CiCo: Domain-Aware Sign Language Retrieval via Cross-Lingual Contrastive Learning

TL;DR

This paper introduces CiCo, a domain-aware cross-lingual contrastive learning framework for sign language retrieval that effectively models linguistic properties and addresses data scarcity, significantly improving retrieval performance.

Contribution

The work proposes a novel cross-lingual contrastive learning approach that incorporates linguistic properties and domain-aware encoding for sign language retrieval, outperforming previous methods.

Findings

Significantly improves T2V and V2T retrieval metrics on multiple datasets.

Effectively leverages large-scale sign video pre-training with pseudo-labeling.

Achieves state-of-the-art performance with large margin improvements.

Abstract

This work focuses on sign language retrieval-a recently proposed task for sign language understanding. Sign language retrieval consists of two sub-tasks: text-to-sign-video (T2V) retrieval and sign-video-to-text (V2T) retrieval. Different from traditional video-text retrieval, sign language videos, not only contain visual signals but also carry abundant semantic meanings by themselves due to the fact that sign languages are also natural languages. Considering this character, we formulate sign language retrieval as a cross-lingual retrieval problem as well as a video-text retrieval task. Concretely, we take into account the linguistic properties of both sign languages and natural languages, and simultaneously identify the fine-grained cross-lingual (i.e., sign-to-word) mappings while contrasting the texts and the sign videos in a joint embedding space. This process is termed as cross-lingual contrastive learning. Another challenge is raised by the data scarcity issue-sign language datasets are orders of magnitude smaller in scale than that of speech recognition. We alleviate this issue by adopting a domain-agnostic sign encoder pre-trained on large-scale sign videos into the target domain via pseudo-labeling. Our framework, termed as domain-aware sign language retrieval via Cross-lingual Contrastive learning or CiCo for short, outperforms the pioneering method by large margins on various datasets, e.g., +22.4 T2V and +28.0 V2T R@1 improvements on How2Sign dataset, and +13.7 T2V and +17.1 V2T R@1 improvements on PHOENIX-2014T dataset. Code and models are available at: https://github.com/FangyunWei/SLRT.