Explore cutting-edge research in unsupervised cross-domain image retrieval through this 11-minute conference talk presented at SIGIR 2024. Delve into the innovative Semantic-Attended Mixture-of-Experts approach as authors Kai Wang, Jiayang Liu, Xing Xu, Jingkuan Song, Xin Liu, and Heng Tao Shen discuss their findings. Gain insights into advanced techniques for improving image retrieval across different domains without the need for supervised learning. Learn how this method leverages semantic information and expert models to enhance retrieval accuracy and efficiency in diverse visual contexts.
Unsupervised Cross-Domain Image Retrieval with Semantic-Attended Mixture-of-Experts
Association for Computing Machinery (ACM) via YouTube
Overview
Syllabus
SIGIR 2024 M1.4 [fp] Unsupervised Cross-Domain Image Retrieval Semantic-Attended Mixture-of-Experts
Taught by
Association for Computing Machinery (ACM)
Related Courses
-
Fine-grained Textual Inversion Network for Zero-Shot Composed Image Retrieval - Multimedia 1
-
Invisible Relevance Bias: Text-Image Retrieval Models Prefer AI-Generated Images - Multimedia 1
-
Uncertainty-Guided Noisy Correspondence Learning for Efficient Cross-Modal Matching - Multimodal Session 3.3
-
Multilingual Meta-Distillation Alignment for Semantic Retrieval - Session M2.4
-
Unsupervised Large Language Model Alignment for Information Retrieval via Contrastive Feedback - Lecture 1
-
Contrast then Memorize: Semantic Neighbor Retrieval-Enhanced Inductive Multimodal Knowledge Graph Completion
