DeepAI AI Chat
Log In Sign Up

Towards Universal Representation for Unseen Action Recognition

by   Yi Zhu, et al.

Unseen Action Recognition (UAR) aims to recognise novel action categories without training examples. While previous methods focus on inner-dataset seen/unseen splits, this paper proposes a pipeline using a large-scale training source to achieve a Universal Representation (UR) that can generalise to a more realistic Cross-Dataset UAR (CD-UAR) scenario. We first address UAR as a Generalised Multiple-Instance Learning (GMIL) problem and discover 'building-blocks' from the large-scale ActivityNet dataset using distribution kernels. Essential visual and semantic components are preserved in a shared space to achieve the UR that can efficiently generalise to new datasets. Predicted UR exemplars can be improved by a simple semantic adaptation, and then an unseen action can be directly recognised using UR during the test. Without further training, extensive experiments manifest significant improvements over the UCF101 and HMDB51 benchmarks.


Universal Prototype Transport for Zero-Shot Action Recognition and Localization

This work addresses the problem of recognizing action categories in vide...

Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximization

Zero-shot skeleton-based action recognition aims to recognize actions of...

Learning Using Privileged Information for Zero-Shot Action Recognition

Zero-Shot Action Recognition (ZSAR) aims to recognize video actions that...

SAFCAR: Structured Attention Fusion for Compositional Action Recognition

We present a general framework for compositional action recognition – i....

ODN: Opening the Deep Network for Open-set Action Recognition

In recent years, the performance of action recognition has been signific...

Cross-Domain First Person Audio-Visual Action Recognition through Relative Norm Alignment

First person action recognition is an increasingly researched topic beca...