Research
Speech & Audio
Large-scale weakly-supervised pre-training for video action recognition
May 1, 2019
Abstract
Current fully-supervised video datasets consist of only a few hundred thousand videos and fewer than a thousand domain-specific labels. This hinders the progress towards advanced video architectures. This paper presents an in-depth study of using large volumes of web videos for pre-training video models for the task of action recognition. Our primary empirical finding is that pre-training at a very large scale (over 65 million videos), despite on noisy social-media videos and hashtags, substantially improves the state-of-the-art on three challenging public action recognition datasets. Further, we examine three questions in the construction of weakly-supervised video action datasets. First, given that actions involve interactions with objects, how should one construct a verb-object pre-training label space to benefit transfer learning the most? Second, frame-based models perform quite well on action recognition; is pre-training for good image features sufficient or is pre-training for spatio-temporal features valuable for optimal transfer learning? Finally, actions are generally less well-localized in long videos vs. short videos; since action labels are provided at a video level, how should one choose video clips for best performance, given some fixed budget of number or minutes of videos?
AUTHORS
Research Topics
Related Publications
May 12, 2026
Human & Machine Intelligence
NeuralSet: A High-Performing Python Package for Neuro-AI
Corentin Bel, Linnea Evanson, Julien Gadonneix, Andrea Santos Revilla, Mingfang (Lucy) Zhang, Julie Bonnaire, Charlotte Caucheteux, Alexandre Défossez, Théo Desbordes, Pablo Diego-Simón, Shubh Khanna, Juliette Millet, Pierre Orhan, Saarang Panchavati, Antoine Ratouchniak, Alexis Thual, Hubert Jacob Banville, Jarod Levy, Jean Remi King, Josephine Raugel, Jérémy Rapin, Katelyn Begany, Marlene Careil, Simon Dahan, Sophia Houhamdi, Stéphane d'Ascoli, Teon Brooks, Yohann Benchetrit
May 12, 2026
March 17, 2026
Speech & Audio
Omnilingual SONAR: Cross-Lingual and Cross-Modal Sentence Embeddings Bridging Massively Multilingual Text and Speech
Omnilingual SONAR Team, Ioannis Tsiamas, Yen Meng, Vivek Iyer, Guillem Ramirez, Jaehyeong Jo, Alexandre Mourachko, Yu-An Chung, Artyom Kozhevnikov, Belen Alastruey, Christophe Ropers, David Dale, Holger Schwenk, João Maria Janeiro, Kevin Heffernan, Loic Barrault, Marta R. Costa-jussa, Paul-Ambroise Duquenne, Pere Lluís Huguet Cabot
March 17, 2026
November 10, 2025
Speech & Audio
Omnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages
Omnilingual ASR team, Skyler Wang, Ife Adebara, Michael Auli, Kaushik Ram Sadagopan, Zheng-Xin Yong, Albert Ventayol-Boada, Alexandre Mourachko, Alexander Erben, Yu-An Chung, Arina Turkatenko, Artyom Kozhevnikov, Caley Drooff, Can Balioglu, Chierh Cheng, Christophe Ropers, Cynthia Gao, Gabriel Mejia Gonzalez, Gil Keren, Jean Maillard, Joe Chuang, Kehan Lyu, Kevin Chan, Mark Duppenthaler, Mary Williamson, Matthew Setzler, Paul-Ambroise Duquenne, Rashel Moritz, Safiyyah Saleem, Sagar Miglani, Shireen Yates, Vineel Pratap, Yen Meng
November 10, 2025
June 27, 2025
Human & Machine Intelligence
Conversational AI
Seamless Interaction: Dyadic Audiovisual Motion Modeling and Large-Scale Dataset
Morteza Behrooz, Ning Dong, Jeff Girard, Vasu Sharma, Jan Zikes, Akinniyi Akinyemi, Alex Shcherbyna, Alexander Richard, Alice Rakotoarison, Amia Oberai, Anastasis Stathopoulos, Anna Sun, Antony D'Avirro, Arina Turkatenko, Benjamin Peloquin, Bo Wan, Brandon Han, Carleigh Wood, Chao Wang, Chen Zhang, Christophe Ropers, Christopher Klaiber, Cynthia Gao, Dejan Kovachev, Denise Hernandez, Evonne Ng, Fabian Prada, Fabio Maria Carlucci, Guangyao Ma, Hang Li, Hirofumi Inaguma, Hongyu Gong, Jason Zheng, Jeff Wang, Jie Shen, Jiemin Zhang, Jing Ma, Joe Chuang, Jon Daly, Jovan Popovic, Joy Chen, Juan Pino, Julia Buffalini, Zhiyuan Yao, Junming Chen, Kam-Woh Ng, Kathryn Alvero, Louis-Philippe Morency, Lucas Mantovani, Mark Duppenthaler, Martin Gleize, Martin Ma, Mary Williamson, Michael Zollhoefer, Moneish Kumar, Omid Poursaeed, Paden Tomasello, Pavel Litvin, Pavlo Zhyzheria, Praveen Chowdary, Qingyao Jia, Raj Janardhan, Rongjie Huang, Safiyyah Saleem, Sagar Miglani, Sahir Gomez, Sen He, Shiyang Cheng, Somya Jain, Sreyas Mohan, Srivathsan Govindarajan, Tao Xiang, Tu Anh Nguyen, Tuan Tran, Vasu Agrawal, Wei Liu, Xinyue Zhang, Xutai Ma, Yilei Li, Yilin Yang, Yordan Hristov, Zhang Chen
June 27, 2025
October 10, 2016
Speech & Audio
Computer Vision
Polysemous Codes | Facebook AI Research
Matthijs Douze, Hervé Jégou, Florent Perronnin
October 10, 2016
June 18, 2018
Speech & Audio
Computer Vision
Low-shot learning with large-scale diffusion | Facebook AI Research
Matthijs Douze, Arthur Szlam, Bharath Hariharan, Hervé Jégou
June 18, 2018
July 10, 2018
NLP
Speech & Audio
Hierarchical Text Generation and Planning for Strategic Dialogue | Facebook AI Research
Denis Yarats, Mike Lewis
July 10, 2018
September 08, 2017
NLP
Speech & Audio
Deal or No Deal? End-to-End Learning for Negotiation Dialogues | Facebook AI Research
Mike Lewis, Denis Yarats, Yann Dauphin, Devi Parikh, Dhruv Batra
September 08, 2017
Help Us Pioneer The Future of AI
We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.
Our approach
Latest news
Foundational models
Meta © 2026