AI Paper Atlas

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

Context-Aware Visual Policy Network for Fine-Grained Image Captioning

Zheng-Jun Zha, Daqing Liu, Hanwang Zhang, Yongdong Zhang, Feng He Wu

TPAMI 2019 · Vision-language and multimodal › Human and embodied modeling · approach: Concept-guided image captioning · 152 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 explicit visual context via CAVP sub-policies (vs single sub-policy) (ablation)Up-Down · MS-COCO Karpathy test (ablation)CIDEr: 121.9 -> 126.3Improved
memorize full historical visual context rather than only last visual feature (ablation)CAVP · MS-COCO Karpathy test (ablation)CIDEr: 124.5 -> 126.3Improved
behavior cloning of output sub-policy from language-parser expert (ablation)CAVP · MS-COCO Karpathy test (ablation)CIDEr: 124.5 -> 124.6No clear effect
share LSTM weights among sub-policy networks (ablation)CAVP · MS-COCO Karpathy test (ablation)CIDEr: 126.4 -> 126.3No clear effect
share LSTM weights among sub-policy networks (ablation)CAVP · Efficiencyparameters (M): 108.5M -> 83.0MImproved
add CAVP to Up-DownUp-Down · Efficiencytesting time (ms/image): 44.40 -> 56.48Hurt
optimize CIDEr instead of BLEU reward (ablation)CAVP · MS-COCO Karpathy test (ablation)CIDEr: 114.5 -> 126.4Improved
optimize SPIDEr instead of CIDEr reward (ablation)CAVP · MS-COCO Karpathy test (ablation)SPICE: 21.6 -> 23.1Improved
optimize METEOR reward instead of CIDEr (ablation)CAVP · MS-COCO Karpathy test (ablation)BLEU-4: 38.3 -> 33.6Hurt
add sentence-level CAVP visual context (ablation)Single Policy · Stanford image-paragraphCIDEr: 16.36 -> 17.29Improved
add hierarchical sentence-level and word-level visual policies (ablation)Sentence CAVP · Stanford image-paragraphCIDEr: 17.29 -> 19.63Improved
add CIDEr reinforcement training to hierarchical CAVP_XE (ablation)Hierarchical CAVP · Stanford image-paragraphCIDEr: 19.63 -> 20.94Improved

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