Research map / Vision-language and multimodal / Human and embodied modeling
Fashion Captioning: Towards Generating Accurate Descriptions with Semantic Rewards
Xuewen Yang, Heming Zhang, Di Jin, Yingru Liu, Chi-Hao Wu, Jianchao Tan, Dongliang Xie, Jue Wang, Xin Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add attribute embedding (ablation) | SRFC · FACAD test | CIDEr: 111.8 -> 114.8 | Improved |
| add attribute embedding (ablation) | SRFC · FACAD test | mAP: 0.239 -> 0.240 | Improved |
| add ALS reward (ablation) | SRFC · FACAD test | CIDEr: 110.2 -> 114.8 | Improved |
| add ALS reward (ablation) | SRFC · FACAD test | mAP: 0.233 -> 0.240 | Improved |
| add SLS reward (ablation) | SRFC · FACAD test | CIDEr: 109.7 -> 114.8 | Improved |
| add SLS reward (ablation) | SRFC · FACAD test | ACC: 0.463 -> 0.512 | Improved |
| add both ALS and SLS rewards (ablation) | SRFC · FACAD test | CIDEr: 102.1 -> 114.8 | Improved |
| add attribute embedding, ALS and SLS together (ablation) | SRFC · FACAD test | CIDEr: 98.5 -> 114.8 | Improved |
| add attribute embedding (ablation) | SRFC · FACAD test | ACC: 0.491 -> 0.512 | Improved |
| add ALS reward (ablation) | SRFC · FACAD test | BLEU4: 22.9 -> 24.2 | Improved |
| add SLS reward (ablation) | SRFC · FACAD test | BLEU4: 22.6 -> 24.2 | Improved |
Closest papers by meaning
- Easy Regional Contrastive Learning of Expressive Fashion Representations (NeurIPS 2024 · similarity 0.88)
- Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback (CVPR 2021 · similarity 0.88)
- FashionSAP: Symbols and Attributes Prompt for Fine-Grained Fashion Vision-Language Pre-Training (CVPR 2023 · similarity 0.88)
- FashionViL: Fashion-Focused Vision-and-Language Representation Learning (ECCV 2022 · similarity 0.87)
- FashionVLP: Vision Language Transformer for Fashion Retrieval With Feedback (CVPR 2022 · similarity 0.86)
- FashionERN: Enhance-and-Refine Network for Composed Fashion Image Retrieval (AAAI 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
