AutoShot — A Short Video Dataset and State-of-the-Art Shot Boundary Detection
Paper introducing a short-video shot-boundary dataset and model that outperforms TransNetV2 on subtle transitions, with released code.
Link
Related resources
- DSBD — Deep Shot Boundary Detection at ScaleSpatio-temporal CNN for shot boundary detection with an accompanying dataset emphasizing gradual transitions.
- PySceneDetect DocumentationCanonical docs for PySceneDetect's CLI and Python API: content/adaptive/threshold detectors and ffmpeg/mkvmerge-based video splitting.
- BAND-2k — banding artifact database and detectorDataset of 2,000 banding images plus a dual-CNN banding evaluator that vastly outperforms CAMBI on banding-quality correlation (SRCC 0.88 v…
- TwelveLabs Marengo — Video Embedding Model DocumentationDocs for a multimodal video embedding model supporting long-form video with shot-boundary segmentation, used for search, dedup and content…
- Introducing an Open Source DAW Plugin for Eclipsa Audio (IAMF)June 2025 announcement of an open source DAW plugin for authoring IAMF/Eclipsa immersive audio, including the YouTube ingest path.
- PyNvVideoCodec API Programming GuideNVIDIA's Python bindings over the Video Codec SDK for GPU-accelerated decode/encode pipelines feeding ML and analytics workloads.
- hdr10plus_tool — Codec Wiki Usage GuideCommunity reference with flags and FFmpeg pipe recipes for extracting, injecting and inspecting HDR10+ dynamic metadata in HEVC/MKV.
- FFmpeg 8.0 whisper Filter DocumentationReference for FFmpeg 8.0's built-in Whisper ASR filter: model selection, VAD, queueing, and SRT/JSON transcript output destinations.
- EBU ADM Guidelines and Example FilesEBU hub for Audio Definition Model guidelines, sample ADM/BW64 files and the ADM Production Profile for practical broadcast interchange.
- UVQ — Universal Video Quality (Google)Google's no-reference perceptual video quality model for user-generated content, scoring compression, content and distortion without a pris…
- DOVER — Disentangled Objective Video Quality EvaluatorICCV 2023 no-reference VQA model that outputs separate aesthetic and technical quality scores, with ONNX export and a DOVER-Mobile variant…
- ColorVideoVDP — reference implementationPyTorch implementation of the ColorVideoVDP full-reference metric (SIGGRAPH 2024), usable as a CLI quality tool or as a differentiable perc…