Step-wise Soft Alignment Enhanced Procedural Text Generation from Long Instructional Videos.

@inproceedings{wang-2025-stepwise, author = {Zhihao Wang and Lin Li and Xian Zhong and Xiaohui Tao and Jianquan Liu}, editor = {Zhongfei Zhang and Elisa Ricci and Yan Yan and Liqiang Nie and Vincent Oria and Lamberto Ballan}, title = {{Step-wise Soft Alignment Enhanced Procedural Text Generation from Long Instructional Videos}}, booktitle = {{Proceedings of the 2025 International Conference on Multimedia Retrieval, ICMR 2025, Chicago, IL, USA, 30 June 2025 - 3 July 2025}}, pages = {1377--1385}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3731715.3733438}, doi = {https://doi.org/10.1145/3731715.3733438} }