English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Continuous sign language recognition (cSLR) is a public significant task thattranscribes a sign language video into an ordered gloss sequence. It isimportant to capture the fine-grained gloss-level details, since there is noexplicit alignment between sign video frames and the corresponding glosses.Among the past works, one promising way is to adopt a one-dimensionalconvolutional network (1D-CNN) to temporally fuse the sequential frames.However, CNNs are agnostic to similarity or dissimilarity, and thus are unableto capture local consistent semantics within temporally neighboring frames. Toaddress the issue, we propose to adaptively fuse local features via temporalsimilarity for this task. Specifically, we devise a Multi-scale Local-TemporalSimilarity Fusion Network (mLTSF-Net) as follows: 1) In terms of a specificvideo frame, we firstly select its similar neighbours with multi-scalereceptive regions to accommodate different lengths of glosses. 2) To ensuretemporal consistency, we then use position-aware convolution to temporallyconvolve each scale of selected frames. 3) To obtain a local-temporallyenhanced frame-wise representation, we finally fuse the results of differentscales using a content-dependent aggregator. We train our model in anend-to-end fashion, and the experimental results on RWTH-PHOENIX-Weather 2014datasets (RWTH) demonstrate that our model achieves competitive performancecompared with several state-of-the-art models.

Multi-Scale Local-Temporal Similarity Fusion for Continuous Sign Language Recognition