中文
相关论文

相关论文: Gaze-Guided Graph Neural Network for Action Antici…

200 篇论文

Computer-use agents can operate computers and automate laborious tasks, but despite recent rapid progress, they still lag behind human users, especially when tasks require domain-specific procedural knowledge about particular applications,…

计算机视觉与模式识别 · 计算机科学 2025-11-07 Yujian Liu , Ze Wang , Hao Chen , Ximeng Sun , Xiaodong Yu , Jialian Wu , Jiang Liu , Emad Barsoum , Zicheng Liu , Shiyu Chang

Short-term action anticipation (STA) in first-person videos is a challenging task that involves understanding the next active object interactions and predicting future actions. Existing action anticipation methods have primarily focused on…

计算机视觉与模式识别 · 计算机科学 2023-06-26 Sanket Thakur , Cigdem Beyan , Pietro Morerio , Vittorio Murino , Alessio Del Bue

Gaze following and social gaze prediction are fundamental tasks providing insights into human communication behaviors, intent, and social interactions. Most previous approaches addressed these tasks separately, either by designing highly…

计算机视觉与模式识别 · 计算机科学 2024-03-18 Anshul Gupta , Samy Tafasca , Arya Farkhondeh , Pierre Vuillecard , Jean-Marc Odobez

Nuanced understanding and the generation of detailed descriptive content for (bimanual) manipulation actions in videos is important for disciplines such as robotics, human-computer interaction, and video content analysis. This study…

计算机视觉与模式识别 · 计算机科学 2023-10-03 Fatemeh Ziaeetabar , Reza Safabakhsh , Saeedeh Momtazi , Minija Tamosiunaite , Florentin Wörgötter

Learning actions from human demonstration is an emerging trend for designing intelligent robotic systems, which can be referred as video to command. The performance of such approach highly relies on the quality of video captioning. However,…

计算机视觉与模式识别 · 计算机科学 2019-09-11 Shuo Yang , Wei Zhang , Weizhi Lu , Hesheng Wang , Yibin Li

Action and intention recognition of pedestrians in urban settings are challenging problems for Advanced Driver Assistance Systems as well as future autonomous vehicles to maintain smooth and safe traffic. This work investigates a number of…

计算机视觉与模式识别 · 计算机科学 2020-10-19 Dimitrios Varytimidis , Fernando Alonso-Fernandez , Boris Duran , Cristofer Englund

Gaze following estimates gaze targets of in-scene person by understanding human behavior and scene information. Existing methods usually analyze scene images for gaze following. However, compared with visual images, audio also provides…

计算机视觉与模式识别 · 计算机科学 2024-01-17 Yuqi Hou , Zhongqun Zhang , Nora Horanyi , Jaewon Moon , Yihua Cheng , Hyung Jin Chang

Fluent and safe interactions of humans and robots require both partners to anticipate the others' actions. A common approach to human intention inference is to model specific trajectories towards known goals with supervised classifiers.…

机器人学 · 计算机科学 2017-02-28 Judith Bütepage , Hedvig Kjellström , Danica Kragic

Student's academic performance prediction empowers educational technologies including academic trajectory and degree planning, course recommender systems, early warning and advising systems. Given a student's past data (such as grades in…

机器学习 · 计算机科学 2020-01-06 Qian Hu , Huzefa Rangwala

Effective collaboration between humans and AIs hinges on transparent communication and alignment of mental models. However, explicit, verbal communication is not always feasible. Under such circumstances, human-human teams often depend on…

Approaches for teaching learning agents via human demonstrations have been widely studied and successfully applied to multiple domains. However, the majority of imitation learning work utilizes only behavioral information from the…

Unsupervised segmentation of action segments in egocentric videos is a desirable feature in tasks such as activity recognition and content-based video retrieval. Reducing the search space into a finite set of action segments facilitates a…

计算机视觉与模式识别 · 计算机科学 2021-06-24 I. Hipiny , H. Ujir , J. L. Minoi , S. F. Samson Juan , M. A. Khairuddin , M. S. Sunar

Despite the notable progress made in action recognition tasks, not much work has been done in action recognition specifically for human-robot interaction. In this paper, we deeply explore the characteristics of the action recognition task…

计算机视觉与模式识别 · 计算机科学 2020-07-03 Ziyang Song , Ziyi Yin , Zejian Yuan , Chong Zhang , Wanchao Chi , Yonggen Ling , Shenghao Zhang

A multi-modal framework to generate user intention distributions when operating a mobile vehicle is proposed in this work. The model learns from past observed trajectories and leverages traversability information derived from the visual…

机器人学 · 计算机科学 2022-03-17 Kavindie Katuwandeniya , Stefan H. Kiss , Lei Shi , Jaime Valls Miro

This paper aims to tackle the interactive behavior prediction task, and proposes a novel Conditional Goal-oriented Trajectory Prediction (CGTP) framework to jointly generate scene-compliant trajectories of two interacting agents. Our CGTP…

机器人学 · 计算机科学 2022-10-28 Ding Li , Qichao Zhang , Shuai Lu , Yifeng Pan , Dongbin Zhao

Distinguishing if an action is performed as intended or if an intended action fails is an important skill that not only humans have, but that is also important for intelligent systems that operate in human environments. Recognizing if an…

计算机视觉与模式识别 · 计算机科学 2022-09-27 Olga Zatsarynna , Yazan Abu Farha , Juergen Gall

A core challenge for an agent learning to interact with the world is to predict how its actions affect objects in its environment. Many existing methods for learning the dynamics of physical interactions require labeled object information.…

机器学习 · 计算机科学 2016-10-19 Chelsea Finn , Ian Goodfellow , Sergey Levine

Eye gaze, encompassing fixations and saccades, provides critical insights into human intentions and future actions. This study introduces a gaze-regularized framework that enhances Vision Language Models (VLMs) for egocentric behavior…

计算机视觉与模式识别 · 计算机科学 2026-03-25 Anupam Pani , Yanchao Yang

Robot understanding of human intentions is essential for fluid human-robot interaction. Intentions, however, cannot be directly observed and must be inferred from behaviors. We learn a model of adaptive human behavior conditioned on the…

机器人学 · 计算机科学 2019-01-23 Min Chen , David Hsu , Wee Sun Lee

Anticipating actions before they occur is a core challenge in action understanding research. While conventional methods rely on extracting and aggregating temporal information from videos, as humans we can often predict upcoming actions by…