Entering "a drone shot over a city at night" makes Fast Video Cataloger show the top-matching scenes from 11,766 thumbnails, ordered by relevance. None of those clips had a drone or aerial keyword.
Describe the visual and locate the footage: "waves crashing on rocks" returns an entire page of matching scenes drawn from an 11,766-clip library, best first, with no prior tagging required.
This new visual search capability finds shots in a local video collection using natural-language descriptions, without any advance tagging or uploaded footage.
You remember what a shot looks like long before you remember what you called it. Visual search lets you look for it the way you remember it.”— Fredrik Lönn, co-founder, VideoStormSTOCKHOLM, SWEDEN, October 2, 2026 /EINPresswire.com/ — VideoStorm has launched version 10.4 of Fast Video Cataloger, the Windows-based video cataloging application. The headline addition is visual search. An editor types what a scene looks like, such as "drone shot over a city at night", and the software displays the library scenes that are most similar. It searches the actual image content, not keywords, so it uncovers footage that was never tagged.
Locating a clip typically involves scrubbing through hours of unlogged material or content that was tagged with different terms than the editor is using now. With visual search, the editor describes the shot in the same way they would tell a coworker. This description works alongside the other filters in the Search window, so a query can be narrowed to a single folder or a specific project keyword.
ADDITIONAL SIMILAR CLIPS
Once an editor has found a suitable shot, Find similar scenes ranks the entire catalog by visual resemblance. This surfaces the rest of a sequence or every take from the same location. The closest matches appear first. By default, each video contributes a limited number of results so that a single long clip does not dominate the list.
The search index is constructed on the user's own computer during video indexing. Older catalogs can be processed in a separate pass that shows the percentage of the library covered and can be paused and resumed. The footage and the index never leave the user's machines. For shared catalogs, the search runs on the Fast Video Cataloger server, which also exposes it to scripts via the REST API and to AI assistants through MCP.
"You remember what a shot looks like long before you remember what you called it," said Fredrik Lönn, co-founder of VideoStorm. "Visual search lets you look for it the way you remember it."
TAGS THAT IMPROVE FROM USER FEEDBACK
Version 10.4 also enhances Trained Tags, first introduced in version 10.3. A trained tag is a custom AI keyword that the user teaches using a small set of example thumbnails. Users can now right-click an incorrect match and mark it as Not this. The keyword is removed, and the tag stops matching similar images. The Trained Tags window also highlights examples that degrade a tag, such as near-duplicates.
PRICING AND AVAILABILITY
Fast Video Cataloger works alongside editing tools like Premiere Pro and DaVinci Resolve without replacing them. It serves as the place where editors search and organize their footage, offering visual browsing, structured metadata, and fully local storage. Version 10.4 includes numerous smaller fixes and improvements. The complete list is in the version history in the user guide.
Fast Video Cataloger 10.4 is available now for Windows 10 and 11. Pricing starts at $9.90 per month, $97 per year, or a one-time perpetual license of $197. A free 30-day trial is available at videocataloger.com.
Fredrik Lönn
VideoStorm Sweden AB
email us here
Visit us on social media:
LinkedIn
Instagram
Facebook
YouTube
TikTok
Find any shot by describing it – visual search in Fast Video Cataloger
