Action Genome: Actions as Composition of Spatio-temporal Scene Graphs
arXiv:1912.06992
Abstract
Action recognition has typically treated actions and activities as monolithic events that occur in videos. However, there is evidence from Cognitive Science and Neuroscience that people actively encode activities into consistent hierarchical part structures. However in Computer Vision, few explorations on representations encoding event partonomies have been made. Inspired by evidence that the prototypical unit of an event is an action-object interaction, we introduce Action Genome, a representation that decomposes actions into spatio-temporal scene graphs. Action Genome captures changes between objects and their pairwise relationships while an action occurs. It contains 10K videos with 0.4M objects and 1.7M visual relationships annotated. With Action Genome, we extend an existing action recognition model by incorporating scene graphs as spatio-temporal feature banks to achieve better performance on the Charades dataset. Next, by decomposing and learning the temporal changes in visual relationships that result in an action, we demonstrate the utility of a hierarchical event decomposition by enabling few-shot action recognition, achieving 42.7% mAP using as few as 10 examples. Finally, we benchmark existing scene graph models on the new task of spatio-temporal scene graph prediction.
References in corpus (11)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
- The Kinetics Human Action Video Dataset
- A Short Note on the Kinetics-700-2020 Human Action Dataset
- Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction
- Object Level Visual Reasoning in Videos
- Human Action Localization with Sparse Spatial Supervision
- A Better Baseline for AVA
- TARN: Temporal Attentive Relation Network for Few-Shot and Zero-Shot Action Recognition
- Graph R-CNN for Scene Graph Generation
- Learning Predicates as Functions to Enable Few-shot Scene Graph Prediction