Showing 2024Show all
2 papers · 1 filter
cs.CV2024
Open-Event Procedure Planning in Instructional Videos
Yilu Wu, Hanlin Wang, Jing Wang +1
Given the current visual observations, the traditional procedure planning task in instructional videos requires a model to generate goal-directed plans within a given action space.…
cs.CV2024
Contextual AD Narration with Interleaved Multimodal Sequence
Hanlin Wang, Zhan Tong, Kecheng Zheng +2
The Audio Description (AD) task aims to generate descriptions of visual elements for visually impaired individuals to help them access long-form video content, like movies. With vi…