数据集与基准论文趋势 2023–2026

新数据集与评测协议

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 5,856 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

数据集与基准论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
2023227162166382937
20244482163183641,346
20256374191893371,582
20266236352754581,991

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

全部数据集与基准论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 1,537 篇，第 29 / 31 页

  1. CVPR 2023Nighttime Smartphone Reflective Flare Removal Using Optical Center Symmetry Prior
  2. CVPR 2023NIKI: Neural Inverse Kinematics With Invertible Neural Networks for 3D Human Pose and Shape Estimation
  3. CVPR 2023No One Left Behind: Improving the Worst Categories in Long-Tailed Learning
  4. CVPR 2023Noisy Correspondence Learning With Meta Similarity Correction
  5. CVPR 2023Objaverse: A Universe of Annotated 3D Objects
  6. CVPR 2023Object Pose Estimation With Statistical Guarantees: Conformal Keypoint Detection and Geometric Uncertainty Propagation
  7. CVPR 2023Occlusion-Free Scene Recovery via Neural Radiance Fields
  8. CVPR 2023OCELOT: Overlapped Cell on Tissue Dataset for Histopathology
  9. CVPR 2023Octree Guided Unoriented Surface Reconstruction
  10. CVPR 2023Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild
  11. CVPR 2023OmniCity: Omnipotent City Understanding With Multi-Level and Multi-View Images
  12. CVPR 2023OmniMAE: Single Model Masked Pretraining on Images and Videos
  13. CVPR 2023Omnimatte3D: Associating Objects and Their Effects in Unconstrained Monocular Video
  14. CVPR 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation
  15. CVPR 2023On Calibrating Semantic Segmentation Models: Analyses and an Algorithm
  16. CVPR 2023On the Benefits of 3D Pose and Tracking for Human Action Recognition
  17. CVPR 2023On the Effectiveness of Partial Variance Reduction in Federated Learning With Heterogeneous Data
  18. CVPR 2023On the Effects of Self-Supervision and Contrastive Alignment in Deep Multi-View Clustering
  19. CVPR 2023On the Stability-Plasticity Dilemma of Class-Incremental Learning
  20. CVPR 2023OpenGait: Revisiting Gait Recognition Towards Better Practicality
  21. CVPR 2023Overlooked Factors in Concept-Based Explanations: Dataset Choice, Concept Learnability, and Human Capability
  22. CVPR 2023PACO: Parts and Attributes of Common Objects
  23. CVPR 2023PAniC-3D: Stylized Single-View 3D Reconstruction From Portraits of Anime Characters
  24. CVPR 2023PartDistillation: Learning Parts From Instance Segmentation
  25. CVPR 2023Partial Network Cloning
  26. CVPR 2023Parts2Words: Learning Joint Embedding of Point Clouds and Texts by Bidirectional Matching Between Parts and Words
  27. CVPR 2023PET-NeuS: Positional Encoding Tri-Planes for Neural Surfaces
  28. CVPR 2023PIRLNav: Pretraining With Imitation and RL Finetuning for ObjectNav
  29. CVPR 2023Pixels, Regions, and Objects: Multiple Enhancement for Salient Object Detection
  30. CVPR 2023PlenVDB: Memory Efficient VDB-Based Radiance Fields for Fast Training and Rendering
  31. CVPR 2023Point2Pix: Photo-Realistic Point Cloud Rendering via Neural Radiance Fields
  32. CVPR 2023Polynomial Implicit Neural Representations for Large Diverse Datasets
  33. CVPR 2023PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation
  34. CVPR 2023Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation
  35. CVPR 2023PosterLayout: A New Benchmark and Approach for Content-Aware Visual-Textual Presentation Layout
  36. CVPR 2023Power Bundle Adjustment for Large-Scale 3D Reconstruction
  37. CVPR 2023Prefix Conditioning Unifies Language and Label Supervision
  38. CVPR 2023Progressive Transformation Learning for Leveraging Virtual Images in Training
  39. CVPR 2023Propagate and Calibrate: Real-Time Passive Non-Line-of-Sight Tracking
  40. CVPR 2023ProtoCon: Pseudo-Label Refinement via Online Clustering and Prototypical Consistency for Efficient Semi-Supervised Learning
  41. CVPR 2023ProxyFormer: Proxy Alignment Assisted Point Cloud Completion With Missing Part Sensitive Transformer
  42. CVPR 2023PSVT: End-to-End Multi-Person 3D Pose and Shape Estimation With Progressive Video Transformers
  43. CVPR 2023RankMix: Data Augmentation for Weakly Supervised Learning of Classifying Whole Slide Images With Diverse Sizes and Imbalanced Categories
  44. CVPR 2023Rate Gradient Approximation Attack Threats Deep Spiking Neural Networks
  45. CVPR 2023Re-Basin via Implicit Sinkhorn Differentiation
  46. CVPR 2023Real-Time Evaluation in Online Continual Learning: A New Hope
  47. CVPR 2023REC-MV: REconstructing 3D Dynamic Cloth From Monocular Videos
  48. CVPR 2023Recognizability Embedding Enhancement for Very Low-Resolution Face Recognition and Quality Estimation
  49. CVPR 2023Recognizing Rigid Patterns of Unlabeled Point Clouds by Complete and Continuous Isometry Invariants With No False Negatives and No False Positives
  50. CVPR 2023Recovering 3D Hand Mesh Sequence From a Single Blurry Image: A New Dataset and Temporal Unfolding

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查数据集与基准在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "dataset-and-benchmarks"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

常见问题

2023–2026 年四大会议一共有多少篇数据集与基准论文？
共 5,856 篇，按年份分别是 2023 年 937 篇、2024 年 1,346 篇、2025 年 1,582 篇、2026 年 1,991 篇。
NeurIPS 2026 有多少篇数据集与基准论文？
NeurIPS 2026 有 623 篇数据集与基准论文，上一届是 637 篇。
ICLR 2026 有多少篇数据集与基准论文？
ICLR 2026 有 635 篇数据集与基准论文，上一届是 419 篇。
ICML 2026 有多少篇数据集与基准论文？
ICML 2026 有 275 篇数据集与基准论文，上一届是 189 篇。
CVPR 2026 有多少篇数据集与基准论文？
CVPR 2026 有 458 篇数据集与基准论文，上一届是 337 篇。
哪个会议的数据集与基准论文最多？
NeurIPS，2023–2026 年共 1,935 篇。

「效率与系统」下的其他主题