TL;DR
This paper introduces a novel learning framework, AGPIS, for automatically generating product image sequences in e-commerce, utilizing a multi-modality classifier and additional modules to ensure compliance and quality.
Contribution
The paper presents MUIsC, a multi-modality classifier that detects rule violations using textual feedback and descriptions, improving automation in product image generation.
Findings
MUIsC significantly outperforms baseline models in rule violation detection.
The AGPIS framework generated high-standard images for 1.5 million products.
Achieved a 13.6% reject rate in real-world deployment.
Abstract
Product images are essential for providing desirable user experience in an e-commerce platform. For a platform with billions of products, it is extremely time-costly and labor-expensive to manually pick and organize qualified images. Furthermore, there are the numerous and complicated image rules that a product image needs to comply in order to be generated/selected. To address these challenges, in this paper, we present a new learning framework in order to achieve Automatic Generation of Product-Image Sequence (AGPIS) in e-commerce. To this end, we propose a Multi-modality Unified Image-sequence Classifier (MUIsC), which is able to simultaneously detect all categories of rule violations through learning. MUIsC leverages textual review feedback as the additional training target and utilizes product textual description to provide extra semantic information. Based on offline evaluations,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
