Salvato in:
| Autori principali: | , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2508.12628 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913160723693568 |
|---|---|
| author | Lin, Yukang Zhang, Xiang Jia, Shichang Wan, Bowen Fu, Chenghan Ren, Xudong Liu, Yueran Guan, Wanxian Wang, Pengji Xu, Jian Zheng, Bo Liu, Baolin |
| author_facet | Lin, Yukang Zhang, Xiang Jia, Shichang Wan, Bowen Fu, Chenghan Ren, Xudong Liu, Yueran Guan, Wanxian Wang, Pengji Xu, Jian Zheng, Bo Liu, Baolin |
| contents | Creative image in advertising is the heart and soul of e-commerce platform. An eye-catching creative image can enhance the shopping experience for users, boosting income for advertisers and advertising revenue for platforms. With the advent of AIGC technology, advertisers can produce large quantities of creative images at minimal cost. However, they struggle to assess the creative quality to select. Existing methods primarily focus on creative ranking, which fails to address the need for explainable creative selection.
In this work, we propose the first paradigm for explainable creative assessment and selection. Powered by multimodal large language models (MLLMs), our approach integrates the assessment and selection of creative images into a natural language generation task. To facilitate this research, we construct CreativePair, the first comparative reasoning-induced creative dataset featuring 8k annotated image pairs, with each sample including a label indicating which image is superior. Additionally, we introduce Creative4U (pronounced Creative for You), a MLLMs-based creative selector that takes into account users' interests. Through Reason-to-Select RFT, which includes supervised fine-tuning with Chain-of-Thought (CoT-SFT) and Group Relative Policy Optimization (GRPO) based reinforcement learning, Creative4U is able to evaluate and select creative images accurately. Both offline and online experiments demonstrate the effectiveness of our approach. Our code and dataset will be made public to advance research and industrial applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_12628 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Creative4U: MLLMs-based Advertising Creative Image Selector with Comparative Reasoning Lin, Yukang Zhang, Xiang Jia, Shichang Wan, Bowen Fu, Chenghan Ren, Xudong Liu, Yueran Guan, Wanxian Wang, Pengji Xu, Jian Zheng, Bo Liu, Baolin Computer Vision and Pattern Recognition Creative image in advertising is the heart and soul of e-commerce platform. An eye-catching creative image can enhance the shopping experience for users, boosting income for advertisers and advertising revenue for platforms. With the advent of AIGC technology, advertisers can produce large quantities of creative images at minimal cost. However, they struggle to assess the creative quality to select. Existing methods primarily focus on creative ranking, which fails to address the need for explainable creative selection. In this work, we propose the first paradigm for explainable creative assessment and selection. Powered by multimodal large language models (MLLMs), our approach integrates the assessment and selection of creative images into a natural language generation task. To facilitate this research, we construct CreativePair, the first comparative reasoning-induced creative dataset featuring 8k annotated image pairs, with each sample including a label indicating which image is superior. Additionally, we introduce Creative4U (pronounced Creative for You), a MLLMs-based creative selector that takes into account users' interests. Through Reason-to-Select RFT, which includes supervised fine-tuning with Chain-of-Thought (CoT-SFT) and Group Relative Policy Optimization (GRPO) based reinforcement learning, Creative4U is able to evaluate and select creative images accurately. Both offline and online experiments demonstrate the effectiveness of our approach. Our code and dataset will be made public to advance research and industrial applications. |
| title | Creative4U: MLLMs-based Advertising Creative Image Selector with Comparative Reasoning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.12628 |