3 papers
cs.CV2021
Reconstructing and grounding narrated instructional videos in 3D
Dimitri Zhukov, Ignacio Rocco, Ivan Laptev +4
Narrated instructional videos often show and describe manipulations of similar objects, e.g., repairing a particular model of a car or laptop. In this work we aim to reconstruct su…
cs.CV2019
HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips
Antoine Miech, Dimitri Zhukov, Jean-Baptiste Alayrac +3
Learning text-video embeddings usually requires a dataset of video clips with manually provided captions. However, such datasets are expensive and time consuming to create and ther…
cs.CV2019
Cross-task weakly supervised learning from instructional videos
Dimitri Zhukov, Jean-Baptiste Alayrac, Ramazan Gokberk Cinbis +3
In this paper we investigate learning visual models for the steps of ordinary tasks using weak supervision via instructional narrations and an ordered list of steps instead of stro…