HAKE: Human Activity Knowledge Engine
This addresses imbalanced data and action ambiguity in human activity understanding for AI systems, but it is incremental as it builds upon existing datasets and methods.
The authors tackled challenges in human activity understanding by building a large-scale Human Activity Knowledge Engine (HAKE) with over 7 million part state annotations, which improved Human-Object Interaction recognition by 7.2 mAP and one-shot subsets by 12.38 mAP.
Human activity understanding is crucial for building automatic intelligent system. With the help of deep learning, activity understanding has made huge progress recently. But some challenges such as imbalanced data distribution, action ambiguity, complex visual patterns still remain. To address these and promote the activity understanding, we build a large-scale Human Activity Knowledge Engine (HAKE) based on the human body part states. Upon existing activity datasets, we annotate the part states of all the active persons in all images, thus establish the relationship between instance activity and body part states. Furthermore, we propose a HAKE based part state recognition model with a knowledge extractor named Activity2Vec and a corresponding part state based reasoning network. With HAKE, our method can alleviate the learning difficulty brought by the long-tail data distribution, and bring in interpretability. Now our HAKE has more than 7 M+ part state annotations and is still under construction. We first validate our approach on a part of HAKE in this preliminary paper, where we show 7.2 mAP performance improvement on Human-Object Interaction recognition, and 12.38 mAP improvement on the one-shot subsets.