Correcting an image classifier prediction by using a single image Editing a classifier by rewriting its prediction rules arXiv paper...

Better document understanding without OCR using Donut transformer Donut: Document Understanding Transformer without OCR arXiv paper...

Get centimeter depth image from smartphone using LiDAR and unsteadiness of hand The Implicit Values of A Good Hand Shake: Handheld...

Classifying visual and audio events of various durations in videos with MM-Pyramid MM-Pyramid: Multimodal Pyramid Attentional Network for...

Multi-label image classification using information on context, space, and meaning Spatial-context-aware deep neural network for...

Survey of panoptic image segmentation for objects and regions Panoptic Segmentation: A Review arXiv paper abstract...

Many types of computer vision tasks possible with new customizable vision foundation model, Florence Florence: A New Foundation Model for...

Correcting Face Distortion in Wide-Angle Videos Correcting Face Distortion in Wide-Angle Videos arXiv paper abstract...

Train new object detector without bounding box annotations using captioned images Towards Open Vocabulary Object Detection without...

Reidentify people in new scenes better by using multiple networks Learning to Disentangle Scenes for Person Re-identification arXiv paper...

Faster multi-person pose estimation by using object modeling Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects...

Better training data for driving by using simulator to guide realistic image synthesis Towards Optimal Strategies for Training...

Survey of fine-grained image analysis using deep learning Fine-Grained Image Analysis with Deep Learning: A Survey arXiv paper abstract...

Survey of computer vision using transformers A Survey of Visual Transformers arXiv paper abstract https://arxiv.org/abs/2111.06091 arXiv...

Match 3D points with 99% outliers quickly with VOCRA Practical, Fast and Robust Point Cloud Registration for 3D Scene Stitching and...

Improved super-resolution for images by using flows Normalizing Flow as a Flexible Fidelity Objective for Photo-Realistic...

Detect image anomalies by using low-dimensional embeddings of patches PEDENet: Image Anomaly Localization via Patch Embedding and Density...

Survey of video anomaly detection using self-supervised deep learning A Critical Study on the Recent Deep Learning Based Semi-Supervised...

Get 3D scene geometry and segmentation from a single RGB image Panoptic 3D Scene Reconstruction From a Single RGB Image arXiv paper...

Video segmentation with less carrying over of errors by using a cyclic workflow Exploring the Semi-supervised Video Object Segmentation...