Hassan Akbari, Liangzhe Yuan, Rui Qian, Wei-Hong Chuang, Shih-Fu Chang, Yin Cui, Boqing Gong. VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text. In Marc'Aurelio Ranzato, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, Jennifer Wortman Vaughan, editors, Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual. pages 24206-24221, 2021. [doi]
@inproceedings{AkbariYQCCCG21, title = {VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text}, author = {Hassan Akbari and Liangzhe Yuan and Rui Qian and Wei-Hong Chuang and Shih-Fu Chang and Yin Cui and Boqing Gong}, year = {2021}, url = {https://proceedings.neurips.cc/paper/2021/hash/cb3213ada48302953cb0f166464ab356-Abstract.html}, researchr = {https://researchr.org/publication/AkbariYQCCCG21}, cites = {0}, citedby = {0}, pages = {24206-24221}, booktitle = {Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual}, editor = {Marc'Aurelio Ranzato and Alina Beygelzimer and Yann N. Dauphin and Percy Liang and Jennifer Wortman Vaughan}, }