CVT-SLR: Contrastive Visual-Textual Transformation for Sign Language Recognition with Variational Alignment

Siyuan Li, Jun Xia, Ge Wang, Stan Li, Cheng Tan, Yile Wang, Jiangbin Zheng, Yidong Chen

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 8 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• binbinjiang/CVT-SLR

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Sign language recognition (SLR) is a weakly supervised task that annotates sign videos as textual glosses. Recent studies show that insufficient training caused by the lack of large-scale available sign datasets becomes the main bottleneck for SLR. Most SLR works thereby adopt pretrained visual modules and develop two mainstream solutions. The multi-stream architectures extend multi-cue visual features, yielding the current SOTA performances but requiring complex designs and might introduce potential noise. Alternatively, the advanced single-cue SLR frameworks using explicit cross-modal alignment between visual and textual modalities are simple and effective, potentially competitive with the multi-cue framework. In this work, we propose a novel contrastive visual-textual transformation for SLR, CVT-SLR, to fully explore the pretrained knowledge of both the visual and language modalities. Based on the single-cue cross-modal alignment framework, we propose a variational autoencoder (VAE) for pretrained contextual knowledge while introducing the complete pretrained language module. The VAE implicitly aligns visual and textual modalities while benefiting from pretrained contextual knowledge as the traditional contextual module. Meanwhile, a contrastive cross-modal alignment algorithm is designed to explicitly enhance the consistency constraints. Extensive experiments on public datasets (PHOENIX-2014 and PHOENIX-2014T) demonstrate that our proposed CVT-SLR consistently outperforms existing single-cue methods and even outperforms SOTA multi-cue methods. The source codes and models are available at https://github.com/binbinjiang/CVT-SLR.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2303.05725")
get_code_for_paper("2303.05725")
have("2303.05725")

Connect an agent — have() is free.