AI Paper Atlas

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

Multi-modal Dependency Tree for Video Captioning

Wentian Zhao, Xinxiao Wu, Jiebo Luo

NeurIPS 2021 · Vision-language and multimodal › Human and embodied modeling · approach: Concept-guided image captioning · 11 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 dependency-tree structure instead of chain-structured sequence (ablation)Multi-modal dependency tree captioner · ActivityNet Captions (GT proposals, C3D)CIDEr: 42.30 -> 44.13Improved
add dependency-tree structure instead of chain (ablation)captioner · Charades CaptionsCIDEr: 23.50 -> 24.21Improved
add RL fine-tuning stage (ablation)captioner · ActivityNet Captions (GT proposals, C3D)CIDEr: 38.90 -> 44.13Improved
add RL fine-tuning stage (ablation)captioner · Charades CaptionsCIDEr: 22.53 -> 24.21Improved
add visual feature to tree-node embeddings (ablation)captioner · ActivityNet Captions (GT proposals, C3D)CIDEr: 35.10 -> 44.13Improved
add visual feature to tree-node embeddings (ablation)captioner · Charades CaptionsCIDEr: 21.87 -> 24.21Improved
use node-level reward instead of sequence-level reward (ablation)captioner · ActivityNet Captions (GT proposals, C3D)CIDEr: 41.39 -> 44.13Improved
use node-level reward instead of sequence-level reward (ablation)captioner · Charades CaptionsCIDEr: 23.41 -> 24.21Improved
use tree structure on complex-sentence subset (ablation)captioner · Charades complex subsetROUGE-L: 33.3 -> 39.8Improved
use tree structure on simple-sentence subset (ablation)captioner · Charades simple subsetCIDEr: 28.4 -> 25.8Hurt
use BLEU-4 instead of CIDEr in the reward (ablation)captioner · Charades CaptionsCIDEr: 24.21 -> 22.95Hurt
use ROUGE-L instead of CIDEr in the reward (ablation)captioner · Charades CaptionsCIDEr: 24.21 -> 22.32Hurt

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