Mini-3DCvT: a lightweight lip-reading method based on 3D convolution visual transformer

Xception: Deep Learning with Depthwise Separable Convolutions

François Chollet · 2017 · 19K citations

Computing, Computer Science, Computer Vision +7

CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features

Sangdoo Yun, Dongyoon Han, Sanghyuk Chun et al. · 2019 · 4.7K citations

Computing, Computer Science, Computer Vision +16

Visual Contribution to Speech Intelligibility in Noise

William H. Sumby, Irwin Pollack · The Journal of the Acoustical Society of America · 1954 · 2.6K citations

Health Professions, Audiology, Speech-language Pathology +13

TinyBERT: Distilling BERT for Natural Language Understanding

Xiaoqi Jiao, Yichun Yin, Lifeng Shang et al. · 2020 · 1.6K citations · Full text

Computing, Computer Science, Knowledge Representation +14

ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

Zhenzhong Lan, Mingda Chen, Sebastian Goodman et al. · arXiv (Cornell University) · 2019 · 984 citations · Full text

Computing, Computer Science, Machine Learning +13