# Long-Term Anticipation of Activities with Cycle Consistency

arXiv: https://arxiv.org/abs/2009.01142 · HTML: https://mlsanity.com/paper/2009.01142/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Sep 2020.

## Built on by (most cited first, 30 of 40)

- [Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities](https://mlsanity.com/paper/2203.14712/) (2022)
- [AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?](https://mlsanity.com/paper/2307.16368/) (2023)
- [EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level Planning](https://mlsanity.com/paper/2312.06722/) (2023)
- [Future Transformer for Long-term Action Anticipation](https://mlsanity.com/paper/2205.14022/) (2022)
- [Predicting the Future from First Person (Egocentric) Vision: A Survey](https://mlsanity.com/paper/2107.13411/) (2021)
- [PDPP: Projected Diffusion for Procedure Planning in Instructional Videos](https://mlsanity.com/paper/2303.14676/) (2023)
- [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)
- [Multi-Modal Temporal Convolutional Network for Anticipating Actions in Egocentric Videos](https://mlsanity.com/paper/2107.09504/) (2021)
- [VideoLLaMB: Long Streaming Video Understanding with Recurrent Memory Bridges](https://mlsanity.com/paper/2409.01071/) (2024)
- [On the Pitfalls of Batch Normalization for End-to-End Video Learning: A Study on Surgical Workflow Analysis](https://mlsanity.com/paper/2203.07976/) (2022)
- [A Survey on Deep Learning Techniques for Action Anticipation](https://mlsanity.com/paper/2309.17257/) (2023)
- [Multimodal Large Models Are Effective Action Anticipators](https://mlsanity.com/paper/2501.00795/) (2025)
- [GePSAn: Generative Procedure Step Anticipation in Cooking Videos](https://mlsanity.com/paper/2310.08312/) (2023)
- [DiffAnt: Diffusion Models for Action Anticipation](https://mlsanity.com/paper/2311.15991/) (2023)
- [Human Action Anticipation: A Survey](https://mlsanity.com/paper/2410.14045/) (2024)
- [Action Anticipation from SoccerNet Football Video Broadcasts](https://mlsanity.com/paper/2504.12021/) (2025)
- [Uncertainty-boosted Robust Video Activity Anticipation](https://mlsanity.com/paper/2404.18648/) (2024)
- [Hierarchical and Multimodal Data for Daily Activity Understanding](https://mlsanity.com/paper/2504.17696/) (2025)
- [Higher Order Recurrent Space-Time Transformer for Video Action Prediction](https://mlsanity.com/paper/2104.08665/) (2021)
- [A-ACT: Action Anticipation through Cycle Transformations](https://mlsanity.com/paper/2204.00942/) (2022)
- [Multiscale Video Pretraining for Long-Term Activity Forecasting](https://mlsanity.com/paper/2307.12854/) (2023)
- [Gated Temporal Diffusion for Stochastic Long-Term Dense Anticipation](https://mlsanity.com/paper/2407.11954/) (2024)
- [Review of Video Predictive Understanding: Early Action Recognition and Future Action Prediction](https://mlsanity.com/paper/2107.05140/) (2021)
- [FutureHuman3D: Forecasting Complex Long-Term 3D Human Behavior from Video Observations](https://mlsanity.com/paper/2211.14309/) (2022)
- [Cross-modal Contrastive Distillation for Instructional Activity Anticipation](https://mlsanity.com/paper/2201.06734/) (2022)
- [VS-TransGRU: A Novel Transformer-GRU-based Framework Enhanced by Visual-Semantic Fusion for Egocentric Action Anticipation](https://mlsanity.com/paper/2307.03918/) (2023)
- [Knowledge-Guided Short-Context Action Anticipation in Human-Centric Videos](https://mlsanity.com/paper/2309.05943/) (2023)
- [ActFusion: a Unified Diffusion Model for Action Segmentation and Anticipation](https://mlsanity.com/paper/2412.04353/) (2024)
- [HiMemFormer: Hierarchical Memory-Aware Transformer for Multi-Agent Action Anticipation](https://mlsanity.com/paper/2411.01455/) (2024)

## Abstract (arXiv)

With the success of deep learning methods in analyzing activities in videos, more attention has recently been focused towards anticipating future activities. However, most of the work on anticipation either analyzes a partially observed activity or predicts the next action class. Recently, new approaches have been proposed to extend the prediction horizon up to several minutes in the future and that anticipate a sequence of future activities including their durations. While these works decouple the semantic interpretation of the observed sequence from the anticipation task, we propose a framework for anticipating future activities directly from the features of the observed frames and train it in an end-to-end fashion. Furthermore, we introduce a cycle consistency loss over time by predicting the past activities given the predicted future. Our framework achieves state-of-the-art results on two datasets: the Breakfast dataset and 50Salads.