Lin Wang, Hongyi Zhang, Xingfu Wang, Yan Xiong. Learning a Contextualized Multimodal Embedding for Zero-shot Cooking Video Caption Generation. In Wen-Huang Cheng, Wei-Ta Chu, Min-Chun Hu 0001, Jiaying Liu 0001, Munchurl Kim, Wei Zhang 0031, editors, ACM Multimedia Asia 2023, MMAsia 2023, Tainan, Taiwan, December 6-8, 2023. ACM, 2023. [doi]
@inproceedings{WangZWX23, title = {Learning a Contextualized Multimodal Embedding for Zero-shot Cooking Video Caption Generation}, author = {Lin Wang and Hongyi Zhang and Xingfu Wang and Yan Xiong}, year = {2023}, doi = {10.1145/3595916.3626413}, url = {https://doi.org/10.1145/3595916.3626413}, researchr = {https://researchr.org/publication/WangZWX23}, cites = {0}, citedby = {0}, booktitle = {ACM Multimedia Asia 2023, MMAsia 2023, Tainan, Taiwan, December 6-8, 2023}, editor = {Wen-Huang Cheng and Wei-Ta Chu and Min-Chun Hu 0001 and Jiaying Liu 0001 and Munchurl Kim and Wei Zhang 0031}, publisher = {ACM}, }