Raksha Ramesh, Vishal Anand, Zifan Chen, Yifei Dong, Yun Chen, Ching-Yung Lin. Leveraging Text Representation and Face-head Tracking for Long-form Multimodal Semantic Relation Understanding. In João Magalhães, Alberto Del Bimbo, Shin'ichi Satoh 0001, Nicu Sebe, Xavier Alameda-Pineda, Qin Jin, Vincent Oria, Laura Toni, editors, MM '22: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, October 10 - 14, 2022. pages 7215-7219, ACM, 2022. [doi]
@inproceedings{RameshACDCL22, title = {Leveraging Text Representation and Face-head Tracking for Long-form Multimodal Semantic Relation Understanding}, author = {Raksha Ramesh and Vishal Anand and Zifan Chen and Yifei Dong and Yun Chen and Ching-Yung Lin}, year = {2022}, doi = {10.1145/3503161.3551610}, url = {https://doi.org/10.1145/3503161.3551610}, researchr = {https://researchr.org/publication/RameshACDCL22}, cites = {0}, citedby = {0}, pages = {7215-7219}, booktitle = {MM '22: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, October 10 - 14, 2022}, editor = {João Magalhães and Alberto Del Bimbo and Shin'ichi Satoh 0001 and Nicu Sebe and Xavier Alameda-Pineda and Qin Jin and Vincent Oria and Laura Toni}, publisher = {ACM}, isbn = {978-1-4503-9203-7}, }