AI Paper Atlas

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

Finding It at Another Side: A Viewpoint-Adapted Matching Encoder for Change Captioning

Xiangxi Shi, Xu Yang, Jiuxiang Gu, Shafiq Joty, Jianfei Cai

ECCV 2020 · Vision-language and multimodal › Human and embodied modeling · approach: Concept-guided image captioning · 61 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 reinforcement attention fine-tuning (RAF) to M-VAM (ablation)M-VAM · Spot-the-DiffBLEU4: 10.1 -> 11.1Improved
add reinforcement attention fine-tuning (RAF) to M-VAM (ablation)M-VAM · Spot-the-DiffROUGE_L: 31.3 -> 33.2Improved
add reinforcement attention fine-tuning (RAF) to M-VAM (ablation)M-VAM · Spot-the-DiffCIDEr: 38.1 -> 42.5Improved
add reinforcement attention fine-tuning (RAF) to M-VAM (ablation)M-VAM · Spot-the-DiffSPICE: 14.0 -> 17.1Improved
add reinforcement attention fine-tuning (RAF) to M-VAM (ablation)M-VAM · Spot-the-DiffMETEOR: 12.4 -> 12.9Improved
add reinforcement attention fine-tuning (RAF) to M-VAM (ablation)M-VAM · CLEVR-Change (with distractor)BLEU4: 50.3 -> 51.3Improved
add reinforcement attention fine-tuning (RAF) to M-VAM (ablation)M-VAM · CLEVR-Change (with distractor)CIDEr: 114.9 -> 115.8Improved
add reinforcement attention fine-tuning (RAF) to M-VAM (ablation)M-VAM · CLEVR-Change (with distractor)SPICE: 30.5 -> 30.7Improved
add reinforcement attention fine-tuning (RAF) to M-VAM (ablation)M-VAM · CLEVR-Change (without distractor)BLEU4: 45.5 -> 50.1Improved
add reinforcement attention fine-tuning (RAF) to M-VAM (ablation)M-VAM · CLEVR-Change (without distractor)CIDEr: 117.4 -> 119.1Improved
add reinforcement attention fine-tuning (RAF) to M-VAM (ablation)M-VAM · CLEVR-Change (without distractor)SPICE: 29.4 -> 31.2Improved
train without distractor image pairsM-VAM + RAF · CLEVR-ChangeSPICE: 30.7 -> 31.2Improved

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