Existing 3D skeleton-based action recognition approaches reach impressive performance by encoding handcrafted features to image format and decoding CNNs. However, such methods are limited in two ways: a) the difficult handle challenging actions, b) they generally require complex CNN models improve accuracy, which usually occur heavy computational burden. To overcome these limitations, we introd...

Few-shot action recognition aims to recognize novel classes (query) using just a few samples (support). The majority of current approaches follow the metric learning paradigm, which learns compare similarity between videos. Recently, it has been observed that directly measuring this is not ideal since different instances may show distinctive temporal distribution, resulting in severe misalignme...

Training robust deep video representations has proven to be much more challenging than learning deep image representations and consequently hampered tasks like video action recognition. This is in part due to the enormous size of raw video streams, the associated amount of computation required, and the high temporal redundancy. The ‘true’ and interesting signal is often drowned in too much irre...

Automatic action recognition in video has a broad array of applications, from surveillance to interactive video games. Classic algorithms usually use handcrafted descriptors such as SIFT (see [5]) or HOG (see [3]) to compute feature vectors of videos, and have achieved promising results in the past (see [7]). More recently, Quoc Le and Will Zou at the Stanford AI lab have proved that ISA featur...

Human Action Recognition. Human action recognition has broad range of applications such as video search, sports analysis, human robotics interactions, and health care. Our work is organized in two directions: 1) detailed pixel-level ‘motion and pose’, focusing on close interactions among people; 2) action recognition focusing on goal oriented motion, simplified as ‘action = motion + intention’....