AssistQ: Affordance-centric Question-driven Task Completion for Egocentric Assistant
This work addresses a problem for developers of egocentric AI assistants like AR glasses or robots, by providing a foundational task and dataset, though it is incremental in advancing the field.
The paper tackles the lack of clear task definition and benchmarks for affordance-centric question-driven task completion in egocentric AI assistants, by introducing a new dataset (AssistQ with 531 samples) and a Q2A model that significantly outperforms VQA baselines.
A long-standing goal of intelligent assistants such as AR glasses/robots has been to assist users in affordance-centric real-world scenarios, such as "how can I run the microwave for 1 minute?". However, there is still no clear task definition and suitable benchmarks. In this paper, we define a new task called Affordance-centric Question-driven Task Completion, where the AI assistant should learn from instructional videos to provide step-by-step help in the user's view. To support the task, we constructed AssistQ, a new dataset comprising 531 question-answer samples from 100 newly filmed instructional videos. We also developed a novel Question-to-Actions (Q2A) model to address the AQTC task and validate it on the AssistQ dataset. The results show that our model significantly outperforms several VQA-related baselines while still having large room for improvement. We expect our task and dataset to advance Egocentric AI Assistant's development. Our project page is available at: https://showlab.github.io/assistq/.