Overview

Vision-language retrieval studies how to rank images, video, and visual documents against text queries, from short captions to detailed or compositional descriptions. Common approaches include CLIP-style contrastive dual encoders, fine-grained attribute or region alignment, and coarse-to-fine pipelines that rerank candidates with vision-language models or language-model reasoning. Benchmarks span image-text datasets such as COCO and Flickr, video retrieval, and specialized settings including visual documents, geolocation, and fine-grained product search. A central tension is that fast similarity scores can miss logical constraints or subtle evidence, while richer reranking and reasoning improve precision at greater computational cost and may generalize unevenly across domains.

Latest papers

CardsList

107 papers10 papers in the last four weeks, down 37% on the four weeks before. 0.1% of all new papers.

  1. LoCaR: Localized Canvas Retrieval With Frozen Vision-Language Model

    Nov 17, 2026Rahim Hossain, Dipanwita Saha, Ashirbad Mishra +3Image-Text RetrievalVision-Language Retrieval

  2. Negation Through Affirmation: Leveraging Positive Evidence in Vision-Language Models

    Nov 11, 2026Aashish Pokhrel, Tejas Anvekar, Shivanand Venkanna SheshappanavarVLM ReasoningVision-Language Retrieval

  3. Heads That Write, Not Just Point: Image Retrieval Heads in Vision-Language Models

    Nov 3, 2026Junsung Park, Sangwon Yu, Donghun Kang +6Large Vision-Language ModelsVLM Interpretability

  4. MultiInpaintCOCO: Fine-Grained Visual Understanding in Multiple Languages

    Nov 2, 2026Andrei-Alexandru Manea, Jindřich Libovický, Philipp J. RöschMultilingual VLM EvaluationVision-Language Retrieval

  5. Queryable Gaussian View Index: Text Retrieval and Selective Camera Localization

    Oct 30, 2026Tianyu Xiong, Rui Li, Jiaqi YangCamera Pose EstimationVision-Language Retrieval

  6. It Takes Two to Probe, Thousands to Retrieve: Putting Vision--Language Probes to the Retrieval Test

    Oct 29, 2026Ivana Beňová, Michal Gregor, Marián ŠimkoVLM EvaluationVision-Language Retrieval

  7. Whispers from the Neighbors: Rethinking Caption Consensus as Inference-Time Evidence for Vision-Language Retrieval

    Oct 24, 2026Khang Nhat Hoang Vo, Belal Shoer, Abhirama Subramanyam PenamakuriVision-Language RetrievalCross-Modal Retrieval

  8. Mitigating Saliency Collapse: Robust Saliency-Aware Long-Text Image-Text Alignment

    Oct 22, 2026Qiuyu Kong, Zanxi Ruan, Marco Cristani +1Vision-Language AlignmentImage-Text Retrieval

  9. OASIS: Online Anchor-centric Scene Inference System for Open-Vocabulary Retrieval and Navigation in Dynamic Environments

    Oct 22, 2026Kaiyao Liao, Qingfeng Li, Chen Chen +3Indoor Robot NavigationSemantic Mapping

  10. In PRAISE of Attributes: Grounding Retrieval Geometry with Query-Conditioned Subspaces for Person Re-Identification

    Oct 20, 2026Rajarshi Bhattacharya, Aryan Shukla, Shakeeb Murtaza +4Person Re-IdentificationVision-Language Retrieval

  11. VTrajEmbed: Aligning Text with Video Object Trajectories via Spatiotemporal Embeddings

    Oct 16, 2026Ruizhi Chen, Zining Fan, Yudi Guo +5Multimodal EmbeddingVision-Language Retrieval

  12. Stuck on Shuffle: On Attribute-Object Binding in Vision-Language Models

    Oct 15, 2026Netanel Y. Tamir, Michael Green, Issar Tzachor +4Vision-Language RetrievalMultimodal Embedding

  13. Flow-CLIP: Image-Conditioned Residual Scoring for CompositionalImage-Text Matching

    Oct 15, 2026Minghong Wei, Enguang Zhu, Pu Cao +2Vision-Language AlignmentCross-Modal Feature Matching

  14. SPELUNKA: A Framework for Finding Unanticipated Associations in Vision-Language Models

    Oct 13, 2026Cassandra Parent, Isha Agarwal, Kumail Alhamoud +4VLM EvaluationVision-Language Retrieval

  15. Token-Budgeted Candidate Retrieval for 3D Scene-Grounded VLMs: Category Names vs. Pairwise Geometry

    Oct 9, 2026Michał Zakrzewski, Mariia Shpir, Taras RumezhakVision-Language Retrieval3D VLMs

  16. VEDJE: Video-Efficient Discriminative Joint Encoder for Scalable Video-Text Retrieval

    Oct 8, 2026Shahaf Wagner, Gabriele Serussi, Dan Ben Ami +2Video-Text RetrievalVideo Retrieval

  17. SoccerNet-FoulRet: Retrieving Semantically Similar Soccer Foul Videos

    Oct 7, 2026Jacobus Arthur, Ahmad Sait, Batool Hani +6Video RetrievalSports Video Analysis

  18. Enhancing Long-Video VLM Embeddings with Query-Aware Streaming Latent Reasoning

    Oct 4, 2026Haozhe Chi, Song Jin, Yang Jin +1Multimodal EmbeddingVision-Language Retrieval

  19. AMBER: Multi-View Adaptive Budget Allocation for Listwise Vision-Language Reranking

    Oct 2, 2026Wenteng Chen, Jiachen Zhu, Rong Shan +10Multimodal RerankingVision-Language Retrieval

  20. AiSearch: Interactive Multi-Modal Search with VLMs

    Oct 1, 2026Ali Koksal, Mei Chee Leong, Vicky Sintunata +2Multimodal IRVision-Language Models

  21. LazySloth: Bounded LLM-based Lazy Tree Search for Fast Long Video Comprehension

    Sep 29, 2026Arka Mukherjee, Kaleen Shrestha, Larissa Zhu +1Efficient VLM InferenceLong-Video Understanding

  22. Concepts Complement Dense Semantics: Learning Compact Sparse Spaces for Text-Image Retrieval

    Sep 26, 2026Yoonseo Kim, Jungwoo Choi, Cheonyoung Park +3Cross-Modal RetrievalVision-Language Retrieval

  23. Kernel-Based Steering of CLIP with Vision-Language Model Preferences

    Sep 26, 2026Sajjad Ghiasvand, Haniyeh Ehsani Oskouie, Sina Mansouri +3VLM AdaptationVisual Representation Learning

  24. MINER: Multi-crop INference-time Enhancement for Rare-Object Retrieval with Frozen Dual Encoders

    Sep 22, 2026Abdulmalik Alquwayfili, Faisal AlMeshal, Jumanah Almajnouni +2Vision-Language RetrievalImage Retrieval

  25. Selective Commitment for Language-Guided Object Retrieval under Partial Observability

    Sep 19, 2026Wonhee Koh, Sushil Samuel Dinesh, Hansol Ko +2Vision-Language RetrievalActive Vision for Robot Manipulation

  26. Human-Grounded Calibration for Long-Text Image-Text Congruence in Vision-Language Models

    Sep 14, 2026Alessandro Gambetti, Qiwei HanText-Image AlignmentVision-Language Retrieval