Ai judges help humans review and edit product video ads efficiently
Multimodal Judges Flag, Humans Decide: A Review-and-Edit Framework for AI-Generated Product Video Ads
Computer Vision and Pattern RecognitionHuman-Computer InteractionMultimedia
Summary
Creating short video ads automatically for products is easy, but deciding if the videos are good enough is tricky. The authors built a system where AI judges first find possible problems with video ads, like the product shown being wrong or the script having issues. Then, human reviewers check those flagged problems, agree or disagree, and fix them using special editing tools. This cooperation helps catch more errors and keep up with how quickly videos are made.
What this means in practice
- •For e-commerce marketing teams: Use AI judges to flag issues in automatically generated product video ads, enabling faster and more thorough human review before publishing.
- •For video content editors: Deploy a review-and-edit workflow that links identified video problems directly to specialized editing tools for efficient fixes.
- •For advertising platform developers: Integrate a multi-question AI judging system that improves quality control for automated video ad generation pipelines.$Commercial implications: This enables commercial platforms to deliver higher-quality automated ads by embedding review tooling that enhances human judgement.
Authors
Anoubhav Agarwaal, Sukesh Perla, Karthikeyan Mohanraj, Susmita Ghose
Abstract
Generative pipelines can now turn every product page of an e-commerce catalog into a short video ad, but deciding whether such an ad is usable is not one good-or-bad call. We describe how we operationalized the review and editing of these ads so that both can keep pace with generation: reviewers go through each ad scene by scene and answer six questions, on the product, scene quality, pronunciation, script, sound and captions; judges built from vision-language, speech and language models file each finding under the matching question, and reviewers accept or reject each finding and add what the judges missed. Each confirmed issue then opens an edit tool matched to it. The questions and the routing from a finding to its fix do not depend on the models that generate the ad. Across 120 ads from our pipeline, reviewed with judge findings on screen, reviewers marked the product wrong on 60% of scenes, and script, caption or sound problems on under 10% each. On 60 of these ads, they marked the product wrong on 58% of scenes, far more than the 26% marked by two reviewers who later saw the ads with the judges hidden; one reviewer who saw the ads both ways marked 57% with judge findings and 19% without. On 120 blind-labeled scenes, a product judge that watches the clip with the catalog photos reached AUC 0.84, while video-quality and photo-similarity scores were close to chance. We tune the judges for recall: the product judge catches nearly all defects but also flags many clean scenes, so reviewers decide; together, the judges widen what reviewers mark and reviewers add what the judges miss. Without judge findings, one reviewer's marking faded over a session. We release a review-portal template and our review data (120 ads and 562 scenes with judge findings and human marks, plus 120 blind-labeled scenes with baseline scores) at https://github.com/anoubhav/ad-review-and-edit.