Chen, Yang, Hu, Hexiang, Luan, Yi, Sun, Haitian, Changpinyo, Soravit, Ritter, Alan, and Chang, Ming-Wei. Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?. Web. doi:10.18653/v1/2023.emnlp-main.925.

Chen, Yang, Hu, Hexiang, Luan, Yi, Sun, Haitian, Changpinyo, Soravit, Ritter, Alan, & Chang, Ming-Wei. Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?. https://doi.org/10.18653/v1/2023.emnlp-main.925

Chen, Yang, Hu, Hexiang, Luan, Yi, Sun, Haitian, Changpinyo, Soravit, Ritter, Alan, and Chang, Ming-Wei. "Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?". Country unknown/Code not available: Association for Computational Linguistics. https://doi.org/10.18653/v1/2023.emnlp-main.925. https://par.nsf.gov/biblio/10512971.

@article{osti_10512971,
place = {Country unknown/Code not available}, title = {Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?}, url = {https://par.nsf.gov/biblio/10512971}, DOI = {10.18653/v1/2023.emnlp-main.925}, abstractNote = {}, journal = {}, publisher = {Association for Computational Linguistics}, author = {Chen, Yang and Hu, Hexiang and Luan, Yi and Sun, Haitian and Changpinyo, Soravit and Ritter, Alan and Chang, Ming-Wei}, }