Moving Camouflaged Animals (MoCA)-Mask
The original Moving Camouflaged Animals (MoCA) Dataset includes 37K frames from 141 YouTube Video sequences with resolution and sampling rate of 720 × 1280 and 24fps in the majority of cases. The dataset covers 67 types of animals moving in natural scenes, but some are not camouflaged animals. Also, the ground truth of the original dataset is bounding boxes rather than dense segmentation masks, which makes it hard to evaluate the VCOD segmentation performance. To this end, we reorganize the dataset as MoCA-Mask and build a comprehensive benchmark with more comprehensive evaluation criteria.
Variants: MoCA-Mask
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Camouflaged Object Segmentation | CamoSAM2 | CamoSAM2: Motion-Appearance Induced Auto-Refining Prompts … | 2025-04-01 |
| Camouflaged Object Segmentation | ZoomNeXt-PVTv2-B5 | ZoomNeXt: A Unified Collaborative Pyramid … | 2023-10-31 |
| Camouflaged Object Segmentation | STL-Net-LT-PVTv2-B5 | Implicit Motion Handling for Video … | 2022-03-14 |
Recent papers with results on this dataset: