PaStaNet: Toward Human Activity Knowledge Engine
arXiv:2004.00945
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. <hand, hold, something>, 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/.
Accepted to CVPR 2020, supplementary materials included, code available: http://hake-mvig.cn/
References in corpus (7)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Semi-Supervised Classification with Graph Convolutional Networks
- Two-Stream Convolutional Networks for Action Recognition in Videos
- UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
- Visual Semantic Role Labeling
- R-CNNs for Pose Estimation and Action Detection
- Beyond Holistic Object Recognition: Enriching Image Understanding with Part States