Ensemble CLIPs: Effective Zero-shot Classification with Hundreds of Multi-modal CLIPs.

@inproceedings{han-2025-ensemble, author = {Bowen Han and Shizhuo Deng and Zehua Gan and Da Teng and Dongyue Chen and Tong Jia}, editor = {Zhongfei Zhang and Elisa Ricci and Yan Yan and Liqiang Nie and Vincent Oria and Lamberto Ballan}, title = {{Ensemble CLIPs: Effective Zero-shot Classification with Hundreds of Multi-modal CLIPs}}, booktitle = {{Proceedings of the 2025 International Conference on Multimedia Retrieval, ICMR 2025, Chicago, IL, USA, 30 June 2025 - 3 July 2025}}, pages = {407--415}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3731715.3733328}, doi = {https://doi.org/10.1145/3731715.3733328} }