AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

``Factual'' or ``Emotional'': Stylized Image Captioning with Adaptive Learning and Attention

Tianlang Chen, Zhongping Zhang, Quanzeng You, Chen Fang, Zhaowen Wang, Hailin Jin, Jiebo Luo

ECCV 2018 · Vision-language and multimodal › Human and embodied modeling · approach: Neural image captioning · 92 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 adaptive learning with reference factual model (ablation)SF-LSTM · FlickrStyle10K humorous, factual refsCIDEr: 28.2 -> 34.2Improved
add adaptive learning with reference factual model (ablation)SF-LSTM · FlickrStyle10K humorous, factual refsBLEU-4: 13.1 -> 15.4Improved
add adaptive learning with reference factual model (ablation)SF-LSTM · FlickrStyle10K romantic, factual refsCIDEr: 23.5 -> 26.7Improved
add adaptive learning with reference factual model (ablation)SF-LSTM · FlickrStyle10K romantic, factual refsBLEU-4: 12.8 -> 13.5Improved
add adaptive learning with reference factual model (ablation)SF-LSTM · FlickrStyle10K humorous, stylized refsCIDEr: 39.8 -> 39.5No clear effect
add adaptive learning with reference factual model (ablation)SF-LSTM · FlickrStyle10K humorous, stylized refsBLEU-4: 4.9 -> 5.1Improved
add adaptive learning with reference factual model (ablation)SF-LSTM · FlickrStyle10K romantic, stylized refsCIDEr: 37.4 -> 37.5No clear effect
add adaptive learning with reference factual model (ablation)SF-LSTM · FlickrStyle10K romantic, stylized refsBLEU-4: 4.9 -> 4.8No clear effect
use style-factual LSTM instead of fine-tuned NICSF-LSTM · FlickrStyle10K humorous, stylized refsCIDEr: 35.4 -> 39.8Improved
use style-factual LSTM instead of fine-tuned NICSF-LSTM · FlickrStyle10K romantic, factual refsCIDEr: 24.0 -> 23.5No clear effect
use SF-LSTM + Adap instead of SentiCapSF-LSTM + Adap · Image sentiment captioning, POS test setCIDEr: 54.4 -> 60.0Improved
use SF-LSTM + Adap instead of SentiCapSF-LSTM + Adap · Image sentiment captioning, NEG test setCIDEr: 61.8 -> 59.7Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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