AI Paper Atlas

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

Deep Joint-Semantics Reconstructing Hashing for Large-Scale Unsupervised Cross-Modal Retrieval

Shupeng Su, Zhisheng Zhong, Chao Zhang

ICCV 2019 · Vision-language and multimodal › Cross-modal learning · approach: Cross-modal hashing · 371 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
merge image and text affinity matrices by weighted sum instead of image affinity alone (ablation)DJSRH-1 · NUS-WIDE I->T (128 bits)mAP@50: 0.741 -> 0.747Improved
merge affinities by weighted sum instead of text affinity alone (ablation)DJSRH-2 · NUS-WIDE T->I (128 bits)mAP@50: 0.581 -> 0.738Improved
add high order neighborhood information (eta = 0.4) (ablation)DJSRH-3 · NUS-WIDE I->T (128 bits)mAP@50: 0.747 -> 0.803Improved
add high order neighborhood information (eta = 0.4) (ablation)DJSRH-3 · NUS-WIDE T->I (128 bits)mAP@50: 0.738 -> 0.757Improved
add regulation parameter mu = 1.5 (ablation)DJSRH-4 · NUS-WIDE I->T (128 bits)mAP@50: 0.803 -> 0.812Improved
add regulation parameter mu = 1.5 (ablation)DJSRH-4 · NUS-WIDE T->I (128 bits)mAP@50: 0.757 -> 0.768Improved
add intra-modal reconstruction terms (lambda1 = lambda2 = 0.1) (ablation)DJSRH-5 · NUS-WIDE T->I (128 bits)mAP@50: 0.768 -> 0.789Improved
add intra-modal reconstruction terms (lambda1 = lambda2 = 0.1) (ablation)DJSRH-5 · NUS-WIDE I->T (128 bits)mAP@50: 0.812 -> 0.817Improved
use tightening tanh (increasing alpha) instead of constant tanh (ablation)DJSRH · NUS-WIDE I->T (128 bits)mAP@50: 0.811 -> 0.817Improved
use tightening tanh (increasing alpha) instead of constant tanh (ablation)DJSRH · NUS-WIDE T->I (128 bits)mAP@50: 0.782 -> 0.789Improved
reconstruct specific similarity values instead of Laplacian constraint (DJSRH-1 vs UDCMH)DJSRH-1 · NUS-WIDE I->T (128 bits)mAP@50: 0.558 -> 0.741Improved
use DJSRH instead of UDCMH on small datasetDJSRH · Wiki T->I (128 bits)mAP@50: 0.658 -> 0.658No clear effect

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