datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
DAVIS-Edit
StableV2V: Stablizing Shape Consistency in Video-to-Video Editing
Chang Liu, Rui Li, Kaidong Zhang, Yunwei Lan, Dong Liu
[Paper] / [Project] / [GitHub] / [Models (Huggingface)] / [Models (wisemodel)] / [DAVIS-Edit (wisemodel)] / [Models (ModelScope)] / [DAVIS-Edit (ModelScope)]
HuggingFace repo of the testing benchmark DAVIS-Edit proposed in the paper titled "StableV2V: Stablizing Shape Consistency in Video-to-Video Editing".
Data Structure
We follow the same data… See the full description on the dataset page: https://huggingface.co/datasets/AlonzoLeeeooo/DAVIS-Edit.davistrain_34_davis-0014train_34_davis-0005davis-0000DAVIS_datasettrain_34_davis-0008DAVIStrain_34_davis-0015davis-0004davis-0011DAVIS-S
DAVIS-S
DAVIS-S is a high-resolution salient object detection (SOD) evaluation set,
released alongside the HRSOD (High-Resolution Salient Object Detection)
paper. It is a saliency-annotated subset of the DAVIS video object
segmentation dataset, curated to benchmark high-resolution salient object
detection methods. Images are full-HD (1920x1080) with pixel-accurate
binary ground-truth saliency masks.
Dataset structure
Split: test (single evaluation set), 92… See the full description on the dataset page: https://huggingface.co/datasets/nobg/DAVIS-S.davis-0002train_34_davis-0009decaf-rvos-davis17davis-0009train_34_davis-0000train_34_davis-0003train_34_davis-0010davis-0012davis-0015val_davis-0000davis-0003wikiart-artist-gene-davisDAVIStrain_34_davis-0006davis-0017DAVISDAVIS_Annotations_Evalcgs_paddy_mai_imgs