CVNov 24, 2022

Multi-Task Learning of Object State Changes from Uncurated Videos

arXiv:2211.13500v114 citationsh-index: 78
Originality Incremental advance
AI Analysis

This addresses the challenge of understanding object interactions in videos for applications like robotics and video analysis, though it is incremental with multi-task and self-supervised enhancements.

The paper tackled the problem of temporally localizing object state changes and state-modifying actions in long uncurated web videos, achieving a 40% relative improvement over prior single-task methods and outperforming zero-shot models.

We aim to learn to temporally localize object state changes and the corresponding state-modifying actions by observing people interacting with objects in long uncurated web videos. We introduce three principal contributions. First, we explore alternative multi-task network architectures and identify a model that enables efficient joint learning of multiple object states and actions such as pouring water and pouring coffee. Second, we design a multi-task self-supervised learning procedure that exploits different types of constraints between objects and state-modifying actions enabling end-to-end training of a model for temporal localization of object states and actions in videos from only noisy video-level supervision. Third, we report results on the large-scale ChangeIt and COIN datasets containing tens of thousands of long (un)curated web videos depicting various interactions such as hole drilling, cream whisking, or paper plane folding. We show that our multi-task model achieves a relative improvement of 40% over the prior single-task methods and significantly outperforms both image-based and video-based zero-shot models for this problem. We also test our method on long egocentric videos of the EPIC-KITCHENS and the Ego4D datasets in a zero-shot setup demonstrating the robustness of our learned model.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes