AI Classification Tab¶

This tab controls the three AI options that describe your video thumbnails during indexing — scene classification, object detection and image tagging — and the settings that tune them. Results are added as keywords.

The on/off switches also appear on the Video Indexer tab; this is where all three are tuned.

Scene Classification -- When checked, automatic scene classification is enabled during video indexing.

Object Detection -- When checked, automatic object detection is enabled during video indexing.

Image Tagging -- When checked, image tagging runs during video indexing. This has no effect until the image-tagging model has been downloaded from AI Models on the start page's Maintenance section — until then indexing simply skips it. Tagging is heavier per frame than the other two, so indexing takes longer with it enabled.

Min Confidence -- Minimum confidence threshold for scene and object detection. Detections below this threshold are ignored. Value between 0.0 and 1.0. This does not apply to image tagging, which uses Tag Sensitivity instead.

Tag Sensitivity -- Threshold for image tagging. Higher values give fewer, more confident tags; lower values tag more freely. Value between 1.5 and 5.0, default 3.0. See how a tag is chosen.

Frame Skip -- Process every Nth thumbnail. Higher values result in faster processing but less detailed analysis. Value between 1 and 100, default 1 (every thumbnail).

Pool Size -- Number of parallel inference sessions. Higher values use more memory but process faster. Set to 0 for auto, which selects based on CPU cores. Value between 0 and 64.