稠密检索论文趋势 2023–2026

主要结论

• 稠密检索论文从 2023 年的 60 篇增长到 2026 年的 162 篇，三年间扩大到约 2.7 倍。
• CVPR 是发稠密检索论文最多的会议，2023–2026 年共 147 篇，占四个会议总量的 37%。
• 交叉方向里涨得最快的是检索记忆：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 21 篇。
• 在「信息检索」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的交叉编码重排是 3.0 倍，稠密检索是 2.7 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• NeurIPS 2026Half-Truths Break Similarity-Based Retrieval
• ICML 2026Deep Discriminative Structure Proxy Hashing for Cross-modal Retrieval
• ICLR 2026A Dense Subset Index for Collective Query Coverage
• CVPR 2026Beyond Caption-Based Queries in Video Moment Retrieval
• NeurIPS 2025Dense Associative Memory with Epanechnikov Energy
• ICML 2025Nonparametric Modern Hopfield Models
• ICLR 2025Contextual Document Embeddings
• CVPR 2025Adapting Dense Matching for Homography Estimation with Grid-based Acceleration
• NeurIPS 2024CARE: a Benchmark Suite for the Classification and Retrieval of Enzymes
• ICML 2024Compute Better Spent: Replacing Dense Layers with Structured Matrices
• ICLR 2024Adaptive Retrieval and Scalable Indexing for k-NN Search with Cross-Encoders
• CVPR 2024Dense Optical Tracking: Connecting the Dots
• NeurIPS 2023Bypassing spike sorting: Density-based decoding using spike localization from dense multielectrode probes
• ICML 2023Everyone's Preference Changes Differently: A Weighted Multi-Interest Model For Retrieval
• ICLR 2023Automating Nearest Neighbor Search Configuration with Constrained Optimization
• CVPR 2023Are Binary Annotations Sufficient? Video Moment Retrieval via Hierarchical Uncertainty-Based Active Learning
• NeurIPS 2026Hyperparameter Transfer for Dense Associative Memories
• ICML 2026Dense associative memory for Gaussian distributions
• ICLR 2026Beyond Instance-Level Alignment: Dual-Level Optimal Transport for Audio-Text Retrieval
• CVPR 2026Beyond Tie Points Satellite Image Block Adjustment based on Dense

全部稠密检索论文

共 60 篇，第 1 / 2 页

1. CVPR 20231% VS 100%: Parameter-Efficient Low Rank Adapter for Dense Predictions
2. CVPR 2023Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection
3. CVPR 2023Are Binary Annotations Sufficient? Video Moment Retrieval via Hierarchical Uncertainty-Based Active Learning
4. CVPR 2023CrOC: Cross-View Online Clustering for Dense Visual Representation Learning
5. CVPR 2023Data-Free Sketch-Based Image Retrieval
6. CVPR 2023DC2: Dual-Camera Defocus Control by Learning To Refocus
7. CVPR 2023DejaVu: Conditional Regenerative Learning To Enhance Dense Prediction
8. CVPR 2023Dense Distinct Query for End-to-End Object Detection
9. CVPR 2023Dense Network Expansion for Class Incremental Learning
10. CVPR 2023Detecting Backdoors in Pre-Trained Encoders
11. CVPR 2023DKM: Dense Kernelized Feature Matching for Geometry Estimation
12. CVPR 2023DPF: Learning Dense Prediction Fields With Weak Supervision
13. CVPR 2023DSFNet: Dual Space Fusion Network for Occlusion-Robust 3D Dense Face Alignment
14. CVPR 2023Dual Alignment Unsupervised Domain Adaptation for Video-Text Retrieval
15. CVPR 2023End-to-End 3D Dense Captioning With Vote2Cap-DETR
16. CVPR 2023ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fields
17. CVPR 2023Event-Guided Person Re-Identification via Sparse-Dense Complementary Learning
18. CVPR 2023Fast Monocular Scene Reconstruction With Global-Sparse Local-Dense Grids
19. CVPR 2023Hierarchical Dense Correlation Distillation for Few-Shot Segmentation
20. CVPR 2023Hierarchical Video-Moment Retrieval and Step-Captioning
21. CVPR 2023Improving Cross-Modal Retrieval With Set of Diverse Embeddings
22. CVPR 2023Learning Multi-Modal Class-Specific Tokens for Weakly Supervised Dense Object Localization
23. CVPR 2023Learning To Detect Mirrors From Videos via Dual Correspondences
24. CVPR 2023One-to-Few Label Assignment for End-to-End Dense Detection
25. CVPR 2023Open-Set Fine-Grained Retrieval via Prompting Vision-Language Evaluator
26. CVPR 2023Pix2map: Cross-Modal Retrieval for Inferring Street Maps From Images
27. CVPR 2023Probabilistic Prompt Learning for Dense Prediction
28. CVPR 2023R2Former: Unified Retrieval and Reranking Transformer for Place Recognition
29. CVPR 2023Revisiting Self-Similarity: Structural Embedding for Image Retrieval
30. CVPR 2023RONO: Robust Discriminative Learning With Noisy Labels for 2D-3D Cross-Modal Retrieval
31. CVPR 2023SmallCap: Lightweight Image Captioning Prompted With Retrieval Augmentation
32. CVPR 2023Unsupervised 3D Shape Reconstruction by Part Retrieval and Assembly
33. CVPR 2023ViLEM: Visual-Language Error Modeling for Image-Text Retrieval
34. CVPR 2023Zero-Shot Dual-Lens Super-Resolution
35. ICLR 2023Accurate Image Restoration with Attention Retractable Transformer
36. ICLR 2023Automating Nearest Neighbor Search Configuration with Constrained Optimization
37. ICLR 2023DENSE RGB SLAM WITH NEURAL IMPLICIT MAPS
38. ICLR 2023Modeling Sequential Sentence Relation to Improve Cross-lingual Dense Retrieval
39. ICLR 2023Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation Learning
40. ICLR 2023Promptagator: Few-shot Dense Retrieval From 8 Examples
41. ICLR 2023Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints
42. ICLR 2023Sparsity-Constrained Optimal Transport
43. ICLR 2023Treeformer: Dense Gradient Trees for Efficient Attention Computation
44. ICLR 2023Unicom: Universal and Compact Representation Learning for Image Retrieval
45. ICLR 2023Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matching
46. ICLR 2023Universal Vision-Language Dense Retrieval: Learning A Unified Representation Space for Multi-Modal Retrieval
47. ICML 2023Everyone's Preference Changes Differently: A Weighted Multi-Interest Model For Retrieval
48. ICML 2023IncDSI: Incrementally Updatable Document Retrieval
49. ICML 2023Learning Dense Correspondences between Photos and Sketches
50. ICML 2023Pre-computed memory or on-the-fly encoding? A hybrid approach to retrieval augmentation makes the most of your compute

常见问题

2023–2026 年四大会议一共有多少篇稠密检索论文？

共 401 篇，按年份分别是 2023 年 60 篇、2024 年 92 篇、2025 年 87 篇、2026 年 162 篇。

NeurIPS 2026 有多少篇稠密检索论文？

NeurIPS 2026 有 51 篇稠密检索论文，上一届是 35 篇。

ICLR 2026 有多少篇稠密检索论文？

ICLR 2026 有 26 篇稠密检索论文，上一届是 12 篇。

ICML 2026 有多少篇稠密检索论文？

ICML 2026 有 35 篇稠密检索论文，上一届是 10 篇。

CVPR 2026 有多少篇稠密检索论文？

CVPR 2026 有 50 篇稠密检索论文，上一届是 30 篇。

哪个会议的稠密检索论文最多？

CVPR，2023–2026 年共 147 篇。