1,082 datasets found

Graph matching (GM) constitutes a pervasive problem in computer vision and pattern recognition, with applications in image registration, recognition, stereo, 3D shape matching,...

Contextual convolution (CoConv) for visual recognition. CoConv is a direct replacement of the standard convolution that can be used at any stage in CNN architectures.

A dataset for visual odometry, containing 11 sequences with provided ground-truth poses.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors applied their approach to the challenging problem of optical flow estimation and...

The dataset used in this paper is a dataset of four CNN models: ResNet-18, Vgg-16, Squeezenet v1.0, and AlexNet.

The Acoustic AVSpeech dataset is a benchmark for visual acoustic matching.

The SoundSpaces-Speech dataset is a benchmark for visual acoustic matching.

The Oxford Radar RobotCar dataset is a radar extension to the Oxford RobotCar dataset, containing radar observations of a vehicle in various scenarios.

ChainerCV supports algorithms to solve tasks in the computer vision field such as object detection, while considering usability and predictable performance as the top priorities.

A large-scale synthetic dataset for human head detection and 3D mesh estimation.

Semantic segmentation is a fundamental task in computer vision and enables many downstream applications. It is related to image classification since it produces per-pixel...

The dataset used in this paper is ImageNet and SQuAD and GLUE datasets.

A modified implementation of the Shadow Neural Radiance Field (S-NeRF) model for surface reconstruction from satellite images.

Dense computer vision tasks such as object detection and segmentation require effective multi-scale feature representation for detecting or classifying objects or regions with...

High dynamic range (HDR) novel view synthesis (NVS) aims to create photorealistic images from novel viewpoints using HDR imaging techniques.

The dataset is a collection of 75 user-generated scenes for a tidying task, where users are asked to arrange objects in a tidy manner.

A benchmark for stereo matching, consisting of 50 stereo pairs with ground truth disparity maps.

A benchmark for stereo matching, consisting of 11 stereo pairs with ground truth disparity maps.

A benchmark for stereo matching, consisting of 75 stereo pairs with ground truth disparity maps.

3D shape analysis is an important research topic in computer vision and graphics. The dataset used in this paper is a collection of 3D shapes with the same connectivity to train...