A Fine-Grained Visual Attention Approach for Fingerspelling Recognition in the Wild

TL;DR

This paper introduces a Transformer-based fine-grained visual attention method leveraging optical flow for improved fingerspelling recognition in unconstrained, real-world videos, addressing challenges of gesture ambiguity and variability.

Contribution

It proposes a novel fine-grained attention mechanism using optical flow within a Transformer model for sequence prediction in wild datasets, outperforming existing methods.

Findings

Outperforms state-of-the-art approaches

Effectively captures fine-grained motion details

Handles real-world, unconstrained video data

Abstract

Fingerspelling in sign language has been the means of communicating technical terms and proper nouns when they do not have dedicated sign language gestures. Automatic recognition of fingerspelling can help resolve communication barriers when interacting with deaf people. The main challenges prevalent in fingerspelling recognition are the ambiguity in the gestures and strong articulation of the hands. The automatic recognition model should address high inter-class visual similarity and high intra-class variation in the gestures. Most of the existing research in fingerspelling recognition has focused on the dataset collected in a controlled environment. The recent collection of a large-scale annotated fingerspelling dataset in the wild, from social media and online platforms, captures the challenges in a real-world scenario. In this work, we propose a fine-grained visual attention mechanism using the Transformer model for the sequence-to-sequence prediction task in the wild dataset. The fine-grained attention is achieved by utilizing the change in motion of the video frames (optical flow) in sequential context-based attention along with a Transformer encoder model. The unsegmented continuous video dataset is jointly trained by balancing the Connectionist Temporal Classification (CTC) loss and the maximum-entropy loss. The proposed approach can capture better fine-grained attention in a single iteration. Experiment evaluations show that it outperforms the state-of-the-art approaches.