First Place Solution to the CVPR'2023 AQTC Challenge: A Function-Interaction Centric Approach with Spatiotemporal Visual-Language Alignment

TT Chen, H Yu, Z Yang, M Li, Z Li, J Wang… - arXiv preprint arXiv …, 2023 - arxiv.org
Affordance-Centric Question-driven Task Completion (AQTC) has been proposed to acquire
knowledge from videos to furnish users with comprehensive and systematic instructions …

A Solution to CVPR'2023 AQTC Challenge: Video Alignment for Multi-Step Inference

C Zhang, S Wu, S Zhao, T Xu, E Chen - arXiv preprint arXiv:2306.14412, 2023 - arxiv.org
Affordance-centric Question-driven Task Completion (AQTC) for Egocentric Assistant
introduces a groundbreaking scenario. In this scenario, through learning instructional …