Video Duplicate and Near-Duplicate Detection
Overview
The Near-Duplicate Detection model is used to find duplicate or near-duplicate segments in videos.
Duplicate segments are segments that are identical or nearly identical, even if they have been modified in some way (with overlays, cropping, split-screen, mixing etc.)
Common use-cases include:
- Video Blacklists and Disallow lists: Blacklist videos and prevent them from (re)appearing on your site or app. For instance copyrighted videos, illegal videos, previously removed videos.
- Copyright detection: Detect and manage copyrighted content in user uploads.
- Video set deduplication: Identify and manage duplicate videos within a set.
Image duplicate detection is also available, see the Image Duplicate Detection guide.
What is detected as duplicate video frames/segments
The duplicate detection works with all types of videos, both long and short, realistic or animated. It will detect duplicate video segments across a wide range of transformations and modifications, many of which are typically used to try to evade or circumvent duplicate detection. Here are examples:
Original clip
Resolution, size and format changes
Changes to the dimensions of the clip (downscaling, upscaling), to the resolution, to the clip format and encoding
Text overlays
The deduplication is robust to the addition of text overlays and watermarks
Clip overlays
The deduplication is robust to clip overlays obscuring large parts of the original clip
Cropping and reframing
The deduplication model is crop-resistant, meaning that '.clip.'s that have been cropped, or have an added border/frame will be detected
Collage
If the original clip is included in a collage of clips, or a split-screen layout, it will still be detected
Blur
Heavy blur effects, including gaussian blur, motion blur, pixelation are detected
Clip mixing
If the original clip is mixed with other clips, it will still be detected
Color changes and filters
Color modifications such as transforming the clip to black-and-white, dropping a channel, changing the saturation, brightness, contrast, hue and other color manipulations
Geometric transformations, stretching, flipping
Modifying the aspect ratio, flipping the image
Next steps: learn how to use
Choose your use-case to learn how to use the Video Deduplication model:
Was this page helpful?