作者位次 #5/5ICML 2026Poster· Applications / Computer Vision
Is Task-Specific Training Necessary for Anomaly Detection?
Xingwu Zhang · Guanxuan Li · Paul Henderson · Gerardo Aragon-Camarasa · ZIJUN LONG
多模态OpenReview
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Xingwu Zhang · Guanxuan Li · Paul Henderson · Gerardo Aragon-Camarasa · ZIJUN LONG
Zhuocheng Zhang · Xingwu Zhang · Kangheng Liang · Guanxuan Li · Richard McCreadie · ZIJUN LONG
Recent advances in interactive text-to-image retrieval (I-TIR) use diffusion models to bridge the modality gap between the textual information need and the images to be searched. However, existing frameworks fuse multi-modal user feedback by simple embedding addition. In this work, we show that t...
Xingwu Zhang · Guanxuan Li · Zhuocheng Zhang · ZIJUN LONG