Training for Identity, Inference for Controllability: A Unified Approach to Tuning-Free Face Personalization.

Lianyu Pang|Ji Zhou|Qiping Wang|Baoquan Zhao|Zhenguo Yang|Qing Li|Xudong Mao


Anthology ID:DBLP:conf/mir/PangZWZYLM26
Volume:Proceedings of the 2026 International Conference on Multimedia Retrieval, ICMR 2026, Amsterdam, The Netherlands, June 16-19, 2026
Year:2026
Venue:International Conference on Multimedia Retrieval (ICMR)
Publisher:ACM
Pages:1879-1888
URL:https://doi.org/10.1145/3805622.3810698
DOI:https://doi.org/10.1145/3805622.3810698
DBLP:conf/mir/PangZWZYLM26
BibTeX:
@inproceedings{pang-2026-training, author = {Lianyu Pang and Ji Zhou and Qiping Wang and Baoquan Zhao and Zhenguo Yang and Qing Li and Xudong Mao}, editor = {Stevan Rudinac and Zi Huang and Marcel Worring and Lucia Vadicamo and Xirong Li and Pascal Mettes and Lizi Liao}, title = {{Training for Identity, Inference for Controllability: A Unified Approach to Tuning-Free Face Personalization}}, booktitle = {{Proceedings of the 2026 International Conference on Multimedia Retrieval, ICMR 2026, Amsterdam, The Netherlands, June 16-19, 2026}}, pages = {1879--1888}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3805622.3810698}, doi = {https://doi.org/10.1145/3805622.3810698} }