Unsupervised Discriminative Embedding for Sub-Action Learning in Complex Activities

TL;DR

This paper introduces an unsupervised method for learning sub-actions in complex activities by mapping visual and temporal data into a latent space where sub-actions are discriminatively learned without explicit clustering.

Contribution

It proposes a novel end-to-end discriminative latent concept learning approach that jointly embeds visual and temporal features for unsupervised sub-action discovery.

Findings

Effective on three benchmark datasets

Outperforms existing unsupervised methods

Learns robust sub-action representations

Abstract

Action recognition and detection in the context of long untrimmed video sequences has seen an increased attention from the research community. However, annotation of complex activities is usually time consuming and challenging in practice. Therefore, recent works started to tackle the problem of unsupervised learning of sub-actions in complex activities. This paper proposes a novel approach for unsupervised sub-action learning in complex activities. The proposed method maps both visual and temporal representations to a latent space where the sub-actions are learnt discriminatively in an end-to-end fashion. To this end, we propose to learn sub-actions as latent concepts and a novel discriminative latent concept learning (DLCL) module aids in learning sub-actions. The proposed DLCL module lends on the idea of latent concepts to learn compact representations in the latent embedding space in an unsupervised way. The result is a set of latent vectors that can be interpreted as cluster centers in the embedding space. The latent space itself is formed by a joint visual and temporal embedding capturing the visual similarity and temporal ordering of the data. Our joint learning with discriminative latent concept module is novel which eliminates the need for explicit clustering. We validate our approach on three benchmark datasets and show that the proposed combination of visual-temporal embedding and discriminative latent concepts allow to learn robust action representations in an unsupervised setting.