Social Scene Understanding: End-to-End Multi-Person Action Localization and Collective Activity Recognition
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)(2016)
摘要
We present a unified framework for understanding human social behaviors in raw image sequences. Our model jointly detects multiple individuals, infers their social actions, and estimates the collective actions with a single feed-forward pass through a neural network. We propose a single architecture that does not rely on external detection algorithms but rather is trained end-to-end to generate dense proposal maps that are refined via a novel inference scheme. The temporal consistency is handled via a person-level matching Recurrent Neural Network. The complete model takes as input a sequence of frames and outputs detections along with the estimates of individual actions and collective activities. We demonstrate state-of-the-art performance of our algorithm on multiple publicly available benchmarks.
更多查看译文
关键词
social scene understanding,multiperson action localization,collective activity recognition,unified framework,human social behaviors,raw image sequences,multiple individuals,social actions,collective actions,single feed-forward pass,external detection algorithms,trained end-to-end,dense proposal maps,temporal consistency,complete model,frames,individual actions,collective activities,multiple publicly available benchmarks,inference scheme,output detections,person-level matching recurrent neural network
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络