Action Anticipation

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

8 leaderboard tables shown for this task, 8 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

11 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 49 papers with code (110 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Rescaling Egocentric Vision
  23 Jun 2020 7 repositories listed Syntology ran 3 of 18 samples · 15 unverified
  This paper introduces the pipeline to extend the largest dataset in egocentric vision, EPIC-KITCHENS.
• Temporal Aggregate Representations for Long-Range Video Understanding
  1 Jun 2020 2 repositories listed
  Future prediction, especially in long-range videos, requires reasoning from current and past observations.
• Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video
  4 May 2020 2 repositories listed
  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.
• HalluciNet-ing Spatiotemporal Representations Using a 2D-CNN
  10 Dec 2019 2 repositories listed
  The hallucination task is treated as an auxiliary task, which can be used with any other action related task in a multitask learning setting.
• What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attention
  22 May 2019 2 repositories listed
  Our method is ranked first in the public leaderboard of the EPIC-Kitchens egocentric action anticipation challenge 2019.
• Scaling Egocentric Vision: The EPIC-KITCHENS Dataset
  8 Apr 2018 2 repositories listed
  First-person vision is gaining interest as it offers a unique viewpoint on people's interaction with objects, their attention, and even intention.
• V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
  11 Jun 2025 1 repository listed Syntology ran 0 of 8 samples · 8 unverified · 8 pointer-only (licence)
  Finally, we show how self-supervised learning can be applied to robotic planning tasks by post-training a latent action-conditioned world model, V-JEPA 2-AC, using less than 62 hours of unlabeled robot videos from the…
• Hierarchical and Multimodal Data for Daily Activity Understanding
  24 Apr 2025 1 repository listed
  To capture the complexity in human activities, DARai is annotated at three levels of hierarchy: (i) high-level activities (L1) that are independent tasks, (ii) lower-level actions (L2) that are patterns shared between…
• Multimodal Large Models Are Effective Action Anticipators
  1 Jan 2025 1 repository listed
  Extensive experiments on benchmark datasets demonstrate the superiority of the proposed ActionLLM framework, encouraging a promising direction to explore LLMs in the context of action anticipation.
• MANTA: Diffusion Mamba for Efficient and Effective Stochastic Long-Term Dense Action Anticipation
  1 Jan 2025 1 repository listed
  Long-term dense action anticipation is very challenging since it requires predicting actions and their durations several minutes into the future based on provided video observations.
• Mamba Fusion: Learning Actions Through Questioning
  17 Sep 2024 1 repository listed
  Video Language Models (VLMs) are crucial for generalizing across diverse tasks and using language cues to enhance learning.
• From Recognition to Prediction: Leveraging Sequence Reasoning for Action Anticipation
  5 Aug 2024 1 repository listed
  ARR decomposes the action anticipation task into action recognition and sequence reasoning tasks, and effectively learns the statistical relationship between actions by next action prediction (NAP).
• QuIIL at T3 challenge: Towards Automation in Life-Saving Intervention Procedures from First-Person View
  18 Jul 2024 1 repository listed
  In this paper, we present our solutions for a spectrum of automation tasks in life-saving intervention procedures within the Trauma THOMPSON (T3) Challenge, encompassing action recognition, action anticipation, and…
• Gated Temporal Diffusion for Stochastic Long-Term Dense Anticipation
  16 Jul 2024 1 repository listed
  As generator, we introduce a Gated Anticipation Network (GTAN) to model both observed and unobserved frames of a video in a mutual representation.
• Semantically Guided Representation Learning For Action Anticipation
  2 Jul 2024 1 repository listed Syntology ran 6 of 8 samples · 2 unverified
  Action anticipation is the task of forecasting future activity from a partially observed sequence of events.
• EgoVideo: Exploring Egocentric Foundation Model and Downstream Adaptation
  26 Jun 2024 1 repository listed Syntology ran 11 of 15 samples · 4 unverified · 15 pointer-only (licence)
  In this report, we present our solutions to the EgoVis Challenges in CVPR 2024, including five tracks in the Ego4D challenge and three tracks in the EPIC-Kitchens challenge.
• EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World
  24 Mar 2024 1 repository listed Syntology ran 7 of 8 samples · 1 unverified
  Along with the videos we record high-quality gaze data and provide detailed multimodal annotations, formulating a playground for modeling the human ability to bridge asynchronous procedural actions from different…
• Action Scene Graphs for Long-Form Understanding of Egocentric Videos
  6 Dec 2023 1 repository listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  We present Egocentric Action Scene Graphs (EASGs), a new representation for long-form understanding of egocentric videos.
• Object-centric Video Representation for Long-term Action Anticipation
  31 Oct 2023 1 repository listed Syntology ran 1 of 5 samples · 4 unverified
  To recognize and predict human-object interactions, we use a Transformer-based neural architecture which allows the "retrieval" of relevant objects for action anticipation at various time scales.
• AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?
  31 Jul 2023 1 repository listed Syntology ran 2 of 2 samples · 0 unverified
  We propose to formulate the LTA task from two perspectives: a bottom-up approach that predicts the next actions autoregressively by modeling temporal dynamics; and a top-down approach that infers the goal of the actor…
• Technical Report for Ego4D Long Term Action Anticipation Challenge 2023
  4 Jul 2023 1 repository listed Syntology ran 1 of 2 samples · 1 unverified
  In this report, we describe the technical details of our approach for the Ego4D Long-Term Action Anticipation Challenge 2023.
• Palm: Predicting Actions through Language Models @ Ego4D Long-Term Action Anticipation Challenge 2023
  28 Jun 2023 1 repository listed Syntology ran 1 of 6 samples · 5 unverified
  We present Palm, a solution to the Long-Term Action Anticipation (LTA) task utilizing vision-language and large language models.
• Action Anticipation with Goal Consistency
  26 Jun 2023 1 repository listed
  In this paper, we address the problem of short-term action anticipation, i.
• Enhancing Next Active Object-based Egocentric Action Anticipation with Guided Attention
  22 May 2023 1 repository listed
  To this end, we propose a novel approach that applies a guided attention mechanism between the objects, and the spatiotemporal features extracted from video clips, enhancing the motion and contextual information, and…
• Fine-grained Affordance Annotation for Egocentric Hand-Object Interaction Videos
  7 Feb 2023 1 repository listed
  Object affordance is an important concept in hand-object interaction, providing information on action possibilities based on human motor capacity and objects' physical property thus benefiting tasks such as action…
• Interaction Region Visual Transformer for Egocentric Action Anticipation
  25 Nov 2022 1 repository listed
  On the EK100 evaluation server, InAViT is the top-performing method on the public leaderboard (at the time of submission) where it outperforms the second-best model by 3.
• Anticipative Feature Fusion Transformer for Multi-Modal Action Anticipation
  23 Oct 2022 1 repository listed
  Although human action anticipation is a task which is inherently multi-modal, state-of-the-art methods on well known action anticipation datasets leverage this data by applying ensemble methods and averaging scores of…
• Rethinking Learning Approaches for Long-Term Action Anticipation
  20 Oct 2022 1 repository listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  Action anticipation involves predicting future actions having observed the initial portion of a video.
• Text-Derived Knowledge Helps Vision: A Simple Cross-modal Distillation for Video-based Action Anticipation
  12 Oct 2022 1 repository listed
  Anticipating future actions in a video is useful for many autonomous and assistive technologies.
• Learning State-Aware Visual Representations from Audible Interactions
  27 Sep 2022 1 repository listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  However, learning representations from videos can be challenging.

Syntology lines on 12 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.