SlowFast Network for Continuous Sign Language Recognition

21 Sep 2023  ·  Junseok Ahn, Youngjoon Jang, Joon Son Chung ·

The objective of this work is the effective extraction of spatial and dynamic features for Continuous Sign Language Recognition (CSLR). To accomplish this, we utilise a two-pathway SlowFast network, where each pathway operates at distinct temporal resolutions to separately capture spatial (hand shapes, facial expressions) and dynamic (movements) information. In addition, we introduce two distinct feature fusion methods, carefully designed for the characteristics of CSLR: (1) Bi-directional Feature Fusion (BFF), which facilitates the transfer of dynamic semantics into spatial semantics and vice versa; and (2) Pathway Feature Enhancement (PFE), which enriches dynamic and spatial representations through auxiliary subnetworks, while avoiding the need for extra inference time. As a result, our model further strengthens spatial and dynamic representations in parallel. We demonstrate that the proposed framework outperforms the current state-of-the-art performance on popular CSLR datasets, including PHOENIX14, PHOENIX14-T, and CSL-Daily.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Sign Language Recognition CSL-Daily SlowFastSign Word Error Rate (WER) 24.9 # 1
Sign Language Recognition RWTH-PHOENIX-Weather 2014 SlowFastSign Word Error Rate (WER) 18.3 # 1
Sign Language Recognition RWTH-PHOENIX-Weather 2014 T SlowFastSign Word Error Rate (WER) 18.7 # 1

Methods


No methods listed for this paper. Add relevant methods here