# Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video

arXiv: https://arxiv.org/abs/2005.02190 · HTML: https://mlsanity.com/paper/2005.02190/

## Key facts

- Cited by 120 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 May 2020.

## Built on by (most cited first, 30 of 120)

- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [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)
- [MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition](https://mlsanity.com/paper/2201.08383/) (2022)
- [MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound](https://mlsanity.com/paper/2201.02639/) (2022)
- [EgoTaskQA: Understanding Human Tasks in Egocentric Videos](https://mlsanity.com/paper/2210.03929/) (2022)
- [Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos](https://mlsanity.com/paper/2204.01696/) (2022)
- [Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos](https://mlsanity.com/paper/2104.07905/) (2021)
- [My View is the Best View: Procedure Learning from Egocentric Videos](https://mlsanity.com/paper/2207.10883/) (2022)
- [HierVL: Learning Hierarchical Video-Language Embeddings](https://mlsanity.com/paper/2301.02311/) (2023)
- [Real-time Online Video Detection with Temporal Smoothing Transformers](https://mlsanity.com/paper/2209.09236/) (2022)
- [E2(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognition](https://mlsanity.com/paper/2112.03596/) (2021)
- [NaQ: Leveraging Narrations as Queries to Supervise Episodic Memory](https://mlsanity.com/paper/2301.00746/) (2023)
- [HRP: Human Affordances for Robotic Pre-Training](https://mlsanity.com/paper/2407.18911/) (2024)
- [Egocentric Audio-Visual Object Localization](https://mlsanity.com/paper/2303.13471/) (2023)
- [Interaction Region Visual Transformer for Egocentric Action Anticipation](https://mlsanity.com/paper/2211.14154/) (2022)
- [MECCANO: A Multimodal Egocentric Dataset for Humans Behavior Understanding in the Industrial-like Domain](https://mlsanity.com/paper/2209.08691/) (2022)
- [Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognition](https://mlsanity.com/paper/2110.10101/) (2021)
- [Video-Mined Task Graphs for Keystep Recognition in Instructional Videos](https://mlsanity.com/paper/2307.08763/) (2023)
- [Can't make an Omelette without Breaking some Eggs: Plausible Action Anticipation using Large Video-Language Models](https://mlsanity.com/paper/2405.20305/) (2024)
- [Egocentric Prediction of Action Target in 3D](https://mlsanity.com/paper/2203.13116/) (2022)
- [Whole-Body Conditioned Egocentric Video Prediction](https://mlsanity.com/paper/2506.21552/) (2025)
- [Rethinking Learning Approaches for Long-Term Action Anticipation](https://mlsanity.com/paper/2210.11566/) (2022)
- [EgoTracks: A Long-term Egocentric Visual Object Tracking Dataset](https://mlsanity.com/paper/2301.03213/) (2023)
- [Differentiable Task Graph Learning: Procedural Activity Representation and Online Mistake Detection from Egocentric Videos](https://mlsanity.com/paper/2406.01486/) (2024)
- [Visual Object Tracking in First Person Vision](https://mlsanity.com/paper/2209.13502/) (2022)
- [Learning State-Aware Visual Representations from Audible Interactions](https://mlsanity.com/paper/2209.13583/) (2022)
- [StillFast: An End-to-End Approach for Short-Term Object Interaction Anticipation](https://mlsanity.com/paper/2304.03959/) (2023)
- [Is First Person Vision Challenging for Object Tracking?](https://mlsanity.com/paper/2108.13665/) (2021)
- [Summarize the Past to Predict the Future: Natural Language Descriptions of Context Boost Multimodal Object Interaction Anticipation](https://mlsanity.com/paper/2301.09209/) (2023)

## Abstract (arXiv)

In this paper, we tackle the problem of egocentric action anticipation, i.e., predicting what actions the camera wearer will perform in the near future and which objects they will interact with. Specifically, we contribute Rolling-Unrolling LSTM, a learning architecture to anticipate actions from egocentric videos. The method is based on three components: 1) an architecture comprised of two LSTMs to model the sub-tasks of summarizing the past and inferring the future, 2) a Sequence Completion Pre-Training technique which encourages the LSTMs to focus on the different sub-tasks, and 3) a Modality ATTention (MATT) mechanism to efficiently fuse multi-modal predictions performed by processing RGB frames, optical flow fields and object-based features. The proposed approach is validated on EPIC-Kitchens, EGTEA Gaze+ and ActivityNet. The experiments show that the proposed architecture is state-of-the-art in the domain of egocentric videos, achieving top performances in the 2019 EPIC-Kitchens egocentric action anticipation challenge. The approach also achieves competitive performance on ActivityNet with respect to methods not based on unsupervised pre-training and generalizes to the tasks of early action recognition and action recognition. To encourage research on this challenging topic, we made our code, trained models, and pre-extracted features available at our web page: http://iplab.dmi.unict.it/rulstm.