Zero-Shot Underwater Gesture Recognition

TL;DR

This paper introduces a zero-shot learning framework for underwater gesture recognition, enabling the identification of unseen gestures by leveraging a transformer and generative adversarial network to synthesize features, thus improving recognition accuracy.

Contribution

The work proposes a novel two-stage zero-shot learning framework combining transformers and GANs for underwater gesture recognition, addressing the challenge of recognizing unseen gestures.

Findings

Outperforms existing zero-shot techniques on the CADDY dataset.

Introduces new seen-unseen splits for gesture classes.

Provides insights into the effectiveness of feature synthesis for unseen classes.

Abstract

Hand gesture recognition allows humans to interact with machines non-verbally, which has a huge application in underwater exploration using autonomous underwater vehicles. Recently, a new gesture-based language called CADDIAN has been devised for divers, and supervised learning methods have been applied to recognize the gestures with high accuracy. However, such methods fail when they encounter unseen gestures in real time. In this work, we advocate the need for zero-shot underwater gesture recognition (ZSUGR), where the objective is to train a model with visual samples of gestures from a few ``seen'' classes only and transfer the gained knowledge at test time to recognize semantically-similar unseen gesture classes as well. After discussing the problem and dataset-specific challenges, we propose new seen-unseen splits for gesture classes in CADDY dataset. Then, we present a two-stage framework, where a novel transformer learns strong visual gesture cues and feeds them to a conditional generative adversarial network that learns to mimic feature distribution. We use the trained generator as a feature synthesizer for unseen classes, enabling zero-shot learning. Extensive experiments demonstrate that our method outperforms the existing zero-shot techniques. We conclude by providing useful insights into our framework and suggesting directions for future research.