AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Collective Deep Quantization for Efficient Cross-Modal Retrieval

Yue Cao, Mingsheng Long, Jianmin Wang, Shichen Liu

AAAI 2017 · Vision-language and multimodal › Cross-modal learning · approach: Cross-modal hashing · 101 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
jointly learn deep representations with collective quantization loss instead of two-step (ablation)CDQ-2 · NUS-WIDE I->Taverage MAP: +2.21%Improved
use adaptive cross-entropy loss instead of pairwise inner-product loss (ablation)CDQ-ip · NUS-WIDE T->Iaverage MAP: +20.91%Improved
add adaptive coefficient alpha in cross-entropy loss (ablation)CDQ-α · MIR-Flickr T->Iaverage MAP: +2.57%Improved
CDQ deep quantization vs CHN deep hashingCHN · NUS-WIDE T->I 32 bitsMAP: 0.7704 -> 0.8478Improved
CDQ deep quantization vs CHN deep hashingCHN · MIR-Flickr I->T 32 bitsMAP: 0.8571 -> 0.8618Improved

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