Hierarchical Multimodal Pre-training for Visually Rich Webpage Understanding.

@inproceedings{xu-2024-hierarchical, author = {Hongshen Xu and Lu Chen and Zihan Zhao and Da Ma and Ruisheng Cao and Zichen Zhu and Kai Yu}, editor = {Luz Angelica Caudillo-Mata and Silvio Lattanzi and Andr\'{e}s Mu\~{n}oz Medina and Leman Akoglu and Aristides Gionis and Sergei Vassilvitskii}, title = {{Hierarchical Multimodal Pre-training for Visually Rich Webpage Understanding}}, booktitle = {{Proceedings of the 17th ACM International Conference on Web Search and Data Mining, WSDM 2024, Merida, Mexico, March 4-8, 2024}}, pages = {864--872}, publisher = {ACM}, year = {2024}, url = {https://doi.org/10.1145/3616855.3635753}, doi = {https://doi.org/10.1145/3616855.3635753} }