目标检测论文趋势 2023–2026

主要结论

• 目标检测论文从 2023 年的 485 篇增长到 2026 年的 681 篇，三年间扩大到约 1.4 倍。
• CVPR 是发目标检测论文最多的会议，2023–2026 年共 1,110 篇，占四个会议总量的 40%。
• 交叉方向里涨得最快的是扩散模型：同时属于两个主题的论文从 2023 年的 11 篇增至 2026 年的 39 篇。
• 在「计算机视觉」的 5 个主题里，它的 2026 年论文数排第 4；同组增长最快的视频理解是 2.6 倍，目标检测是 1.4 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 2026A Systematic Analysis of Out-of-Distribution Detection Under Representation and Training Paradigm Shifts
• ICML 2026BPL: Generalizable Deepfake Detection via Bias-only Pair-aware Learning
• ICLR 2026CGSA: Class-Guided Slot-Aware Adaptation for Source-Free Object Detections
• CVPR 20263D-Object Perception Transformer 3PT
• NeurIPS 2025AdaDetectGPT: Adaptive Detection of LLM-Generated Text with Statistical Guarantees
• ICML 2025A Variational Information Theoretic Approach to Out-of-Distribution Detection
• ICLR 2025A Statistical Approach for Controlled Training Data Detection
• CVPR 2025A Distractor-Aware Memory for Visual Object Tracking with SAM2
• NeurIPS 2024$SE(3)$ Equivariant Ray Embeddings for Implicit Multi-View Depth Estimation
• ICML 2024Contamination-Resilient Anomaly Detection via Adversarial Learning on Partially-Observed Normal and Anomalous Data
• ICLR 2024Boosting Graph Anomaly Detection with Adaptive Message Passing
• CVPR 2024DeconfuseTrack: Dealing with Confusion for Multi-Object Tracking
• NeurIPS 20233D Copy-Paste: Physically Plausible Object Insertion for Monocular 3D Detection
• ICML 2023Accelerated Infeasibility Detection of Constrained Optimization and Fixed-Point Iterations
• ICLR 2023A framework for benchmarking Class-out-of-distribution detection and its application to ImageNet
• CVPR 20232PCNet: Two-Phase Consistency Training for Day-to-Night Unsupervised Domain Adaptive Object Detection
• NeurIPS 2026Auditing Attention Head Masking for Out-of-Distribution Detection: Cross-Architecture Wins, Failures, and Polarity Inversions
• ICML 2026Causal-aware Anomaly Detection for Tabular Data
• ICLR 2026DETR-ViP: Detection Transformer with Robust Discriminative Visual Prompts
• CVPR 2026A Closer Look at Cross-Domain Few-Shot Object Detection Fine-Tuning Matters

全部目标检测论文

共 667 篇，第 2 / 14 页

51. NeurIPS 2024Are nuclear masks all you need for improved out-of-domain generalisation? A closer look at cancer classification in histopathology
52. NeurIPS 2024Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage?
53. NeurIPS 2024Are We on the Right Way for Evaluating Large Vision-Language Models?
54. NeurIPS 2024Artemis: Towards Referential Understanding in Complex Videos
55. NeurIPS 2024Articulate your NeRF: Unsupervised articulated object modeling via conditional view synthesis
56. NeurIPS 2024Assembly Fuzzy Representation on Hypergraph for Open-Set 3D Object Retrieval
57. NeurIPS 2024Attention Temperature Matters in ViT-Based Cross-Domain Few-Shot Learning
58. NeurIPS 2024AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation
59. NeurIPS 2024Automated Label Unification for Multi-Dataset Semantic Segmentation with GNNs
60. NeurIPS 2024Automated Multi-level Preference for MLLMs
61. NeurIPS 2024AverNet: All-in-one Video Restoration for Time-varying Unknown Degradations
62. NeurIPS 2024AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation
63. NeurIPS 2024Be Confident in What You Know: Bayesian Parameter Efficient Fine-Tuning of Vision Foundation Models
64. NeurIPS 2024Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks
65. NeurIPS 2024BetterDepth: Plug-and-Play Diffusion Refiner for Zero-Shot Monocular Depth Estimation
66. NeurIPS 2024Beyond Accuracy: Tracking more like Human via Visual Search
67. NeurIPS 2024Beyond Euclidean: Dual-Space Representation Learning for Weakly Supervised Video Violence Detection
68. NeurIPS 2024Bias Detection via Signaling
69. NeurIPS 2024Binarized Diffusion Model for Image Super-Resolution
70. NeurIPS 2024Binocular-Guided 3D Gaussian Splatting with View Consistency for Sparse View Synthesis
71. NeurIPS 2024BiScope: AI-generated Text Detection by Checking Memorization of Preceding Tokens
72. NeurIPS 2024bit2bit: 1-bit quanta video reconstruction via self-supervised photon prediction
73. NeurIPS 2024Black-Box Forgetting
74. NeurIPS 2024Blind Image Restoration via Fast Diffusion Inversion
75. NeurIPS 2024BoostAdapter: Improving Vision-Language Test-Time Adaptation via Regional Bootstrapping
76. NeurIPS 2024Boosting Semi-Supervised Scene Text Recognition via Viewing and Summarizing
77. NeurIPS 2024Boosting Vision-Language Models with Transduction
78. NeurIPS 2024Boosting Weakly Supervised Referring Image Segmentation via Progressive Comprehension
79. NeurIPS 2024Bootstrapping Top-down Information for Self-modulating Slot Attention
80. NeurIPS 2024Bridge the Modality and Capability Gaps in Vision-Language Model Selection
81. NeurIPS 2024Bridge the Points: Graph-based Few-shot Segment Anything Semantically
82. NeurIPS 2024Bridging Gaps: Federated Multi-View Clustering in Heterogeneous Hybrid Views
83. NeurIPS 2024Bridging OOD Detection and Generalization: A Graph-Theoretic View
84. NeurIPS 2024BuckTales: A multi-UAV dataset for multi-object tracking and re-identification of wild antelopes
85. NeurIPS 2024CALVIN: Improved Contextual Video Captioning via Instruction Tuning
86. NeurIPS 2024Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs
87. NeurIPS 2024Can We Leave Deepfake Data Behind in Training Deepfake Detector?
88. NeurIPS 2024CaptainCook4D: A Dataset for Understanding Errors in Procedural Activities
89. NeurIPS 2024Capturing the denoising effect of PCA via compression ratio
90. NeurIPS 2024Causal Context Adjustment Loss for Learned Image Compression
91. NeurIPS 2024CemiFace: Center-based Semi-hard Synthetic Face Generation for Face Recognition
92. NeurIPS 2024CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition
93. NeurIPS 2024Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers
94. NeurIPS 2024ChatCam: Empowering Camera Control through Conversational AI
95. NeurIPS 2024ChatTracker: Enhancing Visual Tracking Performance via Chatting with Multimodal Large Language Model
96. NeurIPS 2024CIFD: Controlled Information Flow to Enhance Knowledge Distillation
97. NeurIPS 2024CigTime: Corrective Instruction Generation Through Inverse Motion Editing
98. NeurIPS 2024CLAP4CLIP: Continual Learning with Probabilistic Finetuning for Vision-Language Models
99. NeurIPS 2024CLIP in Mirror: Disentangling text from visual images through reflection
100. NeurIPS 2024CLIPAway: Harmonizing focused embeddings for removing objects via diffusion models

常见问题

2023–2026 年四大会议一共有多少篇目标检测论文？

共 2,809 篇，按年份分别是 2023 年 485 篇、2024 年 1,072 篇、2025 年 571 篇、2026 年 681 篇。

NeurIPS 2026 有多少篇目标检测论文？

NeurIPS 2026 有 179 篇目标检测论文，上一届是 175 篇。

ICLR 2026 有多少篇目标检测论文？

ICLR 2026 有 95 篇目标检测论文，上一届是 85 篇。

ICML 2026 有多少篇目标检测论文？

ICML 2026 有 121 篇目标检测论文，上一届是 57 篇。

CVPR 2026 有多少篇目标检测论文？

CVPR 2026 有 286 篇目标检测论文，上一届是 254 篇。

哪个会议的目标检测论文最多？

CVPR，2023–2026 年共 1,110 篇。