mlsanityData to 7 Oct 2026

Action Anticipation with Goal Consistency

arXiv 2306.15045 ↗First posted 26 Jun 2023cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

In this paper, we address the problem of short-term action anticipation, i.e., we want to predict an upcoming action one second before it happens. We propose to harness high-level intent information to anticipate actions that will take place in the future. To this end, we incorporate an additional goal prediction branch into our model and propose a consistency loss function that encourages the anticipated actions to conform to the high-level goal pursued in the video. In our experiments, we show the effectiveness of the proposed approach and demonstrate that our method achieves state-of-the-art results on two large-scale datasets: Assembly101 and COIN.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 18 of its 26 references that are in the map. First posted on arXiv 26 Jun 2023.

Builds on

18 of 26 references.

References · 18

  1. 2017Attention Is All You Needcited by 59,932
  2. 2017Non-local Neural Networkscited by 2,290
  3. 2019COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysiscited by 316
  4. 2022Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activitiescited by 284
  5. 2020The EPIC-KITCHENS Dataset: Collection, Challenges and Baselinescited by 221
  6. 2021Anticipative Video Transformercited by 197
  7. 2022MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognitioncited by 189
  8. 2020Rolling-Unrolling LSTMs for Action Anticipation from First-Person Videocited by 119
  9. 2018When will you do what? - Anticipating Temporal Occurrences of Activitiescited by 106
  10. 2017RED: Reinforced Encoder-Decoder Networks for Action Anticipationcited by 77
  11. 2022Real-time Online Video Detection with Temporal Smoothing Transformerscited by 58
  12. 2022Future Transformer for Long-term Action Anticipationcited by 57
6 more
  1. 2021Forecasting Action through Contact Representations from First Person Videocited by 46
  2. 2015Recurrent Neural Networks for Driver Activity Anticipation via Sensory-Fusion Architecturecited by 42
  3. 2022Intention-Conditioned Long-Term Human Egocentric Action Forecastingcited by 35
  4. 2022Rethinking Learning Approaches for Long-Term Action Anticipationcited by 29
  5. 2021Multi-Modal Temporal Convolutional Network for Anticipating Actions in Egocentric Videoscited by 23
  6. 2022Self-supervised Learning for Unintentional Action Predictioncited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 5; 2025: 4; 2026: 1.

12 papers.

  1. 2023An Outlook into the Future of Egocentric Visioncited by 84
  2. 2025Memory-efficient Streaming VideoLLMs for Real-time Procedural Video Understandingcited by 18
  3. 2023A Survey on Deep Learning Techniques for Action Anticipationcited by 11
  4. 2024Human Action Anticipation: A Surveycited by 8
  5. 2024Gated Temporal Diffusion for Stochastic Long-Term Dense Anticipationcited by 6
  6. 2024Enhancing Action Recognition by Leveraging the Hierarchical Structure of Actions and Textual Contextcited by 4
  7. 2025MANTA: Diffusion Mamba for Efficient and Effective Stochastic Long-Term Dense Anticipationcited by 3
  8. 2025Action Anticipation at a Glimpse: To What Extent Can Multimodal Cues Replace Video?cited by 3
  9. 2024Learning to Visually Connect Actions and their Effectscited by 2
  10. 2026Understanding Multimodal Complementarity for Single-Frame Action Anticipationcited by 2
  11. 2025MixANT: Observation-dependent Memory Propagation for Stochastic Dense Action Anticipationcited by 1
  12. 2024Anticipation through Head Pose Estimation: a preliminary studycited by 0