Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2308.09012 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914942168334336 |
|---|---|
| author | Wang, Zhen Li, Da Su, Yulin Yang, Min Qiu, Minghui Wang, Walton |
| author_facet | Wang, Zhen Li, Da Su, Yulin Yang, Min Qiu, Minghui Wang, Walton |
| contents | Logo embedding models convert the product logos in images into vectors, enabling their utilization for logo recognition and detection within e-commerce platforms. This facilitates the enforcement of intellectual property rights and enhances product search capabilities. However, current methods treat logo embedding as a purely visual problem. A noteworthy issue is that visual models capture features more than logos. Instead, we view this as a multimodal task, using text as auxiliary information to facilitate the visual model's understanding of the logo. The emerging Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in both visual and textual understanding. Inspired by this, we propose an approach, \textbf{FashionLOGO}, to explore how to prompt MLLMs to generate appropriate text for product images, which can help visual models achieve better logo embeddings. We adopt a cross-attention transformer block that enables visual embedding to automatically learn supplementary knowledge from textual embedding. Our extensive experiments on real-world datasets prove that FashionLOGO is capable of generating generic and robust logo embeddings, achieving state-of-the-art performance in all benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2308_09012 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | FashionLOGO: Prompting Multimodal Large Language Models for Fashion Logo Embeddings Wang, Zhen Li, Da Su, Yulin Yang, Min Qiu, Minghui Wang, Walton Computer Vision and Pattern Recognition Logo embedding models convert the product logos in images into vectors, enabling their utilization for logo recognition and detection within e-commerce platforms. This facilitates the enforcement of intellectual property rights and enhances product search capabilities. However, current methods treat logo embedding as a purely visual problem. A noteworthy issue is that visual models capture features more than logos. Instead, we view this as a multimodal task, using text as auxiliary information to facilitate the visual model's understanding of the logo. The emerging Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in both visual and textual understanding. Inspired by this, we propose an approach, \textbf{FashionLOGO}, to explore how to prompt MLLMs to generate appropriate text for product images, which can help visual models achieve better logo embeddings. We adopt a cross-attention transformer block that enables visual embedding to automatically learn supplementary knowledge from textual embedding. Our extensive experiments on real-world datasets prove that FashionLOGO is capable of generating generic and robust logo embeddings, achieving state-of-the-art performance in all benchmarks. |
| title | FashionLOGO: Prompting Multimodal Large Language Models for Fashion Logo Embeddings |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2308.09012 |