most citedVIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning

33 citations · 36 across the 2 of their papers we have counts for

collaborators

5 papers

cs.CV202133 cited

VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning

Hao Tan, Jie Lei, Thomas Wolf +1

Video understanding relies on perceiving the global content and modeling its internal connections (e.g., causality, movement, and spatio-temporal correspondence). To learn these in…

cs.CL2021

Unifying Vision-and-Language Tasks via Text Generation

Jaemin Cho, Jie Lei, Hao Tan +1

Existing methods for vision-and-language learning typically require designing task-specific architectures and objectives for each task. For example, a multi-label answer classifier…

cs.CL20203 cited

ArraMon: A Joint Navigation-Assembly Instruction Interpretation Task in Dynamic Environments

Hyounghun Kim, Abhay Zala, Graham Burri +2

For embodied agents, navigation is an important ability but not an isolated goal. Agents are also expected to perform specific tasks after reaching the target location, such as pic…

cs.CL2020

Vokenization: Improving Language Understanding with Contextualized, Visual-Grounded Supervision

Hao Tan, Mohit Bansal

Humans learn language by listening, speaking, writing, reading, and also, via interaction with the multimodal real world. Existing language pre-training frameworks show the effecti…

cs.CL2020

MAF: Multimodal Alignment Framework for Weakly-Supervised Phrase Grounding

Qinxin Wang, Hao Tan, Sheng Shen +2

Phrase localization is a task that studies the mapping from textual phrases to regions of an image. Given difficulties in annotating phrase-to-object datasets at scale, we develop…