mlsanityData to 14 Oct 2026

StillFast: An End-to-End Approach for Short-Term Object Interaction Anticipation

arXiv 2304.03959 ↗First posted 8 Apr 2023cs.CVcited by 23

Not on the map. Why?

Abstract (arXiv)

Anticipation problem has been studied considering different aspects such as predicting humans' locations, predicting hands and objects trajectories, and forecasting actions and human-object interactions. In this paper, we studied the short-term object interaction anticipation problem from the egocentric point of view, proposing a new end-to-end architecture named StillFast. Our approach simultaneously processes a still image and a video detecting and localizing next-active objects, predicting the verb which describes the future interaction and determining when the interaction will start. Experiments on the large-scale egocentric dataset EGO4D show that our method outperformed state-of-the-art approaches on the considered task. Our method is ranked first in the public leaderboard of the EGO4D short term object interaction anticipation challenge 2022. Please see the project web page for code and additional details: https://iplab.dmi.unict.it/stillfast/.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Builds on 29 of its 41 references that are in the map. First posted on arXiv 8 Apr 2023.

Builds on

29 of 41 references.

References · 29

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  3. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  4. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
  5. 2015Fast R-CNNcited by 2,933
  6. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,162
  7. 2018SlowFast Networks for Video Recognitioncited by 1,867
  8. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,556
  9. 2022VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Trainingcited by 1,322
  10. 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,319
  11. 2018Scaling Egocentric Vision: The EPIC-KITCHENS Datasetcited by 795
  12. 2020X3D: Expanding Architectures for Efficient Video Recognitioncited by 637
17 more
  1. 2022Omnivore: A Single Model for Many Visual Modalitiescited by 215
  2. 2020From Goals, Waypoints & Paths To Long Term Human Trajectory Forecastingcited by 167
  3. 2020Rolling-Unrolling LSTMs for Action Anticipation from First-Person Videocited by 120
  4. 2019What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attentioncited by 105
  5. 2017RED: Reinforced Encoder-Decoder Networks for Action Anticipationcited by 78
  6. 2022Future Transformer for Long-term Action Anticipationcited by 58
  7. 2019Next-Active-Object prediction from Egocentric Videoscited by 55
  8. 2022InternVideo-Ego4D: A Pack of Champion Solutions to Ego4D Challengescited by 48
  9. 2021Forecasting Action through Contact Representations from First Person Videocited by 46
  10. 2022Anticipative Feature Fusion Transformer for Multi-Modal Action Anticipationcited by 41
  11. 2022Graph-based Spatial Transformer with Memory Replay for Multi-future Pedestrian Trajectory Predictioncited by 36
  12. 2022MECCANO: A Multimodal Egocentric Dataset for Humans Behavior Understanding in the Industrial-like Domaincited by 36
  13. 2022How many Observations are Enough? Knowledge Distillation for Trajectory Forecastingcited by 35
  14. 2019Disentangling Human Dynamics for Pedestrian Locomotion Forecasting with Noisy Supervisioncited by 27
  15. 2021SlowFast Rolling-Unrolling LSTMs for Action Anticipation in Egocentric Videoscited by 20
  16. 2022Generative Adversarial Network for Future Hand Segmentation from Egocentric Videocited by 16
  17. 2017Forecasting Hands and Objects in Future Framescited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 7; 2025: 3; 2026: 8.

23 papers.

Sort:

By area:

  1. 2026V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learningcited by 117
  2. 2023An Outlook into the Future of Egocentric Visioncited by 84
  3. 2024EgoVideo: Exploring Egocentric Foundation Model and Downstream Adaptationcited by 44
  4. 2023PALM: Predicting Actions through Language Modelscited by 29
  5. 2023LEGO: Learning EGOcentric Action Frame Generation via Visual Instruction Tuningcited by 28
  6. 2025Exo2Ego: Exocentric Knowledge Guided MLLM for Egocentric Video Understandingcited by 25
  7. 2025An Empirical Study of Autoregressive Pre-training from Videoscited by 21
  8. 2024MADiff: Motion-Aware Mamba Diffusion Models for Hand Trajectory Prediction on Egocentric Videoscited by 18
  9. 2024AFF-ttention! Affordances and Attention models for Short-Term Object Interaction Anticipationcited by 14
  10. 2026EgoForge: Goal-Directed Egocentric World Simulatorcited by 12
  11. 2023ENIGMA-51: Towards a Fine-Grained Understanding of Human-Object Interactions in Industrial Scenarioscited by 11
  12. 2024Grounding 3D Scene Affordance From Egocentric Interactionscited by 11
11 more
  1. 2025Ego-centric Predictive Model Conditioned on Hand Trajectoriescited by 4
  2. 2024Anticipating Object State Changes in Long Procedural Videoscited by 2
  3. 2026Leveraging Gaze and Set-of-Mark in VLLMs for Human-Object Interaction Anticipation from Egocentric Videoscited by 2
  4. 2026VISTA: Technical Report for the Ego4D Short-Term Object Interaction Anticipation at EgoVis 2026cited by 2
  5. 2024Short-term Object Interaction Anticipation with Disentangled Object Detection @ Ego4D Short Term Object Interaction Anticipation Challengecited by 1
  6. 2026Integrating Affordances and Attention models for Short-Term Object Interaction Anticipationcited by 1
  7. 2026FROST-STA: Frozen Dense Features for the Ego4D Short-Term Object Interaction Anticipationcited by 1
  8. 2026FactCheck: Feasibility-aware Long-term Action Anticipation with Multi-agent Collaborationcited by 1
  9. 2026Iterative Erasure Count Is Not an Affine-Invariant Concept Dimensioncited by 1
  10. 2023Guided Attention for Next Active Object @ EGO4D STA Challengecited by 0
  11. 2024ZARRIO @ Ego4D Short Term Object Interaction Anticipation Challenge: Leveraging Affordances and Attention-based models for STAcited by 0