datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
SportMM-LT
SportMM-LT
English | 中文说明
English
SportMM-LT is a multimodal benchmark for evaluating long-tail sports knowledge in vision-language models.
It contains 421 image-question-answer samples across three sports domains:
basketball
football
table tennis
Dataset Overview
SportMM-LT is designed to evaluate whether vision-language models can answer fine-grained, domain-specific sports questions from images. The benchmark focuses on long-tail knowledge that… See the full description on the dataset page: https://huggingface.co/datasets/Guo1115/SportMM-LT.SpotEditBench
SpotEditBench
SpotEditBench is a benchmark for evaluating visually-guided image editing task. It consists of real and syn parts.
Repository: SpotEdit
Paper: 2508.18159
laundry-spots-dataset
Laundry Spots Dataset
Generated from naavox/merged-5.
SPORTgripper-spots-dataset
Laundry Spots Dataset
Generated from naavox/merged-5.