24,167 datasets found

This paper tackles a novel problem: how to transfer knowledge from the emerging Segment Anything Model (SAM) to learn a compact panoramic semantic segmentation model, i.e.,...

The VCTK dataset is a large corpus of speech recordings, each containing a single speaker and a single sentence.

The LJSpeech dataset is a collection of audio recordings of a single female speaker reading aloud.

FastSpeech 2 is a fast and high-quality end-to-end text-to-speech system. It uses a multi-task learning approach to learn the mapping between phonemes and waveforms.

FastDiff is a fast conditional diffusion model for high-quality speech synthesis. It employs a stack of time-aware location-variable convolutions with diverse receptive field...

The dataset used in the paper for image classification, object detection, and face verification tasks.

ImageNet-10 is a dataset of 10,000 224x224 color images in 10 classes, with 1,000 images per class.

The FULL1 and FULL2 datasets are subsets of the Oxford RobotCar dataset, with longer route lengths.

The LOOP1 and LOOP2 datasets are subsets of the Oxford RobotCar dataset, with shorter route lengths.

The dataset used in the paper to evaluate the influence of graph elements on the parameter changes of GCNs without needing to retrain the GCNs.

The dataset used in the paper to evaluate the influence of graph elements on the parameter changes of GCNs without needing to retrain the GCNs.

The dataset used in the paper to evaluate the influence of graph elements on the parameter changes of GCNs without needing to retrain the GCNs.

The dataset used in the paper is a series of datasets introduced in [46], comprising large corpora of product reviews crawled from Amazon.com. Top-level product categories on...

The dataset used in this paper is a large-scale dataset for implicit feedback, consisting of user-item interactions, where each interaction is a pair of a user and an item.

The MovieLens10M dataset is a classic movie rating dataset, whose ratings range from 0.5 to 5.

The KITTI360 dataset is used for evaluating the proposed Tuple-Circle loss function for cross-modality feature learning. The dataset consists of image and LiDAR scan pairs.

PhotoBot is a framework for fully automated photo acquisition based on an interplay between high-level human language guidance and a robot photographer.

The dataset is used for redatuming physical systems using symmetric autoencoders. It contains seismic wave data from different states with varying nuisance parameters.

The authors used the ComplexPoint-v0, Pendulum-v0, LunarLanderContinuous-v2, Swimmer-v2, HalfCheetah-v2, HumanoidStandup-v2, Humanoid-v2 datasets for experiments.

The IQmulus dataset is used for global localization tasks. It contains real-world point cloud data with semantic object-centric maps.