Naver at ActivityNet Challenge 2019 -- Task B Active Speaker Detection (AVA)

Ensemble methods in machine learning

T. G. Dietterich · 2000

Earlier work this paper cites.

Return of the devil in the details: Delving deep into convolutional nets

K. Chatfield, K. Simonyan, A. Vedaldi, and A. Zisserman · 2014

Earlier work this paper cites.

ADAM: A method for stochastic optimization

D. P. Kingma and J. Ba · 2015

Earlier work this paper cites.

Audio-visual speech recognition using deep learning

K. Noda, Y. Yamaguchi, K. Nakadai, H. G. Okuno, and T. Ogata · 2015

Earlier work this paper cites.

Lipnet: End-to-end sentence-level lipreading

Original

Y. M. Assael, B. Shillingford, S. Whiteson, and N. De Freitas · 2016

Earlier work this paper cites.

Cross-modal supervision for learning active speaker detection in video

P. Chakravarty and T. Tuytelaars · 2016

Cited alongside, same era.

Out of time: automated lip sync in the wild

J. S. Chung and A. Zisserman · 2016

Cited alongside, same era.

Automatic differentiation in pytorch

A. Paszke, S. Gross, S. Chintala, G. Chanan, E. Yang, Z. DeVito, Z. Lin, A. Desmaison, L. Antiga, and A. Lerer · 2017

Cited alongside, same era.

The conversation: Deep audio-visual speech enhancement

T. Afouras, J. S. Chung, and A. Zisserman · 2018

Cited alongside, same era.

Looking to listen at the cocktail party: a speaker-independent audio-visual model for speech separation

A. Ephrat, I. Mosseri, O. Lang, T. Dekel, K. Wilson, A. Hassidim, W. T. Freeman, and M. Rubinstein · 2018

Later among the works it cites.

Deep audio-visual speech recognition

T. Afouras, J. S. Chung, A. Senior, O. Vinyals, and A. Zisserman · 2019

Closest in time.

Perfect match: Improved cross-modal embeddings for audio-visual synchronisation

S.-W. Chung, J. S. Chung, and H.-G. Kang · 2019

Closest in time.

AVA-ActiveSpeaker: An audio-visual dataset for active speaker detection

Original

J. Roth, S. Chaudhuri, O. Klejch, R. Marvin, A. Gallagher, L. Kaver, S. Ramaswamy, A. Stopczynski, C. Schmid, Z. Xi, et al · 2019

Closest in time.