视听学习论文趋势 2023–2026

音视频联合建模

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 790 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

视听学习论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202348201278158
202433192088160
202556301094190
2026693932142282

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

全部视听学习论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 401 篇，第 8 / 9 页

  1. CVPR 2023Images Speak in Images: A Generalist Painter for In-Context Visual Learning
  2. CVPR 2023Improving Selective Visual Question Answering by Learning From Your Peers
  3. CVPR 2023Improving Table Structure Recognition With Visual-Alignment Sequential Coordinate Modeling
  4. CVPR 2023Improving Visual Grounding by Encouraging Consistent Gradient-Based Explanations
  5. CVPR 2023iQuery: Instruments As Queries for Audio-Visual Sound Separation
  6. CVPR 2023Joint Visual Grounding and Tracking With Natural Language Specification
  7. CVPR 2023Language-Guided Audio-Visual Source Separation via Trimodal Consistency
  8. CVPR 2023Learning Audio-Visual Source Localization via False Negative Aware Contrastive Learning
  9. CVPR 2023Learning Federated Visual Prompt in Null Space for MRI Reconstruction
  10. CVPR 2023Learning Rotation-Equivariant Features for Visual Correspondence
  11. CVPR 2023Learning To Dub Movies via Hierarchical Prosody Models
  12. CVPR 2023Learning Visual Representations via Language-Guided Sampling
  13. CVPR 2023Logical Implications for Visual Question Answering Consistency
  14. CVPR 2023Long-Term Visual Localization With Mobile Sensors
  15. CVPR 2023Masked Video Distillation: Rethinking Masked Feature Modeling for Self-Supervised Video Representation Learning
  16. CVPR 2023MetaCLUE: Towards Comprehensive Visual Metaphors Research
  17. CVPR 2023Mixed Autoencoder for Self-Supervised Visual Representation Learning
  18. CVPR 2023Modeling Entities As Semantic Points for Visual Information Extraction in the Wild
  19. CVPR 2023Multimodal Prompting With Missing Modalities for Visual Recognition
  20. CVPR 2023Neural Volumetric Memory for Visual Locomotion Control
  21. CVPR 2023Object-Goal Visual Navigation via Effective Exploration of Relations Among Historical Navigation States
  22. CVPR 2023OrienterNet: Visual Localization in 2D Public Maps With Neural Matching
  23. CVPR 2023Parametric Implicit Face Representation for Audio-Driven Facial Reenactment
  24. CVPR 2023Prompting Large Language Models With Answer Heuristics for Knowledge-Based Visual Question Answering
  25. CVPR 2023PVO: Panoptic Visual Odometry
  26. CVPR 2023QuantArt: Quantizing Image Style Transfer Towards High Visual Fidelity
  27. CVPR 2023Renderable Neural Radiance Map for Visual Navigation
  28. CVPR 2023RILS: Masked Visual Reconstruction in Language Semantic Space
  29. CVPR 2023RMLVQA: A Margin Loss Approach for Visual Question Answering With Language Biases
  30. CVPR 2023Self-Supervised Video Forensics by Audio-Visual Anomaly Detection
  31. CVPR 2023SeqTrack: Sequence to Sequence Learning for Visual Object Tracking
  32. CVPR 2023Sound to Visual Scene Generation by Audio-to-Visual Latent Alignment
  33. CVPR 2023StructVPR: Distill Structural Knowledge With Weighting Samples for Visual Place Recognition
  34. CVPR 2023SynthVSR: Scaling Up Visual Speech Recognition With Synthetic Supervision
  35. CVPR 2023Text-Visual Prompting for Efficient 2D Temporal Video Grounding
  36. CVPR 2023Token Boosting for Robust Self-Supervised Visual Transformer Pre-Training
  37. CVPR 2023Top-Down Visual Attention From Analysis by Synthesis
  38. CVPR 2023Towards Effective Visual Representations for Partial-Label Learning
  39. CVPR 2023Towards Generalisable Video Moment Retrieval: Visual-Dynamic Injection to Image-Text Pre-Training
  40. CVPR 2023Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning
  41. CVPR 2023VideoTrack: Learning To Track Objects via Video Transformer
  42. CVPR 2023ViLEM: Visual-Language Error Modeling for Image-Text Retrieval
  43. CVPR 2023Vision Transformers Are Parameter-Efficient Audio-Visual Learners
  44. CVPR 2023Visual Dependency Transformers: Dependency Tree Emerges From Reversed Attention
  45. CVPR 2023Visual Localization Using Imperfect 3D Models From the Internet
  46. CVPR 2023Visual Prompt Multi-Modal Tracking
  47. CVPR 2023Visual Recognition by Request
  48. CVPR 2023Visual-Language Prompt Tuning With Knowledge-Guided Context Optimization
  49. CVPR 2023VQACL: A Novel Visual Question Answering Continual Learning Setting
  50. CVPR 2023Watch or Listen: Robust Audio-Visual Speech Recognition With Visual Corruption Modeling and Reliability Scoring

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 查视听学习在 CVPR 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": "audio-visual-learning"}

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视听学习论文？
共 790 篇，按年份分别是 2023 年 158 篇、2024 年 160 篇、2025 年 190 篇、2026 年 282 篇。
NeurIPS 2026 有多少篇视听学习论文？
NeurIPS 2026 有 69 篇视听学习论文，上一届是 56 篇。
ICLR 2026 有多少篇视听学习论文？
ICLR 2026 有 39 篇视听学习论文，上一届是 30 篇。
ICML 2026 有多少篇视听学习论文？
ICML 2026 有 32 篇视听学习论文，上一届是 10 篇。
CVPR 2026 有多少篇视听学习论文？
CVPR 2026 有 142 篇视听学习论文，上一届是 94 篇。
哪个会议的视听学习论文最多？
CVPR，2023–2026 年共 402 篇。

「语音与音频」下的其他主题