AI Paper Atlas

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

ECCV 2020 · Vision-language and multimodal › Human and embodied modeling · approach: Neural image captioning · 74 citations (OpenAlex)

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 changedWhereMeasuredEffect
add attribute embedding (ablation)SRFC · FACAD testCIDEr: 111.8 -> 114.8Improved
add attribute embedding (ablation)SRFC · FACAD testmAP: 0.239 -> 0.240Improved
add ALS reward (ablation)SRFC · FACAD testCIDEr: 110.2 -> 114.8Improved
add ALS reward (ablation)SRFC · FACAD testmAP: 0.233 -> 0.240Improved
add SLS reward (ablation)SRFC · FACAD testCIDEr: 109.7 -> 114.8Improved
add SLS reward (ablation)SRFC · FACAD testACC: 0.463 -> 0.512Improved
add both ALS and SLS rewards (ablation)SRFC · FACAD testCIDEr: 102.1 -> 114.8Improved
add attribute embedding, ALS and SLS together (ablation)SRFC · FACAD testCIDEr: 98.5 -> 114.8Improved
add attribute embedding (ablation)SRFC · FACAD testACC: 0.491 -> 0.512Improved
add ALS reward (ablation)SRFC · FACAD testBLEU4: 22.9 -> 24.2Improved
add SLS reward (ablation)SRFC · FACAD testBLEU4: 22.6 -> 24.2Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy