SignCLIP: Connecting Text and Sign Language by Contrastive Learning

TL;DR

SignCLIP adapts CLIP to embed spoken language text and sign language videos into a shared space, enabling effective cross-modal sign language understanding without task-specific training.

Contribution

It introduces a scalable, multilingual pretraining approach for sign language processing using contrastive learning on large video-text datasets.

Findings

High accuracy in in-domain text-video retrieval

Competitive performance on out-of-domain sign recognition

Provides linguistic insights through latent space analysis

Abstract

We present SignCLIP, which re-purposes CLIP (Contrastive Language-Image Pretraining) to project spoken language text and sign language videos, two classes of natural languages of distinct modalities, into the same space. SignCLIP is an efficient method of learning useful visual representations for sign language processing from large-scale, multilingual video-text pairs, without directly optimizing for a specific task or sign language which is often of limited size. We pretrain SignCLIP on Spreadthesign, a prominent sign language dictionary consisting of ~500 thousand video clips in up to 44 sign languages, and evaluate it with various downstream datasets. SignCLIP discerns in-domain signing with notable text-to-video/video-to-text retrieval accuracy. It also performs competitively for out-of-domain downstream tasks such as isolated sign language recognition upon essential few-shot prompting or fine-tuning. We analyze the latent space formed by the spoken language text and sign language poses, which provides additional linguistic insights. Our code and models are openly available.