[1]
Zhang, P. et al. 2026. FaNe: Towards Fine-Grained Cross-Modal Contrast with False-Negative Reduction and Text-Conditioned Sparse Attention. Proceedings of the AAAI Conference on Artificial Intelligence. 40, 15 (Mar. 2026), 12681–12689. DOI:https://doi.org/10.1609/aaai.v40i15.38264.