Image Retrieval
Image retrieval focuses on efficiently finding images within large datasets that match a given query, whether that query is an image, text description, or a combination of both. Current research emphasizes improving retrieval accuracy and efficiency through various techniques, including contrastive learning, the adaptation of large language and vision-language models (like CLIP), and the development of novel architectures such as those incorporating attention mechanisms and hybrid convolutional-Transformer networks. These advancements have significant implications for diverse applications, ranging from digital humanities research to medical diagnosis and robotics, by enabling faster and more accurate searches across vast multimedia collections.
Papers
Document Haystacks: Vision-Language Reasoning Over Piles of 1000+ Documents
Jun Chen, Dannong Xu, Junjie Fei, Chun-Mei Feng, Mohamed Elhoseiny
Improving Factuality of 3D Brain MRI Report Generation with Paired Image-domain Retrieval and Text-domain Augmentation
Junhyeok Lee, Yujin Oh, Dahyoun Lee, Hyon Keun Joh, Chul-Ho Sohn, Sung Hyun Baik, Cheol Kyu Jung, Jung Hyun Park, Kyu Sung Choi, Byung-Hoon Kim, Jong Chul Ye
IFCap: Image-like Retrieval and Frequency-based Entity Filtering for Zero-shot Captioning
Soeun Lee, Si-Woo Kim, Taewhan Kim, Dong-Jin Kim
CBIDR: A novel method for information retrieval combining image and data by means of TOPSIS applied to medical diagnosis
Humberto Giuri, Renato A. Krohling
Search and Detect: Training-Free Long Tail Object Detection via Web-Image Retrieval
Mankeerat Sidhu, Hetarth Chopra, Ansel Blume, Jeonghwan Kim, Revanth Gangi Reddy, Heng Ji