SCNet: Spatio-temporal Feature Aggregation and Cross-modal Interactive Encoding Network for DAVIS Object Detection.

@inproceedings{chen-2025-scnet, author = {Yunhua Chen and Jinyu Zhong and Pinghua Chen and Wei Wu and Jinsheng Xiao}, editor = {Zhongfei Zhang and Elisa Ricci and Yan Yan and Liqiang Nie and Vincent Oria and Lamberto Ballan}, title = {{SCNet: Spatio-temporal Feature Aggregation and Cross-modal Interactive Encoding Network for DAVIS Object Detection}}, booktitle = {{Proceedings of the 2025 International Conference on Multimedia Retrieval, ICMR 2025, Chicago, IL, USA, 30 June 2025 - 3 July 2025}}, pages = {99--107}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3731715.3733428}, doi = {https://doi.org/10.1145/3731715.3733428} }