Dual-AI: Dual-path Actor Interaction Learning for Group Activity Recognition
Authors:
- 1 June 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2980-2989
Abstract
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 difficult to model complex group activities from a single view of spatial-temporal actor evolution. To tackle this problem, we propose a distinct Dual-path Actor Interaction (Dual-AI) framework, which flexibly arranges spatial and temporal transformers in two complementary orders, enhancing actor relations by integrating merits from different spatio-temporal paths. Moreover, we introduce a novel Multi-scale Actor Contrastive Loss (MAC-Loss) between two interactive paths of Dual-AI. Via self-supervised actor consistency in both frame and video levels, MAC-Loss can effectively distinguish individual actor representations to reduce action confusion among different actors. Consequently, our Dual-AI can boost group activity recognition by fusing such discriminative features of different actors. To evaluate the proposed approach, we conduct extensive experiments on the widely used benchmarks, including Volleyball [21], Collective Activity [II], and NBA datasets [49]. The proposed Dual-AI achieves state-of-the-art performance on all these datasets. It is worth noting the proposed Dual-AI with 50% training data outperforms a number of recent approaches with 100% training data. This confirms the generalization power of Dual-AI for group activity recognition, even under the challenging scenarios of limited supervision.Keywords
All Related Versions
This publication has 30 references indexed in Scilit:
- Mask R-CNN2017
- Social Scene Understanding: End-to-End Multi-person Action Localization and Collective Activity Recognition2017
- CERN: Confidence-Energy Recurrent Network for Group Activity Recognition2017
- Recurrent Modeling of Interaction Context for Collective Activity Recognition2017
- Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset2017
- Structure Inference Machines: Recurrent Neural Networks for Analyzing Relations in Group Activity Recognition2016
- Rethinking the Inception Architecture for Computer Vision2016
- Sum Product Networks for Activity RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Bilinear Programming for Human Activity Recognition with Unknown MRF Graphs2013
- Discriminative Latent Models for Recognizing Contextual Group ActivitiesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011