Searcharxiv⌕ Search

arXiv subjects

Karthikeyan Mohanraj

Publications and source records attributed to Karthikeyan Mohanraj.

2 recordsLinked to original sources

Multimodal Judges Flag, Humans Decide: A Review-and-Edit Framework for AI-Generated Product Video Ads

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.

cs.CV↗

Forman curvature for complex networks

We adapt Forman's discretization of Ricci curvature to the case of undirected networks, both weighted and unweighted, and investigate the measure in a variety of model and real-world networks. We find that most nodes and edges in model and real networks have a negative curvature. Furthermore, the distribution of Forman curvature of nodes and edges is narrow in random and small-world networks, while the distribution is broad in scale-free and real-world networks. In most networks, Forman curvature is found to display significant negative correlation with degree and centrality measures. However, Forman curvature is uncorrelated with clustering coefficient in most networks. Importantly, we find that both model and real networks are vulnerable to targeted deletion of nodes with highly negative Forman curvature. Our results suggest that Forman curvature can be employed to gain novel insights on the organization of complex networks.

q-bio.MN↗