paper-with-me

Papers

Semantically Guided Representation Learning For Action Anticipation

2024-07-02 · Anxhelo Diko, Danilo Avola, Bardh Prenkaj, Federico Fontana, Luigi Cinque

Action anticipation is the task of forecasting future activity from a partially observed sequence of events. However, this task is exposed to intrinsic future uncertainty and the difficulty of reasoning upon interconnected actions. Unlike previous works that focus on extrapolating better visual and temporal information, we concentrate on learning action representations that are aware of their semantic interconnectivity based on prototypical action patterns and contextual co-occurrences. To this end, we propose the novel Semantically Guided Representation Learning (S-GEAR) framework. S-GEAR learns visual action prototypes and leverages language models to structure their relationship, inducing semanticity. To gather insights on S-GEAR's effectiveness, we test it on four action anticipation benchmarks, obtaining improved results compared to previous works: +3.5, +2.7, and +3.5 absolute points on Top-1 Accuracy on Epic-Kitchen 55, EGTEA Gaze+ and 50 Salads, respectively, and +0.8 on Top-5 Recall on Epic-Kitchens 100. We further observe that S-GEAR effectively transfers the geometric associations between actions from language to visual prototypes. Finally, S-GEAR opens new research frontiers in anticipation tasks by demonstrating the intricate impact of action semantic interconnectivity.

📄 PDF Abstract BibTeX arXiv:2407.02309

Code (1)

ADiko1997/S-GEAR 공식 구현 pytorch

Tasks

Action AnticipationRepresentation Learning

Methods 이 논문이 사용한 방법론

AWARE We propose to theoretically and empirically examine the effect of incorporating weighting schemes into walk-aggregating GNNs. To this end, we propose a simple, interpretable, and…
Focus 설명 없음

Similar Papers 제목 키워드 기반

Intention-Guided Cognitive Reasoning for Egocentric Long-Term Action Anticipation

2025-08-03 · Qiaohui Chu, Haoyu Zhang, Meng Liu, Yisen Feng 외 arxiv

Long-term action anticipation from egocentric video is critical for applications such as human-computer interaction and assistive technologies, where anticipating user intent enables proactive and context-aware AI assist…

Reinforcement LearningAction Anticipation

Understanding Multimodal Complementarity for Single-Frame Action Anticipation

2026-01-29 · Manuel Benavent-Lledo, Konstantinos Bacharidis, Konstantinos Papoutsakis, Antonis Argyros 외 arxiv

Human action anticipation is commonly treated as a video understanding problem, implicitly assuming that dense temporal information is required to reason about future actions. In this work, we challenge this assumption b…

Action Anticipation

Knowledge-Guided Short-Context Action Anticipation in Human-Centric Videos

2023-09-12 · Sarthak Bhagat, Simon Stepputtis, Joseph Campbell, Katia Sycara

This work focuses on anticipating long-term human actions, particularly using short video segments, which can speed up editing workflows through improved suggestions while fostering creativity by suggesting narratives. T…

Action AnticipationLong Term Action Anticipation

Bidirectional Action Sequence Learning for Long-term Action Anticipation with Large Language Models

2025-08-01 · Yuji Sato, Yasunori Ishii, Takayoshi Yamashita arxiv

Video-based long-term action anticipation is crucial for early risk detection in areas such as automated driving and robotics. Conventional approaches extract features from past actions using encoders and predict future …

Action Anticipation

Forecasting Action through Contact Representations from First Person Video

2021-02-01 · Eadom Dessalene, Chinmaya Devaraj, Michael Maynord, Cornelia Fermuller 외

Human actions involving hand manipulations are structured according to the making and breaking of hand-object contact, and human visual understanding of action is reliant on anticipation of contact as is demonstrated by …

Action AnticipationObject