OpenSceneSense — AI video scene tagging

Python library combining vision models and audio transcription with dynamic frame selection to auto-tag and describe video scenes.

Link

• Visit resource

Related resources

• PyProbePython library that parses video metadata via ffprobe or MediaInfo into structured output.
• sprite-vtt-generator — seekbar sprite + WebVTTNode.js tool generating thumbnail sprite sheets and WebVTT files with automatic interval selection for HLS/DASH seekbar previews.
• slhck/h26x-extractor — H.264/H.265 NAL ExtractorPython tool extracting NAL units from H.264/H.265 bitstreams, decoding type and content with JSON output.
• amarghosh/mp4viewer — ISOBMFF Atom AnalyzerPython ISOBMFF atom analyser with shell, GTK, and JSON output for inspecting MP4 structure.
• video_sprites — Ruby sprite + WebVTT generatorRuby gem generating sprite PNG sheets and WebVTT for HTML5 player seek previews, with optional animated GIF output.
• ITU-T P.1203 reference implementationOfficial Python reference implementation of the ITU-T P.1203 HTTP adaptive streaming QoE model (modes 0-3), outputting per-second and integ…
• butteraugli (Rust port)Pure Rust port of Butteraugli from libjxl with XYB color, visual masking, and multi-scale bands, validated to within 0.001% of the referenc…
• SimpleVQADeep-learning no-reference video quality assessment for user-generated content, in PyTorch with SlowFast feature extraction.
• AutoShotCVPR-NAS 2023 shot boundary detection model with a NAS-optimized architecture and the new SHOT dataset (853 videos, 11,606 annotations).