Learning Actor Relation Graphs for Group Activity Recognition
Modeling relation between actors is important for recognizing group activity in a multi-person scene. This paper aims at learning discriminative relation between actors efficiently using deep models. To this end, we propose to build a flexible and efficient Actor Relation Graph (ARG) to simultaneously capture the appearance and position relation between actors. Thanks to the Graph Convolutional Network, the connections in ARG could be automatically learned from group activity videos in an end-to-end manner, and the inference on ARG could be efficiently performed with standard matrix operations. Furthermore, in practice, we come up with two variants to sparsify ARG for more effective modeling in videos: spatially localized ARG and temporal randomized ARG. We perform extensive experiments on two standard group activity recognition datasets: the Volleyball dataset and the Collective Activity dataset, where state-of-the-art performance is achieved on both datasets. We also visualize the learned actor graphs and relation features, which demonstrate that the proposed ARG is able to capture the discriminative relation information for group activity recognition.
Code (2)
Tasks
Action RecognitionActivity RecognitionGroup Activity RecognitionRelationSimilar Papers 제목 키워드 기반
Computer Vision based group activity detection and action spotting
Group activity detection in multi-person scenes is challenging due to complex human interactions, occlusions, and variations in appearance over time. This work presents a computer vision based framework for group activit…
Group Activity RecognitionRelational ReasoningGraph Neural NetworkActivity DetectionDual-AI: Dual-path Actor Interaction Learning for Group Activity Recognition
Learning spatial-temporal relation among multiple actors is crucial for group activity recognition. Different group activities often show the diversified interactions between actors in the video. Hence, it is often diffi…
Activity RecognitionGroup Activity RecognitionFlow-Assisted Motion Learning Network for Weakly-Supervised Group Activity Recognition
Weakly-Supervised Group Activity Recognition (WSGAR) aims to understand the activity performed together by a group of individuals with the video-level label and without actor-level labels. We propose Flow-Assisted Motion…
Activity RecognitionGroup Activity RecognitionOptical Flow EstimationRelationActor-Transformers for Group Activity Recognition
This paper strives to recognize individual actions and group activities from videos. While existing solutions for this challenging problem explicitly model spatial and temporal relationships based on location of individu…
Activity RecognitionGroup Activity RecognitionEmpowering Relational Network by Self-Attention Augmented Conditional Random Fields for Group Activity Recognition
This paper presents a novel relational network for group activity recognition. The core of our network is to augment the conditional random fields (CRF), amenable to learning inter-dependency of correlated observations, …
Activity RecognitionGroup Activity Recognition