Seahawk at MedGenVidQA 2026: LLM Segment-Range Selection for Medical Visual Answer Localization
Year: 2026
Type: conference-paper
Abstract: Medical visual answer localization requires identifying the temporal span in a video where a medical question is answered or visually explained.We present a simple retrieval-andselection pipeline for Task C that treats visual answer localization as segment-level answer paragraph selection over timestamped video transcripts.Given a question and a segmented transcript, our system prompts DeepSeek to select a contiguous range of transcript segments rather than directly generating timestamps.The final start and end times are then computed deterministically from the selected segment boundaries, decreasing the risk of hallucinated or malformed temporal outputs.To support long videos, we apply overlapping slidingwindow prompting and rank candidate ranges using lexical question.In a 20-sample sanity check on test dataset, a completeness-biased configuration achieved an mIoU of 0.3217, while a shorter duration-penalized configuration improved performance to 0.4815.These results suggest that constrained LLM-based segment selection, combined with deterministic timestamp extraction, is a practical baseline for medical visual answer localization.
Authors: Xiaotian Tian, Gulustan Dogan
Institutions: Nankai University, University of North Carolina Wilmington
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
OpenAlex ID: W7166844934