A paper list of some recent Transformer-based CV works. If you find some ignored papers, please open issues or pull requests.
!!The latest version has been updated, and you can click on the following links to view the list of papers and the codes (if available). The old version is 20240323.
**Last updated: 2024/12/23
- Survey
- Recent Papers
- Action
- Active Learning
- Adversarial Attacks
- Anomaly Detection
- Assessment
- Augmentation
- Audio
- Bird's-Eye-View
- Captioning
- Change Detection
- Classification (Backbone)
- Clustering
- Completion
- Compression
- Cross-view
- Crowd
- Deblurring
- Depth
- Deepfake Detection
- Dehazing
- Deraining
- Denoising
- Detection
- Diffusion
- Edge
- Enhancement
- Face
- Federated Learning
- Few-shot Learning
- Fusion
- Gait
- Gaze
- Generative Model
- Graph
- Hand Gesture
- High Dynamic Range Imaging
- HOI
- Hyperspectral
- Illumination
- Incremental Learning
- In-painting
- Instance Segmentation
- Knowledge Distillation
- Lane
- Layout
- Lighting
- LLM
- Matching
- Matting
- Medical
- Mesh
- Metric learning
- Motion
- Multi-label
- Multi-task/modal
- Multi-view Stereo
- NAS
- Navigation
- Neural Rendering
- OCR
- Octree
- Open World
- Optical Flow
- Panoptic Segmentation
- Point Cloud
- Pose
- Planning
- Pruning & Quantization
- Recognition
- Reconstruction
- Referring
- Registration
- Re-identification
- Remote Sensing
- Restoration
- Retrieval
- Robotic
- Salient Detection
- Scene
- Self-supervised Learning
- Semantic Segmentation
- Shape
- SLAM
- SNN
- Style Transfer
- Super-Resolution
- Synthesis
- Text-to-Image/Video
- Texture
- Time Series
- Tracking
- Traffic
- Transfer learning
- Translation
- Unsupervised learning
- UAV
- Video
- Visual Grounding
- Visual Question Answering
- Visual Reasoning
- Visual Relationship Detection
- Voxel
- Weakly Supervised Learning
- Zero-Shot Learning
- Others
- Contact & Feedback
If you have any suggestions about this project, feel free to contact me.
- [e-mail: yzhangcst[at]gmail.com]