53 datasets found

The dataset used in the paper is a set of feature-vectors from two sets of d-dimensional noisy feature-vectors.

Two large-scale benchmark datasets for reference-limited compositional zero-shot learning (RL-CZSL).

The dataset used in this paper for predicting force exertion levels using computer vision and machine learning.

A large-scale, multi-agent video and trajectory benchmark to assess the quality of learned behavior representations.

Realistic real-time talking head synthesis with hash grid landmarks encoding and progressive multilayer conditioning

The proposed network utilizes a classification-regression paradigm with a ViT to incorporate holistic features and local features. The regression phase with hybrid regression...

The WOMD dataset is a large-scale interactive motion forecasting dataset for autonomous driving, which includes 2 million agents and 6 motion trajectories for 8 seconds in the...

A synthetic dataset for sceneries in the passenger compartment of ten different vehicles, to analyze machine learning-based approaches for their generalization capacities and...

Vision models with high overall accuracy often exhibit systematic errors on some important subsets of data, posing potential serious safety concerns. Diagnosing such bugs of...

A dataset for pose estimation and tracking for ASIST system

Three datasets: training, calibration, and evaluation datasets for pedestrian detection task.

A benchmark for stereo matching and depth estimation.

The dataset used for the experiments of the paper "CORE-PERIPHERY PRINCIPLE GUIDED REDISIGN OF SELF-ATTENTION IN TRANSFORMERS"

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used TinyImagenet dataset for pre-training the embedding functions.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used CIFAR-10, CIFAR-100, and STL-10 datasets for training and testing the...

Aerial IR videos of photovoltaic plants for automatic extraction and georeferencing of PV modules

The MNIST and CIFAR-10 datasets are used to test the theory suggesting the existence of many saddle points in high-dimensional functions.

The authors propose a method for self-supervised representation learning using knowledge distillation and vision transformers.

The authors propose a method for zero-shot classification that leverages conditional density estimates from text-to-image diffusion models.

Diffusion models have recently emerged as the state-of-the-art of generative modeling, demonstrating remarkable results in image synthesis and across other modalities.