Reconstructing Humpty Dumpty: Multi-feature Graph Autoencoder for Open Set Action Recognition

TL;DR

This paper introduces 'Humpty Dumpty', a graph autoencoder that leverages reconstruction errors to identify unknown actions in open set recognition, outperforming existing methods on standard datasets.

Contribution

It presents a novel graph-based autoencoder model that captures relations among video clip elements for improved open set action recognition.

Findings

Achieves state-of-the-art results on HMDB-51 and UCF-101 datasets.

Effectively distinguishes known and unknown actions using reconstruction error.

Outperforms existing open set recognition methods.

Abstract

Most action recognition datasets and algorithms assume a closed world, where all test samples are instances of the known classes. In open set problems, test samples may be drawn from either known or unknown classes. Existing open set action recognition methods are typically based on extending closed set methods by adding post hoc analysis of classification scores or feature distances and do not capture the relations among all the video clip elements. Our approach uses the reconstruction error to determine the novelty of the video since unknown classes are harder to put back together and thus have a higher reconstruction error than videos from known classes. We refer to our solution to the open set action recognition problem as "Humpty Dumpty", due to its reconstruction abilities. Humpty Dumpty is a novel graph-based autoencoder that accounts for contextual and semantic relations among the clip pieces for improved reconstruction. A larger reconstruction error leads to an increased likelihood that the action can not be reconstructed, i.e., can not put Humpty Dumpty back together again, indicating that the action has never been seen before and is novel/unknown. Extensive experiments are performed on two publicly available action recognition datasets including HMDB-51 and UCF-101, showing the state-of-the-art performance for open set action recognition.