PoTion: Pose MoTion Representation for Action Recognition

Most state-of-the-art methods for action recognition rely on a two-stream architecture that processes appearance and motion independently. In this paper, we claim that considering them jointly offers rich information for action recognition. We introduce a novel representation that gracefully encodes...

Full description

Saved in:
Bibliographic Details
Published in:2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 7024 - 7033
Main Authors: Choutas, Vasileios, Weinzaepfel, Philippe, Revaud, Jerome, Schmid, Cordelia
Format: Conference Proceeding
Language:English
Published: IEEE 01.06.2018
Subjects:
Computer architecture
Heating systems
Image color analysis
Joints
Optical imaging
Streaming media
ISSN:1063-6919
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Most state-of-the-art methods for action recognition rely on a two-stream architecture that processes appearance and motion independently. In this paper, we claim that considering them jointly offers rich information for action recognition. We introduce a novel representation that gracefully encodes the movement of some semantic keypoints. We use the human joints as these keypoints and term our Pose moTion representation PoTion. Specifically, we first run a state-of-the-art human pose estimator [4] and extract heatmaps for the human joints in each frame. We obtain our PoTion representation by temporally aggregating these probability maps. This is achieved by 'colorizing' each of them depending on the relative time of the frames in the video clip and summing them. This fixed-size representation for an entire video clip is suitable to classify actions using a shallow convolutional neural network. Our experimental evaluation shows that PoTion outperforms other state-of-the-art pose representations [6, 48]. Furthermore, it is complementary to standard appearance and motion streams. When combining PoTion with the recent two-stream I3D approach [5], we obtain state-of-the-art performance on the JHMDB, HMDB and UCF101 datasets.
ISSN:1063-6919
DOI:10.1109/CVPR.2018.00734