Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

MAE-AST: Masked Autoencoding Audio Spectrogram Transformer



Alan Baade , Puyuan Peng , David Harwath

* Submitted to INTERSPEECH. 5 pages, 2 figures, 5 tables 

   Access Paper or Ask Questions

Word Discovery in Visually Grounded, Self-Supervised Speech Models



Puyuan Peng , David Harwath

* submitted to Interspeech 2022 

   Access Paper or Ask Questions

Self-Supervised Representation Learning for Speech Using Visual Grounding and Masked Language Modeling



Puyuan Peng , David Harwath

* SAS workshop at AAAI2022 

   Access Paper or Ask Questions

Everything at Once -- Multi-modal Fusion Transformer for Video Retrieval



Nina Shvetsova , Brian Chen , Andrew Rouditchenko , Samuel Thomas , Brian Kingsbury , Rogerio Feris , David Harwath , James Glass , Hilde Kuehne


   Access Paper or Ask Questions

Routing with Self-Attention for Multimodal Capsule Networks



Kevin Duarte , Brian Chen , Nina Shvetsova , Andrew Rouditchenko , Samuel Thomas , Alexander Liu , David Harwath , James Glass , Hilde Kuehne , Mubarak Shah


   Access Paper or Ask Questions

Cascaded Multilingual Audio-Visual Learning from Videos



Andrew Rouditchenko , Angie Boggust , David Harwath , Samuel Thomas , Hilde Kuehne , Brian Chen , Rameswar Panda , Rogerio Feris , Brian Kingsbury , Michael Picheny , James Glass

* Presented at Interspeech 2021. This version contains updated results using the YouCook-Japanese dataset 

   Access Paper or Ask Questions

Fast-Slow Transformer for Visually Grounding Speech



Puyuan Peng , David Harwath

* 5 pages, 1 figure 

   Access Paper or Ask Questions

Learning Audio-Visual Dereverberation



Changan Chen , Wei Sun , David Harwath , Kristen Grauman


   Access Paper or Ask Questions

Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions



Mathew Monfort , SouYoung Jin , Alexander Liu , David Harwath , Rogerio Feris , James Glass , Aude Oliva

* To appear at CVPR 2021 

   Access Paper or Ask Questions

1
2
3
>>