AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Learning to Compose and Reason with Language Tree Structures for Visual Grounding

Richang Hong, Daqing Liu, Xiaoyu Mo, Xiangnan He, Hanwang Zhang

TPAMI 2019 · Vision-language and multimodal › Multimodal LLMs · approach: Chain-of-thought multimodal reasoning · 206 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
replace holistic BiLSTM chain encoder with parser tree (TreeLSTM) (ablation)Chain · RefCOCOg test (GT boxes)Top-1 accuracy (%): 71.69 -> 73.07Improved
learn tree with supervised pre-training instead of from scratch (ablation)RvG-Tree-Scratch · RefCOCOg test (GT boxes)Top-1 accuracy (%): 72.00 -> 75.20Improved
add in-node score (ablation)RvG-Tree/Node · RefCOCOg test (GT boxes)Top-1 accuracy (%): 74.36 -> 75.20Improved
add recursive score accumulation from score node (ablation)RvG-Tree/S · RefCOCOg test (GT boxes)Top-1 accuracy (%): 73.18 -> 75.20Improved
add pairwise score from feature node (ablation)RvG-Tree/F · RefCOCOg test (GT boxes)Top-1 accuracy (%): 73.98 -> 75.20Improved
add recursive tree-structured grounding score on top of tree encoder (ablation)RvG-Tree-Fix · RefCOCOg val (GT boxes)Top-1 accuracy (%): 73.69 -> 76.82Improved
add pairwise score from feature node (ablation)RvG-Tree/F · RefCOCOg val (GT boxes)Top-1 accuracy (%): 74.12 -> 76.82Improved
add in-node score (ablation)RvG-Tree/Node · RefCOCO+ testB (detected boxes)Top-1 accuracy (%): 55.72 -> 56.66Improved
learn tree from scratch instead of expert pretraining (ablation)RvG-Tree-Scratch · RefCOCO val (GT boxes)Top-1 accuracy (%): 83.48 -> 79.65Hurt
replace MMI cross-entropy loss with triplet loss with hard negatives (ablation)RvG-Tree · RefCOCO familyTop-1 accuracy (%)No clear effect
use random instead of GloVe word initialization (ablation)RvG-Tree · RefCOCO familyTop-1 accuracy (%)No clear effect
use REINFORCE instead of straight-through Gumbel-Softmax (ablation)RvG-Tree · RefCOCO familyTop-1 accuracy (%): 1e-6Hurt

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