NIPS Proceedingsβ

Jiasen Lu

3 Papers

  • ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks (2019)
  • Best of Both Worlds: Transferring Knowledge from Discriminative Learning to a Generative Visual Dialog Model (2017)
  • Hierarchical Question-Image Co-Attention for Visual Question Answering (2016)