PaStaNet: Toward Human Activity Knowledge Engine
Authors:
- 1 June 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 379-388
Abstract
Existing image-based activity understanding methods mainly adopt direct mapping, i.e. from image to activity concepts, which may encounter performance bottleneck since the huge gap. In light of this, we propose a new path: infer human part states first and then reason out the activities based on part-level semantics. Human Body Part States (PaSta) are fine-grained action semantic tokens, e.g. , which can compose the activities and help us step toward human activity knowledge engine. To fully utilize the power of PaSta, we build a large-scale knowledge base PaStaNet, which contains 7M+ PaSta annotations. And two corresponding models are proposed: first, we design a model named Activity2Vec to extract PaSta features, which aim to be general representations for various activities. Second, we use a PaSta-based Reasoning method to infer activities. Promoted by PaStaNet, our method achieves significant improvements, e.g. 6.4 and 13.9 mAP on full and one-shot sets of HICO in supervised learning, and 3.2 and 4.2 mAP on V-COCO and images-based AVA in transfer learning. Code and data are available at http://hake-mvig.cn/.Keywords
All Related Versions
This publication has 40 references indexed in Scilit:
- Actions and Attributes from Wholes and Parts2015
- Show and tell: A neural image caption generator2015
- Human Action Recognition by Representing 3D Skeletons as Points in a Lie Group2014
- Glove: Global Vectors for Word Representation2014
- Towards Understanding Action Recognition2013
- Recognising Human-Object Interaction via Exemplar Based Modelling2013
- Human action recognition by learning bases of action attributes and parts2011
- Action recognition from a distributed representation of pose and appearance2011
- Long Short-Term MemoryNeural Computation, 1997
- WordNetCommunications of the ACM, 1995