paper-with-me

Papers

Group Activity Recognition using Unreliable Tracked Pose

2024-01-06 · Haritha Thilakarathne, Aiden Nibali, Zhen He, Stuart Morgan

Group activity recognition in video is a complex task due to the need for a model to recognise the actions of all individuals in the video and their complex interactions. Recent studies propose that optimal performance is achieved by individually tracking each person and subsequently inputting the sequence of poses or cropped images/optical flow into a model. This helps the model to recognise what actions each person is performing before they are merged to arrive at the group action class. However, all previous models are highly reliant on high quality tracking and have only been evaluated using ground truth tracking information. In practice it is almost impossible to achieve highly reliable tracking information for all individuals in a group activity video. We introduce an innovative deep learning-based group activity recognition approach called Rendered Pose based Group Activity Recognition System (RePGARS) which is designed to be tolerant of unreliable tracking and pose information. Experimental results confirm that RePGARS outperforms all existing group activity recognition algorithms tested which do not use ground truth detection and tracking information.

📄 PDF Abstract BibTeX arXiv:2401.03262

Code (0)

등록된 구현이 없습니다.

Tasks

Activity RecognitionAllGroup Activity RecognitionOptical Flow Estimation

Similar Papers 제목 키워드 기반

Pose is all you need: The pose only group activity recognition system (POGARS)

2021-08-09 · Haritha Thilakarathne, Aiden Nibali, Zhen He, Stuart Morgan

We introduce a novel deep learning based group activity recognition approach called the Pose Only Group Activity Recognition System (POGARS), designed to use only tracked poses of people to predict the performed group ac…

Action ClassificationActivity PredictionActivity RecognitionAll+2

Two is a crowd: tracking relations in videos

2021-08-11 · Artem Moskalev, Ivan Sosnovik, Arnold Smeulders

Tracking multiple objects individually differs from tracking groups of related objects. When an object is a part of the group, its trajectory depends on the trajectories of the other group members. Most of the current st…

ObjectRelationVocal Bursts Valence Prediction

Group Activity Recognition Using Joint Learning of Individual Action Recognition and People Grouping

2021-07-17 · MVA 2021 7 · Chihiro Nakatani, Kohei Sendo, Norimichi Ukita

This paper proposes joint learning of individual action recognition and people grouping for improving group activity recognition. By sharing the information between two similar tasks (i.e., individual action recognition …

Action RecognitionActivity RecognitionGroup Activity Recognition

LSTA: Long Short-Term Attention for Egocentric Action Recognition

2018-11-26 · CVPR 2019 6 · Swathikiran Sudhakaran, Sergio Escalera, Oswald Lanz

Egocentric activity recognition is one of the most challenging tasks in video analysis. It requires a fine-grained discrimination of small objects and their manipulation. While some methods base on strong supervision and…

Action RecognitionActivity RecognitionEgocentric Activity RecognitionTemporal Action Localization

Group Activity Recognition in Computer Vision: A Comprehensive Review, Challenges, and Future Perspectives

2023-07-25 · Chuanchuan Wang, Ahmad Sufril Azlan Mohamed

Group activity recognition is a hot topic in computer vision. Recognizing activities through group relationships plays a vital role in group activity recognition. It holds practical implications in various scenarios, suc…

Activity RecognitionGroup Activity Recognition