HD-EPIC benchmark

The HD-EPIC benchmark is a dataset used to evaluate visual question answering (VQA) tasks, specifically focusing on complex egocentric scenarios across seven categories.

Papers using HD-EPIC benchmark (3)

Semantic and Visual Evidence for Efficient Long-Video Reasoning: A Solution for the HD-EPIC VQA Challenge2026Belief-Aware VLM Model for Human-like Reasoning2026From Pixels To Graphs: Using Scene And Knowledge Graphs For HD-EPIC VQA Challenge2025