From Skeleton to Flesh: Aggregated Relational Transformer Towards Controllable Video Captioning with Two-Step Decoding.

@inproceedings{cao-2025-skeleton, author = {Qianwen Cao and Heyan Huang and Boran Wang}, editor = {Zhongfei Zhang and Elisa Ricci and Yan Yan and Liqiang Nie and Vincent Oria and Lamberto Ballan}, title = {{From Skeleton to Flesh: Aggregated Relational Transformer Towards Controllable Video Captioning with Two-Step Decoding}}, booktitle = {{Proceedings of the 2025 International Conference on Multimedia Retrieval, ICMR 2025, Chicago, IL, USA, 30 June 2025 - 3 July 2025}}, pages = {61--70}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3731715.3733347}, doi = {https://doi.org/10.1145/3731715.3733347} }