ovis
Datasets
All datasets matching “ovis”OVIS_RGBD
OVIS_RGBD
The dataset is for paper "Beyond Appearance: Geometric Cues for Robust Video Instance Segmentation".
You can find the usages in GitHub.
The original frame images and annotations are from OVIS. We use DepthAnythingV2 to perform monocular depth estimation on all images. We concatenate depth map on the channel demension and each image is in RGBD format.
Citations
@InProceedings{niu2025,
author = {Niu, Quanzhu and Zhou, Yikang and Chen, Shihao and… See the full description on the dataset page: https://huggingface.co/datasets/QuanzhuNiu/OVIS_RGBD.repro-ovisocr-end-to-end-document-parsing-traces
Agent traces
Agent sessions published from a Trackio Logbook.
0004-pdf-ovisocr2
Document OCR using OvisOCR2
This dataset contains OCR results from images in stephenmcconnachie/0004-pdf-pages-test using OvisOCR2, a compact 0.9B document parsing model (96.58 on OmniDocBench v1.6).
Processing Details
Source Dataset: stephenmcconnachie/0004-pdf-pages-test
Model: ATH-MaaS/OvisOCR2
Number of Samples: 50
Processing Time: 7.9 min
Processing Date: 2026-07-14 21:00 UTC
Configuration
Image Column: image
Dataset Split: train
Batch Size:… See the full description on the dataset page: https://huggingface.co/datasets/stephenmcconnachie/0004-pdf-ovisocr2.permis-ocr-ovis
Document OCR using OvisOCR2
This dataset contains OCR results from images in mehdigououiad/permis-ocr-bench using OvisOCR2, a compact 0.9B document parsing model (96.58 on OmniDocBench v1.6).
Processing Details
Source Dataset: mehdigououiad/permis-ocr-bench
Model: ATH-MaaS/OvisOCR2
Number of Samples: 2
Processing Time: 5.4 min
Processing Date: 2026-08-11 13:57 UTC
Configuration
Image Column: image
Dataset Split: train
Batch Size: 16
Max Model… See the full description on the dataset page: https://huggingface.co/datasets/mehdigououiad/permis-ocr-ovis.hucker-bakeoff2-ovis-hard
Document OCR using OvisOCR2
This dataset contains OCR results from images in bokane/hucker-ocr-bakeoff-hard using OvisOCR2, a compact 0.9B document parsing model (96.58 on OmniDocBench v1.6).
Processing Details
Source Dataset: bokane/hucker-ocr-bakeoff-hard
Model: ATH-MaaS/OvisOCR2
Number of Samples: 8
Processing Time: 4.5 min
Processing Date: 2026-08-13 22:28 UTC
Configuration
Image Column: image
Dataset Split: train
Batch Size: 16
Max Model… See the full description on the dataset page: https://huggingface.co/datasets/bokane/hucker-bakeoff2-ovis-hard.repro-ovisocr-omnidocbench-outputs