Simply type “a drone shot over a city at night,” and Fast Video Cataloger instantly surfaces the best-matching scenes from a library of 11,766 thumbnails, ranked by relevance. Notably, none of those clips carried a drone or aerial keyword.
Describe the shot, and the shot appears: entering “waves crashing on rocks” delivers a full page of corresponding scenes drawn from an 11,766-scene catalog, ordered by best match first—with no prior tagging required.
New visual search capability locates shots in a local video library using everyday language descriptions, without requiring any pre-tagging or uploading of 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, its Windows-based video cataloging solution. The headline addition is visual search. An editor types a description of what a shot looks like—for instance, “drone shot over a city at night”—and the software displays the best-matching scenes from the library. Because the search examines the images themselves rather than keywords, it also uncovers footage that nobody has ever tagged.
Locating a specific shot typically involves scrubbing through hours of unlogged material or footage tagged with different terms than those an editor is using today. Visual search lets the editor describe the shot in the same words they would use with a colleague. This description works in tandem with other filters in the Search window, so users can narrow results to a single folder or a specific project keyword.
MORE SHOTS LIKE THIS ONE
Once an editor has found a good shot, Find similar scenes reorders the entire catalog based on visual resemblance. This surfaces the rest of a sequence or every take recorded at the same location, with the closest matches appearing first. By default, each video contributes a limited number of results to prevent a single long shot from dominating the list.
The search index is generated on the user’s own computer during video indexing. Older catalogs can be updated through a separate pass that displays the percentage of the library covered and can be paused or resumed at any time. Footage and the index remain on the user’s machines. When using a shared catalog, the search runs on the Fast Video Cataloger server, which also exposes the functionality 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.”
TRAINED TAGS THAT LEARN FROM CORRECTIONS
Version 10.4 also enhances Trained Tags, a feature first introduced in version 10.3. A trained tag is a custom AI keyword that users teach the software using a small set of example thumbnails. If the system produces an incorrect match, the user can right-click it and mark it as “Not this.” That keyword is then removed, and the tag stops matching similar frames. The Trained Tags window additionally flags examples that could degrade the tag’s accuracy, such as near-duplicates.
AVAILABILITY AND PRICING
Fast Video Cataloger operates alongside editing tools like Premiere Pro and DaVinci Resolve, rather than replacing them. It serves as a dedicated workspace where editors search and organize footage using visual browsing, structured metadata, and entirely local storage. Version 10.4 includes numerous smaller fixes and enhancements. The complete list can be found in the version history within 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 for $197. A free 30-day trial is offered 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
