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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We focus on the word-level visual lipreading, which requires recognizing theword being spoken, given only the video but not the audio. State-of-the-artmethods explore the use of end-to-end neural networks, including a shallow (upto three layers) 3D convolutional neural network (CNN) + a deep 2D CNN (e.g.,ResNet) as the front-end to extract visual features, and a recurrent neuralnetwork (e.g., bidirectional LSTM) as the back-end for classification. In thiswork, we propose to replace the shallow 3D CNNs + deep 2D CNNs front-end withrecent successful deep 3D CNNs --- two-stream (i.e., grayscale video andoptical flow streams) I3D. We evaluate different combinations of front-end andback-end modules with the grayscale video and optical flow inputs on the LRWdataset. The experiments show that, compared to the shallow 3D CNNs + deep 2DCNNs front-end, the deep 3D CNNs front-end with pre-training on the large-scaleimage and video datasets (e.g., ImageNet and Kinetics) can improve theclassification accuracy. Also, we demonstrate that using the optical flow inputalone can achieve comparable performance as using the grayscale video as input.Moreover, the two-stream network using both the grayscale video and opticalflow inputs can further improve the performance. Overall, our two-stream I3Dfront-end with a Bi-LSTM back-end results in an absolute improvement of 5.3%over the previous art on the LRW dataset.

Learning Spatio-Temporal Features with Two-Stream Deep 3D CNNs for Lipreading