Learn new objects fast with few examples without forget old ones by hierarchical learning with HDA Fast Hierarchical Learning for...

Improve training of object segmentation with only boxes by using mask quality with BoxTeacher BoxTeacher: Exploring High-Quality Pseudo...

Get object pose with self-supervised learning on videos with self-pose Self-Supervised Geometric Correspondence for Category-Level 6D...

Better rare object recognition by balancing gradients with EFL The Equalization Losses: Gradient-Driven Training for Long-tailed Object...

Real-time dynamic 3D object segmentation including non-rigid objects without priors with STAR Scene-level Tracking and Reconstruction...

Faster and better multi-person pose estimation by using a single stage with AdaptivePose AdaptivePose++: A Powerful Single-Stage Network...

Get 3D scene in real-time from monocular images using depth uncertainty with Rosinol Probabilistic Volumetric Fusion for Dense Monocular...

Improve monocular depth estimation without labeled training data by image masking with MIMDepth Image Masking for Robust Self-Supervised...

Segment objects in new domain by unsupervised training with boxes in old domain with WUDA WUDA: Unsupervised Domain Adaptation Based on...

Improve object detection under difficult conditions by learning many image pre-processors with GDIP GDIP: Gated Differentiable Image...

Better enhancement of dim noisy images by using subspaces with RLED-Net Seeing Through The Noisy Dark: Toward Real-world Low-Light Image...

Detect object changes between images despite different viewpoint and lighting with CYWS The Change You Want to See arXiv paper abstract...

Explain an image classifier result using neural-symbolic learning with Greybox XAI Greybox XAI: a Neural-Symbolic learning framework to...

Survey of super-resolution advances including diffusion and transformers Hitchhiker's Guide to Super-Resolution: Introduction and Recent...

Survey of deep learning for high-resolution computer vision Efficient High-Resolution Deep Learning: A Survey arXiv paper abstract...

Survey of crowd counting with computer vision Revisiting Crowd Counting: State-of-the-art, Trends, and Future Perspectives arXiv paper...

Video correspondence by self-supervised learning with less cost by using spatial then time with Li Spatial-then-Temporal Self-Supervised...

Get background even when have a moving camera using transformers with DeepMCBM A Deep Moving-camera Background Model arXiv paper abstract...

Simpler unsupervised object segmentation in videos using spectral clustering with SSL-VOS A Simple and Powerful Global Optimization for...

Get optical flow and object orientation even with lighting changes with INV-Flow2PoseNet INV-Flow2PoseNet: Light-Resistant Rigid Object...