Scene segmentation 7.3 times faster with 3D transformer using patch attention PatchFormer: A Versatile 3D Transformer Based on Patch...

Improve vision transformer by using anti-aliasing Blending Anti-Aliasing into Vision Transformer arXiv paper abstract...

Train object detectors using images synthesized from real unmarked images Self-Supervised Object Detection via Generative Image Synthesis...

Survey of training object detectors with limited data or unlabeled data A Survey of Self-Supervised and Few-Shot Object Detection arXiv...

Recognizing actions without training using scene context with object recognition Zero-Shot Action Recognition from Diverse Object-Scene...

Get foreground in image without user marking borders using 100x smaller model Highly Efficient Natural Image Matting arXiv paper abstract...

Better image captioning and question answering using weakly supervised training SimVLM: Simple Visual Language Model Pretraining with...

Find person in image gallery using text queries by leveraging larger libraries Text-Based Person Search with Limited Data arXiv paper...

Train 3D segmentation model using labeled 2D images and raw 3D data Learning 3D Semantic Segmentation with only 2D Image Supervision...

Survey of deep learning to re-identify people seen by multiple cameras Deep Learning Based Person Re-Identification Methods: A Survey and...

Remove image banding artifacts with deep learning Deep Image Debanding arXiv paper abstract https://arxiv.org/abs/2110.08569v1 arXiv PDF...

State of AI Report 2021 (Benaich and Hogarth) (includes Computer Vision) State of AI Report 2021 The State of AI Report analyses the most...

Kaggle 2021 survey on ML and Data Science State of Data Science and Machine Learning 2021 Kaggle https://www.kaggle.com/kaggle-survey-202...

Image classifier explains features used and how to modify them to change output Explaining in Style: Training a GAN to explain a...

Improved multi-object tracking by associating all detection boxes ByteTrack: Multi-Object Tracking by Associating Every Detection Box...

Make images in-focus at every pixel with the dual-pixel cameras in smartphones Defocus Map Estimation and Deblurring from a Single...

Improve road lane detection by using multiple images with neural networks A Hybrid Spatial-temporal Sequence-to-one Neural Network Model...

Identify human actions on objects and their locations after training on image captions Weakly Supervised Human-Object Interaction...

Neural networks to remove image flare How to Train Neural Networks for Flare Removal arXiv paper abstract https://arxiv.org/abs/2011.1248...

Enhance dim images and video using regions in zero-shot learning Semantic-Guided Zero-Shot Learning for Low-Light Image/Video Enhancement...