Overview of the NLPCC 2026 Shared Task 1: Difficulty-Aware Multilingual and Multimodal Medical Instructional Video Understanding Evaluation

2026-07-07

AI Summary

This work addresses the lack of difficulty differentiation in question-answering tasks for multilingual, multimodal medical instructional videos by introducing MedVidQA, the first difficulty-aware benchmark for medical video question answering. The benchmark explicitly categorizes question difficulty based on the type of evidence required—ranging from caption-only text to visual grounding, procedural understanding, and cross-modal reasoning—and establishes three subtask tracks for systematic evaluation. It features a high-quality multilingual dataset spanning emergency care, rehabilitation, and nursing scenarios, integrating temporal localization, video retrieval, and cross-video corpus-based QA. Difficulty levels are defined through a human-validated grading scheme. Already attracting multiple participating teams, MedVidQA advances fine-grained multimodal reasoning evaluation and provides a practical, representative platform for medical video understanding.

Abstract

Following the CMIVQA, MMI-VQA, and M4IVQA challenges in NLPCC 2023--2025, we introduce the Difficulty-Aware Medical Instructional Video Question Answering (DA-MIVQA) shared task for NLPCC 2026. DA-MIVQA extends previous multilingual and multimodal medical video benchmarks by explicitly distinguishing questions according to the type and complexity of evidence required for answering. Specifically, simple questions can often be answered from subtitle-based textual cues, whereas complex questions require visual grounding, procedural understanding, and cross-modal evidence integration. The challenge contains three tracks: Difficulty-Aware Temporal Answer Grounding in Single Video (DA-TAGSV), Difficulty-Aware Video Corpus Retrieval (DA-VCR), and Difficulty-Aware Temporal Answer Grounding in Video Corpus (DA-TAGVC). The dataset is collected from public medical instructional channels, covers diverse scenarios such as first aid, emergency response, rehabilitation, nursing, and general medical education, and is manually verified with difficulty annotations. This paper presents the task motivation, dataset construction, evaluation protocol, participation overview, competition results, and representative systems of DA-MIVQA. DA-MIVQA provides a practical benchmark for evaluating medical instructional video question answering systems under varying textual, visual, temporal, and procedural reasoning requirements.

Problem

• medical instructional video
• difficulty-aware question answering
• multimodal understanding
• video question answering
• cross-modal reasoning

Innovation

• Difficulty-Aware
• Multimodal Medical Video QA
• Temporal Answer Grounding
• Cross-Modal Reasoning
• Video Corpus Retrieval