Deconfounded fashion image captioning with transformer and multimodal retrieval
Background: The annotation of fashion images is a significantly important task in the fashion industry as well as social media and e-commerce. However, owing to the complexity and diversity of fashion images, this task entails multiple challenges, including the lack of fine-grained captions and conf...
সংরক্ষণ করুন:
| প্রধান লেখক: | , , , , |
|---|---|
| বিন্যাস: | Artigo |
| ভাষা: | Inglês |
| প্রকাশিত: |
KeAi Communications Co., Ltd.
2025-04-01
|
| মালা: | Virtual Reality & Intelligent Hardware |
| বিষয়গুলি: | |
| অনলাইন ব্যবহার করুন: | http://www.sciencedirect.com/science/article/pii/S2096579624000494 |
| ট্যাগগুলো: |
কোনো ট্যাগ নেই, প্রথমজন হিসাবে ট্যাগ করুন!
|