluation and it obtains a F-score of 11.92 and mean IoU of 9.6527.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2412.15514>)

[PDF](<https://arxiv.org/pdf/2412.15514.pdf>)