43 datasets found

The dataset used in the paper is a multimodal learning task for robots.

The dataset used in the paper is a multimodal categorization task using image data and speech signals.

A large-scale city-wise dataset for exploring the relationships among air pollutants and their causal agents over time.

The MAMI dataset is a collection of images and text posts used for training and testing the proposed multimodal model for misogyny identification.

The XD-Violence dataset is a large-scale multimodal video dataset for violence detection. It consists of 4,754 untrimmed videos with a total duration of 217 hours, covering six...

Weakly supervised multimodal violence detection aims to learn a violence detection model by leveraging multiple modalities such as RGB, optical flow, and audio, while only...

The VQA dataset is a large-scale visual question answering dataset that consists of pairs of images that require natural language answers.

DeepFashion Multimodal dataset contains 12701 full-body images in 24 categories

The BraTS 2020 challenge dataset is a multimodal MRI brain tumor segmentation dataset. It contains 369 subjects with 4 MRI modalities (T2 weighted FLAIR, T1 weighted, T1...

Automatic segmentation of brain tumors is an essential but challenging step for extracting quantitative imaging biomarkers for accurate tumor detection, diagnosis, prognosis,...

The Stanford Drone Dataset (SDD) is a large-scale dataset that consists of 60 aerial-view videos captured by drones over Stanford University. SDD contains positions of more than...

Multimodal anti-UAV dataset for modern miniature drone threats

MIMIC-CXR-JPG dataset comprises 227,835 imaging studies conducted on 64,588 patients who sought treatment at the BIDMC Emergency Department from 2011 to 2016.

LADI-VTON: Latent diffusion textual-inversion enhanced model for virtual try-on

Multimodal Garment Designer: Human-Centric Latent Diffusion Models for Fashion Image Editing

FashionSD-X: Multimodal Fashion Garment Synthesis using Latent Diffusion

RAVDESS (Ryerson Audio-Visual Database of Emotional Speech and Song) dataset contains 24 professional actors (12 female, 12 male) to offer the performance with good quality and...

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

The MineCLIP dataset is a large-scale dataset of Minecraft demonstrations.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used a combination of reinforcement learning and generative models to solve...