How2: A Large-scale Dataset for Multimodal Language Understanding

Recommended citation: @inproceedings{sanabria2018how2, author = {Sanabria, Ramon and Caglayan, Ozan and Palaskar, Shruti and Elliott, Desmond and Barrault, Loïc and Specia, Lucia and Metze, Florian}, booktitle = {Proceedings of the Workshop on Visually Grounded Interaction and Language (NeurIPS 2018)}, category = {ACTI}, month = {November}, title = {How2: A Large-scale Dataset for Multimodal Language Understanding}, url = {https://loicbarrault.github.io/papers/sanabria_vigil2018.pdf}, year = {2018} } https://loicbarrault.github.io/papers/sanabria_vigil2018.pdf