{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:49:16Z","timestamp":1773802156769,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"15","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>With the rapid growth of visual content in open-world environments, zero-shot hashing image retrieval (ZSHIR) has emerged to tackle the challenge of recognizing novel classes using attribute-level and semantic information.  However, existing methods often rely on shallow fusion of multi-source cues (e.g., attributes, labels, and visual features) through external supervision or feature concatenation, failing to capture the underlying semantic structure in a generative way.  Particularly, current bridging strategies between modalities suffer from information fragmentation and weak alignment, hindering the model's ability to fully understand complex attribute-visual relations.  Moreover, subtle semantic gaps or \u201csemantic drift\u201d between seen and unseen classes further degrade inter-class separability and the scalability of hashing models.  To address these issues, we propose a novel framework called Proxy Zero-Shot Hashing with Multimodal Fusion via Stable Diffusion (PZSH), which integrates generative modeling and contrastive learning.  PZSH leverages a pre-trained Stable Diffusion (SD) model to synthesize multimodal content, and uses dual BLIP encoders to enhance semantic alignment across modalities. We further design a proxy hashing loss to enforce discriminative binary representations.  Extensive experiments on benchmark datasets show that PZSH achieves state-of-the-art performance with stronger generalization to unseen classes.<\/jats:p>","DOI":"10.1609\/aaai.v40i15.38247","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:18:47Z","timestamp":1773793127000},"page":"12529-12537","source":"Crossref","is-referenced-by-count":0,"title":["Proxy Zero-Shot Hashing with Multimodal Fusion via Stable Diffusion"],"prefix":"10.1609","volume":"40","author":[{"given":"Hui","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weikang","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/38247\/42209","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/38247\/42209","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:18:47Z","timestamp":1773793127000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/38247"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i15.38247","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}