-
KITTI-Object
Monocular 3D object localization in driving scenes is a crucial task, but challenging due to its ill-posed nature. Estimating 3D coordinates for each pixel on the object surface... -
Improvised Aerial Object Detection approach for YOLOv3 Using Weighted Luminance
Aerial imaging of ground targets is highly challenging because of various factors that affect light propagation through different mediums. Several convolutional neural... -
ImageNet-1K, COCO, and ADE20K datasets
The dataset used in the paper is not explicitly described. However, it is mentioned that the authors used the ImageNet-1K, COCO, and ADE20K datasets for image classification,... -
Breast Ultrasound Dataset
The dataset in this paper comes from the database of the Ultrasound Imaging Department of Peking University Shenzhen Hospital. -
Moving MNIST dataset
The Moving MNIST dataset consists of videos of MNIST digits. -
KITTI 2012
KITTI 2012 is a real-world dataset in the outdoor scenario, and contains 194 training and 195 testing stereo image pairs with the size of 376 × 1240. -
Flickr1024
Stereo image super-resolution aims to improve the quality of high-resolution stereo image pairs by exploiting complementary information across views. -
Training CLIP models on Data from Scientific Papers
Contrastive Language-Image Pretraining (CLIP) models are trained with datasets extracted from web crawls, which are of large quantity but limited quality. This paper explores... -
MVSEC dataset
A real-world dataset collected in indoor and outdoor scenarios with sparse optical flow labels. -
Multi-Density Rendered (MDR) event optical flow dataset
A rendered event-flow dataset created using computer graphics models, with accurate events and flow labels. -
FCPose: Fully Convolutional Multi-Person Pose Estimation
Multi-person pose estimation framework using dynamic instance-aware convolutions -
DeiT and ViT models on ImageNet-1k and CIFAR-100
The dataset used in the paper is not explicitly described, but it is mentioned that the authors used DeiT and ViT models on ImageNet-1k and CIFAR-100 datasets. -
DropIT: DROPPING INTERMEDIATE TENSORS FOR MEMORY-EFFICIENT DNN TRAINING
The dataset used in the paper is not explicitly described, but it is mentioned that the authors used DeiT and ViT models on ImageNet-1k and CIFAR-100 datasets. -
NYU-v2 Dataset
Indoor segmentation and support inference from RGB-D images. -
CIFAR-10 and ILSVRC-2012 datasets
The dataset used in this paper is a convolutional neural network (CNN) model, specifically VGG-16 and ResNet-56/110 on CIFAR-10 and ILSVRC-2012 datasets. -
Pix3D: Dataset and methods for single-image 3D shape modeling
The Pix3D dataset is a dataset of pairs of natural images and CAD models. -
MPI Sintel
The dataset used in the paper for unsupervised single image intrinsic decomposition. -
NEAT Dataset
The NEAT dataset, used for training and evaluation of the Neural Attention Fields (NEAT) model.
