Overview

Image retrieval studies how to find relevant images in large collections using images, text, sketches, metadata, or combinations of these. Common approaches learn shared vision-language embeddings with contrastive training, then improve fine-grained matching with regions or patches, reranking, and compact hashes or indexes. Composed and conversational retrieval adds user-described changes or constraints, while applications range from products and people to medical images, geolocation, and scientific data. A central challenge is balancing broad, efficient retrieval with precise semantic and local matching, while benchmarks must distinguish genuine multimodal understanding from shortcuts or noisy relevance labels.

Latest papers

CardsList

96 papers11 papers in the last four weeks, up 57% on the four weeks before. 0.1% of all new papers.

  1. Through the PRISm: Importance-Aware Scene Graphs for Semantic Image Retrieval

    Dec 20, 2025Dimitrios Georgoulopoulos, Nikolaos Chaidos, Angeliki Dimitriou +1Image RetrievalGraph-Based Retrieval

  2. VLM2GeoVec: Toward Universal Multimodal Embeddings for Remote Sensing

    Dec 12, 2025Emanuel Sánchez Aimar, Gulnaz Zhambulova, Fahad Shahbaz Khan +2Multimodal UnderstandingCross-Modal Learning

  3. DualHash: Stochastic Primal-Dual Algorithms for W-Type Regularized Deep Hashing

    Oct 21, 2025Luxuan Li, Xiao Wang, Chunfeng CuiImage RetrievalBinary Quantization

  4. Disentangling Latent Embeddings with Sparse Linear Concept Cones (SLiCC)

    Aug 27, 2025Zhi Li, Hau Phan, Matthew Emigh +1Sparse CodingDisentangled Representation Learning

  5. Open-Attribute Person Retrieval: Finding People Through Distinctive and Novel Attributes

    Aug 2, 2025Minjeong Park, Hongbeen Park, Sangwon Lee +1Pedestrian Attribute RecognitionInformation Retrieval

  6. Latent Space Analysis for Interpretable Uncertainty in Melanoma Classification

    Jun 23, 2025Ciro Listone, Aniello MuranoVariational AutoencodersSkin Lesion Classification