# What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attention

arXiv: https://arxiv.org/abs/1905.09035 · HTML: https://mlsanity.com/paper/1905.09035/

## Key facts

- Cited by 105 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 May 2019.

## Built on by (most cited first, 30 of 105)

- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language](https://mlsanity.com/paper/2204.00598/) (2022)
- [Affordances from Human Videos as a Versatile Representation for Robotics](https://mlsanity.com/paper/2304.08488/) (2023)
- [Anticipative Video Transformer](https://mlsanity.com/paper/2106.02036/) (2021)
- [VideoLLM: Modeling Video Sequence with Large Language Models](https://mlsanity.com/paper/2305.13292/) (2023)
- [Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos](https://mlsanity.com/paper/2204.01696/) (2022)
- [Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding](https://mlsanity.com/paper/2403.09626/) (2024)
- [Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos](https://mlsanity.com/paper/2104.07905/) (2021)
- [EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World](https://mlsanity.com/paper/2403.16182/) (2024)
- [An Outlook into the Future of Egocentric Vision](https://mlsanity.com/paper/2308.07123/) (2023)
- [Future Transformer for Long-term Action Anticipation](https://mlsanity.com/paper/2205.14022/) (2022)
- [Zero-Shot Robot Manipulation from Passive Human Videos](https://mlsanity.com/paper/2302.02011/) (2023)
- [Forecasting Action through Contact Representations from First Person Video](https://mlsanity.com/paper/2102.00649/) (2021)
- [With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognition](https://mlsanity.com/paper/2111.01024/) (2021)
- [Anticipative Feature Fusion Transformer for Multi-Modal Action Anticipation](https://mlsanity.com/paper/2210.12649/) (2022)
- [Learning to Anticipate Egocentric Actions by Imagination](https://mlsanity.com/paper/2101.04924/) (2021)
- [Memory-and-Anticipation Transformer for Online Action Understanding](https://mlsanity.com/paper/2308.07893/) (2023)
- [Anticipating human actions by correlating past with the future with Jaccard similarity measures](https://mlsanity.com/paper/2105.12414/) (2021)
- [Predicting the Future from First Person (Egocentric) Vision: A Survey](https://mlsanity.com/paper/2107.13411/) (2021)
- [MECCANO: A Multimodal Egocentric Dataset for Humans Behavior Understanding in the Industrial-like Domain](https://mlsanity.com/paper/2209.08691/) (2022)
- [Self-Regulated Learning for Egocentric Video Activity Anticipation](https://mlsanity.com/paper/2111.11631/) (2021)
- [OphNet: A Large-Scale Video Benchmark for Ophthalmic Surgical Workflow Understanding](https://mlsanity.com/paper/2406.07471/) (2024)
- [Egocentric Prediction of Action Target in 3D](https://mlsanity.com/paper/2203.13116/) (2022)
- [Rethinking Learning Approaches for Long-Term Action Anticipation](https://mlsanity.com/paper/2210.11566/) (2022)
- [Pretrained Language Models as Visual Planners for Human Assistance](https://mlsanity.com/paper/2304.09179/) (2023)
- [Multimodal Distillation for Egocentric Action Recognition](https://mlsanity.com/paper/2307.07483/) (2023)
- [Visual Object Tracking in First Person Vision](https://mlsanity.com/paper/2209.13502/) (2022)
- [A Survey on Human-aware Robot Navigation](https://mlsanity.com/paper/2106.11650/) (2021)
- [Multi-Modal Temporal Convolutional Network for Anticipating Actions in Egocentric Videos](https://mlsanity.com/paper/2107.09504/) (2021)
- [StillFast: An End-to-End Approach for Short-Term Object Interaction Anticipation](https://mlsanity.com/paper/2304.03959/) (2023)

## Abstract (arXiv)

Egocentric action anticipation consists in understanding which objects the camera wearer will interact with in the near future and which actions they will perform. We tackle the problem proposing an architecture able to anticipate actions at multiple temporal scales using two LSTMs to 1) summarize the past, and 2) formulate predictions about the future. The input video is processed considering three complimentary modalities: appearance (RGB), motion (optical flow) and objects (object-based features). Modality-specific predictions are fused using a novel Modality ATTention (MATT) mechanism which learns to weigh modalities in an adaptive fashion. Extensive evaluations on two large-scale benchmark datasets show that our method outperforms prior art by up to +7% on the challenging EPIC-Kitchens dataset including more than 2500 actions, and generalizes to EGTEA Gaze+. Our approach is also shown to generalize to the tasks of early action recognition and action recognition. Our method is ranked first in the public leaderboard of the EPIC-Kitchens egocentric action anticipation challenge 2019. Please see our web pages for code and examples: http://iplab.dmi.unict.it/rulstm - https://github.com/fpv-iplab/rulstm.