-
PandaNet: Anchor-based Single-Shot Multi-Person 3D Pose Estimation
PandaNet is a single-shot approach for multi-person 3D pose estimation that can handle images with a large number of people, strong occlusions, and varying sizes. -
Breast Ultrasound Video Diagnosis
The dataset is used for breast cancer diagnosis in ultrasound videos. -
Animals with Attributes 2
The dataset used is Animals with Attributes 2. -
CIFAR-10-C and CIFAR-100-C
CIFAR-10-C and CIFAR-100-C are robustness benchmarks consisting of 19 corruptions types with five levels of severities. -
DecoyFMNIST
The DecoyFMNIST dataset is an updated version of MNIST that is more complex and less overused in research. -
DecoyMNIST
The DecoyMNIST dataset is a variation of MNIST with decoy squares in the image corners, confounding the training data. -
CIFAR-10, FEMNIST, and IMDB
The dataset used in the paper is CIFAR-10, FEMNIST, and IMDB. The authors used these datasets to evaluate the performance of the EmbracingFL framework. -
Stanford 3D Scanning Repository
The dataset used in the paper is not explicitly described, but it is mentioned that the authors tested their model on various signal reconstruction tasks: 1D sinusoidal... -
GPU Accelerated Cascade Hashing Image Matching for Large Scale 3D Reconstruction
Image feature point matching is a key step in Structure from Motion(SFM). However, it is becoming more and more time consuming because the number of images is getting larger and... -
KITTI tracking dataset
KITTI tracking dataset provides 21 training and 29 test sequences. The dataset provides 2D bounding box annotations for cars, pedestrians, and 6 other classes, but only the... -
Systematic Literature Review on Computer Vision Applications in Robotized Wir...
The dataset is used for a systematic literature review on computer vision applications in robotized wire harness assembly. -
Efficient and Robust Classification for Sparse Attacks
The MNIST and CIFAR datasets are used to test the robustness of neural networks against sparse attacks. -
Attention Based Simple Primitives for Open World Compositional Zero Shot Lear...
Compositional Zero-Shot Learning (CZSL) aims to predict unknown compositions made up of attribute and object pairs. -
Dual-Camera Smooth Zoom on Mobile Phones
The dataset is used for training and testing the proposed dual-camera smooth zoom (DCSZ) method. -
Weakly Supervised Gaussian Networks for Action Detection
Detecting temporal extents of human actions in videos is a challenging computer vision problem that requires detailed manual supervision including frame-level labels. -
Pascal VOC Keypoints
Pascal Visual Object Classification challenge consist of 20 image classes, where each image was parsed into an image graph using keypoints as nodes. -
Matching Map Recovery with an Unknown Number of Outliers
The dataset used in the paper is a set of feature-vectors from two sets of d-dimensional noisy feature-vectors. -
Harbour Bridge
A dataset of tricamera stereo sequences for road-modeling in the presence of windscreen wipers. -
Tree Branch Dynamics for Manipulation
The dataset used for learning the dynamic behavior of tree branches by utilizing the simulation-based parameter inference approach.
