# Learning reusable concepts across different egocentric video understanding tasks

arXiv: https://arxiv.org/abs/2505.24690 · HTML: https://mlsanity.com/paper/2505.24690/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 10 references that are in the map.
- First posted on arXiv 30 May 2025.

## Builds on (most cited first, 9 of 9)

- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification](https://mlsanity.com/paper/2211.11158/) (2022)
- [Egocentric Video-Language Pretraining](https://mlsanity.com/paper/2206.01670/) (2022)
- [Static and Dynamic Concepts for Self-supervised Video Representation Learning](https://mlsanity.com/paper/2207.12795/) (2022)
- [Understanding Video Transformers via Universal Concept Discovery](https://mlsanity.com/paper/2401.10831/) (2024)
- [Egocentric Video Task Translation](https://mlsanity.com/paper/2212.06301/) (2022)
- [Concept Bottleneck Models Without Predefined Concepts](https://mlsanity.com/paper/2407.03921/) (2024)
- [A Backpack Full of Skills: Egocentric Video Understanding with Diverse Task Perspectives](https://mlsanity.com/paper/2403.03037/) (2024)

## Abstract (arXiv)

Our comprehension of video streams depicting human activities is naturally multifaceted: in just a few moments, we can grasp what is happening, identify the relevance and interactions of objects in the scene, and forecast what will happen soon, everything all at once. To endow autonomous systems with such holistic perception, learning how to correlate concepts, abstract knowledge across diverse tasks, and leverage tasks synergies when learning novel skills is essential. In this paper, we introduce Hier-EgoPack, a unified framework able to create a collection of task perspectives that can be carried across downstream tasks and used as a potential source of additional insights, as a backpack of skills that a robot can carry around and use when needed.