All About Knowledge Graphs for Actions

28 Aug 2020  ·  Pallabi Ghosh, Nirat Saini, Larry S. Davis, Abhinav Shrivastava ·

Current action recognition systems require large amounts of training data for recognizing an action. Recent works have explored the paradigm of zero-shot and few-shot learning to learn classifiers for unseen categories or categories with few labels. Following similar paradigms in object recognition, these approaches utilize external sources of knowledge (eg. knowledge graphs from language domains). However, unlike objects, it is unclear what is the best knowledge representation for actions. In this paper, we intend to gain a better understanding of knowledge graphs (KGs) that can be utilized for zero-shot and few-shot action recognition. In particular, we study three different construction mechanisms for KGs: action embeddings, action-object embeddings, visual embeddings. We present extensive analysis of the impact of different KGs in different experimental setups. Finally, to enable a systematic study of zero-shot and few-shot approaches, we propose an improved evaluation paradigm based on UCF101, HMDB51, and Charades datasets for knowledge transfer from models trained on Kinetics.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Zero-Shot Action Recognition Kinetics GCN Top-1 Accuracy 22.3 # 19
Top-5 Accuracy 49.7 # 13

Methods


No methods listed for this paper. Add relevant methods here