ChiQA: A Large Scale Image-based Real-World Question Answering Dataset for Multi-Modal Understanding.

@inproceedings{wang-2022-chiqa, author = {Bingning Wang and Feiyang Lv and Ting Yao and Jin Ma and Yu Luo and Haijin Liang}, editor = {Mohammad Al Hasan and Li Xiong}, title = {{ChiQA: A Large Scale Image-based Real-World Question Answering Dataset for Multi-Modal Understanding}}, booktitle = {{Proceedings of the 31st ACM International Conference on Information & Knowledge Management, Atlanta, GA, USA, October 17-21, 2022}}, pages = {1996--2006}, publisher = {ACM}, year = {2022}, url = {https://doi.org/10.1145/3511808.3557258}, doi = {https://doi.org/10.1145/3511808.3557258} }