Uncertainty-aware sign language video retrieval with probability distribution modeling

TL;DR

This paper introduces UPRet, a novel uncertainty-aware probabilistic approach for sign language video retrieval that models the inherent uncertainty of sign language videos to improve retrieval accuracy.

Contribution

The paper proposes UPRet, a new method that models sign language video-text mapping as probability distributions, addressing uncertainty and scarcity of fine-grained annotations.

Findings

Achieves state-of-the-art results on three benchmarks.

Effectively models uncertainty in sign language videos.

Demonstrates improved retrieval performance over existing methods.

Abstract

Sign language video retrieval plays a key role in facilitating information access for the deaf community. Despite significant advances in video-text retrieval, the complexity and inherent uncertainty of sign language preclude the direct application of these techniques. Previous methods achieve the mapping between sign language video and text through fine-grained modal alignment. However, due to the scarcity of fine-grained annotation, the uncertainty inherent in sign language video is underestimated, limiting the further development of sign language retrieval tasks. To address this challenge, we propose a novel Uncertainty-aware Probability Distribution Retrieval (UPRet), that conceptualizes the mapping process of sign language video and text in terms of probability distributions, explores their potential interrelationships, and enables flexible mappings. Experiments on three benchmarks demonstrate the effectiveness of our method, which achieves state-of-the-art results on How2Sign (59.1%), PHOENIX-2014T (72.0%), and CSL-Daily (78.4%).