查看2022年综述文献点这里↘️ 2022-CV-Surveys
2023 年,计算机视觉相关综述。包括目标检测、跟踪........
📗📗📗在【我爱计算机视觉】微信公众号后台回复“CV综述”,即可收到本文列出的全部论文的打包下载。至2月15日已公开 42 篇。
1月份20篇。
- Advanced Data Augmentation Approaches: A Comprehensive Survey and Future directions
[2023-01-10]
⭐code - Data Distillation: A Survey
- Towards Label-Efficient Incremental Learning: A Survey
[2023-02-02]
⭐code - 类增量学习
- Deep Class-Incremental Learning: A Survey
[2023-02-08]
⭐code
- Deep Class-Incremental Learning: A Survey
- 机器人
- 知识蒸馏
- 目标检测
- 异常检测
- A Survey on Efficient Training of Transformers
[2023-02-03]
- A Comprehensive Review of Modern Object Segmentation Approaches
[2023-01-19] - Semantic Image Segmentation: Two Decades of Research
[2023-02-15] - 人体解析
- Deep Learning for Human Parsing: A Survey
[2023-01-31]
- Deep Learning for Human Parsing: A Survey
- 三维重建
- 表面重建
- A Survey on Human Action Recognition
[2023-01-18] - Transformers in Action Recognition: A Review on Temporal Modeling
[2023-02-06]
- Comprehensive Literature Survey on Deep Learning used in Image Memorability Prediction and Modification
[2023-01-18]
- Deepfake检测
- A Survey of Feature detection methods for localisation of plain sections of Axial Brain Magnetic Resonance Imaging
[2023-02-09] - 医学影像分析
- 脑微出血检测
- 生物医学重建
- Biomedical Image Reconstruction: A Survey
[2023-01-30]
- Biomedical Image Reconstruction: A Survey
- 果实成熟度分类
- Fruit Ripeness Classification: a Survey
[2023-01-02]
- Fruit Ripeness Classification: a Survey
- 去噪
- 去模糊
- A survey on facial image deblurring
[2023-02-13]
- A survey on facial image deblurring
- VAD
- Skeletal Video Anomaly Detection using Deep Learning: Survey, Challenges and Future Directions
[2023-01-03]
对使用从视频中提取的骨架的隐私保护型深度学习异常检测方法进行了调查 - Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Models
[2023-02-13]
- Skeletal Video Anomaly Detection using Deep Learning: Survey, Challenges and Future Directions
- 视频错误信息检测
- Online Misinformation Video Detection: A Survey
[2023-02-08]
⭐code
- Online Misinformation Video Detection: A Survey
- 域适应
- Source-Free Unsupervised Domain Adaptation: A Survey
[2023-01-03]
从技术角度对现有的SFUDA方法进行了系统的文献回顾。具体来说,将目前的SFUDA研究分为两类,即白盒SFUDA和黑盒SFUDA,并根据它们使用的不同学习策略进一步划分为更细的子类别。以及研究了每个子类别中方法的挑战,讨论了白盒和黑盒SFUDA方法的优势/劣势,总结了常用的基准数据集,另外还总结了在不使用源数据的情况下提高模型通用性的流行技术。
- Source-Free Unsupervised Domain Adaptation: A Survey
- 人体解析
- 手势合成
- 动作识别与姿势估计
- 体育
- A survey on Organoid Image Analysis Platforms
[2023-01-09] - A Survey of Explainable AI in Deep Visual Modeling: Methods and Metrics
[2023-02-01] - Deep Learning for Time Series Classification and Extrinsic Regression: A Current Survey
[2023-02-07] - 上下文理解
- Context Understanding in Computer Vision: A Survey
[2023-02-13]
⭐[code]
- Context Understanding in Computer Vision: A Survey