From Pixels to Graphs: using Scene and Knowledge Graphs for HD-EPIC VQA Challenge
This addresses complex egocentric visual question answering for AI systems, though it appears incremental as it combines existing graph and knowledge techniques.
The authors tackled the HD-EPIC VQA Challenge 2025 by developing SceneNet and KnowledgeNet, which use scene graphs and external commonsense knowledge to improve visual question answering, achieving an overall accuracy of 44.21% on the benchmark.
This report presents SceneNet and KnowledgeNet, our approaches developed for the HD-EPIC VQA Challenge 2025. SceneNet leverages scene graphs generated with a multi-modal large language model (MLLM) to capture fine-grained object interactions, spatial relationships, and temporally grounded events. In parallel, KnowledgeNet incorporates ConceptNet's external commonsense knowledge to introduce high-level semantic connections between entities, enabling reasoning beyond directly observable visual evidence. Each method demonstrates distinct strengths across the seven categories of the HD-EPIC benchmark, and their combination within our framework results in an overall accuracy of 44.21% on the challenge, highlighting its effectiveness for complex egocentric VQA tasks.