应用 · computer vision论文趋势 2023–2026

应用方向：computer_vision

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 2,538 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

应用 · computer vision论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
20233420844106
2024891522568334
202516533820168772
2026168538554661,326

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

全部应用 · computer vision论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 2,538 篇，第 36 / 51 页

  1. ICML 2025Beyond Confidence: Exploiting Homogeneous Pattern for Semi-Supervised Semantic Segmentation
  2. ICML 2025Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts
  3. ICML 2025Beyond Entropy: Region Confidence Proxy for Wild Test-Time Adaptation
  4. ICML 2025Beyond Low-rank Decomposition: A Shortcut Approach for Efficient On-Device Learning
  5. ICML 2025BiMaCoSR: Binary One-Step Diffusion Model Leveraging Flexible Matrix Compression for Real Super-Resolution
  6. ICML 2025Boosting Adversarial Robustness with CLAT: Criticality Leveraged Adversarial Training
  7. ICML 2025Boosting Virtual Agent Learning and Reasoning: A Step-Wise, Multi-Dimensional, and Generalist Reward Model with Benchmark
  8. ICML 2025Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing
  9. ICML 2025CAD-Editor: A Locate-then-Infill Framework with Automated Training Data Synthesis for Text-Based CAD Editing
  10. ICML 2025Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attention
  11. ICML 2025CoCoA-Mix: Confusion-and-Confidence-Aware Mixture Model for Context Optimization
  12. ICML 2025Complex Wavelet Mutual Information Loss: A Multi-Scale Loss Function for Semantic Segmentation
  13. ICML 2025Componential Prompt-Knowledge Alignment for Domain Incremental Learning
  14. ICML 2025ConText: Driving In-context Learning for Text Removal and Segmentation
  15. ICML 2025Continual Generalized Category Discovery: Learning and Forgetting from a Bayesian Perspective
  16. ICML 2025Contour Integration Underlies Human-Like Vision
  17. ICML 2025Contrastive Visual Data Augmentation
  18. ICML 2025Control and Realism: Best of Both Worlds in Layout-to-Image without Training
  19. ICML 2025CostFilter-AD: Enhancing Anomaly Detection through Matching Cost Filtering
  20. ICML 2025Cradle: Empowering Foundation Agents towards General Computer Control
  21. ICML 2025CSV-Occ: Fusing Multi-frame Alignment for Occupancy Prediction with Temporal Cross State Space Model and Central Voting Mechanism
  22. ICML 2025CUPS: Improving Human Pose-Shape Estimators with Conformalized Deep Uncertainty
  23. ICML 2025DAMA: Data- and Model-aware Alignment of Multi-modal LLMs
  24. ICML 2025David and Goliath: Small One-step Model Beats Large Diffusion with Score Post-training
  25. ICML 2025DCBM: Data-Efficient Visual Concept Bottleneck Models
  26. ICML 2025Decomposition of Graphic Design with Unified Multimodal Model
  27. ICML 2025Demystifying Catastrophic Forgetting in Two-Stage Incremental Object Detector
  28. ICML 2025Diff-MoE: Diffusion Transformer with Time-Aware and Space-Adaptive Experts
  29. ICML 2025Divide and Conquer: Exploring Language-centric Tree Reasoning for Video Question-Answering
  30. ICML 2025Do Multiple Instance Learning Models Transfer?
  31. ICML 2025DocVXQA: Context-Aware Visual Explanations for Document Question Answering
  32. ICML 2025DragLoRA: Online Optimization of LoRA Adapters for Drag-based Image Editing in Diffusion Model
  33. ICML 2025DreamDPO: Aligning Text-to-3D Generation with Human Preferences via Direct Preference Optimization
  34. ICML 2025DVI:A Derivative-based Vision Network for INR
  35. ICML 2025DyPolySeg: Taylor Series-Inspired Dynamic Polynomial Fitting Network for Few-shot Point Cloud Semantic Segmentation
  36. ICML 2025EcoMapper: Generative Modeling for Climate-Aware Satellite Imagery
  37. ICML 2025EFDTR: Learnable Elliptical Fourier Descriptor Transformer for Instance Segmentation
  38. ICML 2025Efficient and Separate Authentication Image Steganography Network
  39. ICML 2025Efficient Motion Prompt Learning for Robust Visual Tracking
  40. ICML 2025Efficient Multi-modal Long Context Learning for Training-free Adaptation
  41. ICML 2025Efficient Noise Calculation in Deep Learning-based MRI Reconstructions
  42. ICML 2025Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias
  43. ICML 2025Elucidating the design space of language models for image generation
  44. ICML 2025Enhancing Foundation Models with Federated Domain Knowledge Infusion
  45. ICML 2025Enhancing Performance of Explainable AI Models with Constrained Concept Refinement
  46. ICML 2025Enhancing Visual Localization with Cross-Domain Image Generation
  47. ICML 2025Event-Customized Image Generation
  48. ICML 2025EvFocus: Learning to Reconstruct Sharp Images from Out-of-Focus Event Streams
  49. ICML 2025Ex-VAD: Explainable Fine-grained Video Anomaly Detection Based on Visual-Language Models
  50. ICML 2025Exploring Invariance in Images through One-way Wave Equations

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 查应用 · computer vision在 ICLR 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": "app-computer-vision"}

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应用 · computer vision论文？
共 2,538 篇，按年份分别是 2023 年 106 篇、2024 年 334 篇、2025 年 772 篇、2026 年 1,326 篇。
NeurIPS 2026 有多少篇应用 · computer vision论文？
NeurIPS 2026 有 168 篇应用 · computer vision论文，上一届是 165 篇。
ICLR 2026 有多少篇应用 · computer vision论文？
ICLR 2026 有 538 篇应用 · computer vision论文，上一届是 338 篇。
ICML 2026 有多少篇应用 · computer vision论文？
ICML 2026 有 554 篇应用 · computer vision论文，上一届是 201 篇。
CVPR 2026 有多少篇应用 · computer vision论文？
CVPR 2026 有 66 篇应用 · computer vision论文，上一届是 68 篇。
哪个会议的应用 · computer vision论文最多？
ICLR，2023–2026 年共 1,048 篇。

「应用领域」下的其他主题