# Video Amodal Segmentation on SAIL-VOS Source: [Video Amodal Segmentation on SAIL-VOS]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:10:31.665Z Evaluation of Video Amodal Segmentation performance on the SAIL-VOS dataset, typically measured using mIoU and mIoUocc. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Video Amodal Segmentation | | Dataset (including any stated split) | SAIL-VOS | | Metric | mIoU | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 11 of 11 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [mIoU](): Higher is better; unit: PERCENT. - [mIoUocc](): Higher is better; unit: PERCENT. ## Recorded results | Method | mIoU | Result date | Report paper | | --- | --- | --- | --- | | Ours | 79.23 | Not recorded | 68fa76121e209131cea6b410 | | Ours | 77.07 | Not recorded | 68fa76121e209131cea6b410 | | PCNet-M | 74.2 | Not recorded | 68fa76121e209131cea6b410 | | AISFormer | 73.51 | Not recorded | 68fa76121e209131cea6b410 | | 3D-UNet | 72.79 | Not recorded | 68fa76121e209131cea6b410 | | Convex R | 71.21 | Not recorded | 68fa76121e209131cea6b410 | | VideoMAE | 69.67 | Not recorded | 68fa76121e209131cea6b410 | | Modal | 67.89 | Not recorded | 68fa76121e209131cea6b410 | | Convex | 63.18 | Not recorded | 68fa76121e209131cea6b410 | | pix2gestalt | 60.79 | Not recorded | 68fa76121e209131cea6b410 | | pix2gestalt | 54.83 | Not recorded | 68fa76121e209131cea6b410 | ### Ours mIoU: 79.23. Result ID: 699424273a6c3148491b5866. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method category":"Video-based","Top-k prediction":"3"}. This record does not assert independent reproduction. ### Ours mIoU: 77.07. Result ID: 699424273a6c3148491b5865. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method category":"Video-based","Top-k prediction":"1"}. This record does not assert independent reproduction. ### PCNet-M mIoU: 74.2. Result ID: 699424273a6c3148491b585f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method category":"Image-based"}. This record does not assert independent reproduction. ### AISFormer mIoU: 73.51. Result ID: 699424273a6c3148491b5860. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method category":"Image-based"}. This record does not assert independent reproduction. ### 3D-UNet mIoU: 72.79. Result ID: 699424273a6c3148491b5864. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Method category":"Video-based"}. This record does not assert independent reproduction. ### Convex R mIoU: 71.21. Result ID: 699424273a6c3148491b585e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method category":"Image-based"}. This record does not assert independent reproduction. ### VideoMAE mIoU: 69.67. Result ID: 699424273a6c3148491b5863. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Method category":"Video-based"}. This record does not assert independent reproduction. ### Modal mIoU: 67.89. Result ID: 699424273a6c3148491b585c. [Reporting paper]() Recorded evaluation configuration: {"Method category":"Image-based"}. This record does not assert independent reproduction. ### Convex mIoU: 63.18. Result ID: 699424273a6c3148491b585d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method category":"Image-based"}. This record does not assert independent reproduction. ### pix2gestalt mIoU: 60.79. Result ID: 699424273a6c3148491b5862. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Method category":"Image-based","Top-k prediction":"3"}. This record does not assert independent reproduction. ### pix2gestalt mIoU: 54.83. Result ID: 699424273a6c3148491b5861. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Method category":"Image-based","Top-k prediction":"1"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.