Yen-Chun Chen

LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval pdf

Jingjing Liu, Shuohang Wang, Siqi Sun, 2021, NAACL.

Cluster-Former: Clustering-based Sparse Transformer for Question Answering

Zhe Gan, Jingjing Liu, Shuohang Wang, 2021, FINDINGS.

VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation pdf

Zhe Gan, Jingjing Liu, Jie Lei, 2021, NeurIPS Datasets and Benchmarks.

Playing Lottery Tickets with Vision and Language pdf

Zhe Gan, Jingjing Liu, Shuohang Wang, 2021, AAAI.