Category: Paper Collection

A non-local algorithm for image denoising; Fields of Experts: a framework for learning image priors

Event-based analysis of video; Constructing models for content-based image retrieval; Dynamic texture recognition

Unbiased look at dataset bias; Localizing parts of faces using a consensus of exemplars; Fast cost-volume filtering for visual correspondence and beyond

Aggregating local descriptors into a compact image representation; Secrets of optical flow estimation and their principles; Learning mid-level features for recognition; New features and insights for pedestrian detection

Learning to Detect A Salient Object; Saliency Detection: A Spectral Residual Approach; Hierarchical Matching of Deformable Shapes; Learning Local Image Descriptors; Semantic Hierarchies for Visual Object Recognition

Three things everyone should know to improve object retrieval; Image denoising: Can plain neural networks compete with BM3D?; FREAK: Fast Retina Keypoint

Full of familiar names: ResNet, ImageNet, YOLO, GoogLeNet, HoG, R-CNN, FCN, KITTI, FaceNet, FPN, Pix2pix, SENet, Xception, MobileNet, SRGAN, SRCNN, Sub-Pixel Conv, ResNeXt, EfficientDet, Dark Channel, ….

Learning to detect unseen object classes by between-class attribute transfer; Recognizing realistic actions from videos “in the wild”; Understanding and evaluating blind deconvolution algorithms; From contours to regions: An empirical evaluation; Geometric reasoning for single image structure recovery; Nonparametric scene parsing: Label transfer via dense scene alignment; Describing objects by their attributes; Picking the best DAISY