datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
Genres
Genres Dataset
Genres is a benchmark dataset for evaluating gender bias in multimodal large language models (MLLMs) through narrative generation involving social relationships. It is grounded in Fiske’s relational models theory and consists of 1,440 Narrative Elicitation Pairs (NEPs), each pairing a visual scene with a text prompt to elicit character profiles and stories. The dataset is designed to examine how gender bias manifests across different types of interpersonal… See the full description on the dataset page: https://huggingface.co/datasets/Savannah-y7/Genres.Brazilian_Cerrado-Savanna_Scenes
Dataset Card for "Brazilian_Cerrado-Savanna_Scenes"
Licensing Information
[CC BY-NC]
Citation Information
Towards vegetation species discrimination by using data-driven descriptors
@inproceedings{nogueira2016towards,
title = {Towards vegetation species discrimination by using data-driven descriptors},
author = {Nogueira, Keiller and Dos Santos, Jefersson A and Fornazari, Tamires and Silva, Thiago Sanna Freire and Morellato, Leonor Patricia and… See the full description on the dataset page: https://huggingface.co/datasets/jonathan-roberts1/Brazilian_Cerrado-Savanna_Scenes.