AI Paper Atlas

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

Cross-Modal Deep Variational Hashing

Venice Erin Liong, Jiwen Lu, Yap-Peng Tan, Jie Zhou

ICCV 2017 · Vision-language and multimodal › Cross-modal learning · approach: Cross-modal hashing · 100 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 latent network to fusion network (ablation)CMDVH · NUS-WIDE image-to-text, 16 bitsmAP: 0.7864 -> 0.8503Improved
add latent network to fusion network (ablation)CMDVH · NUS-WIDE image-to-text, 128 bitsmAP: 0.8666 -> 0.8910Improved
add latent network to fusion network (ablation)CMDVH · NUS-WIDE text-to-image, 16 bitsmAP: 0.7390 -> 0.8270Improved
add latent network to fusion network (ablation)CMDVH · NUS-WIDE text-to-image, 128 bitsmAP: 0.8504 -> 0.8782Improved
add probabilistic interpretation to modality-specific networks (ablation)CMDVH · NUS-WIDE image-to-text, 16 bitsmAP: 0.8234 -> 0.8503Improved
add probabilistic interpretation to modality-specific networks (ablation)CMDVH · NUS-WIDE image-to-text, 128 bitsmAP: 0.8821 -> 0.8910Improved
add probabilistic interpretation to modality-specific networks (ablation)CMDVH · NUS-WIDE text-to-image, 16 bitsmAP: 0.7992 -> 0.8270Improved
add probabilistic interpretation to modality-specific networks (ablation)CMDVH · NUS-WIDE text-to-image, 128 bitsmAP: 0.8583 -> 0.8782Improved
use CMDVH instead of SePH-kmSePH-km · Wiki image-to-text, 128 bitsmAP: 0.4472 -> 0.4442Mixed
use CMDVH instead of DisCMHDisCMH · NUS-WIDE image-to-text, 128 bitsmAP: 0.7605 -> 0.8910Improved
use CMDVH instead of DVSHDVSH · IAPRTC12 image-to-text, 128 bitsmAP: 0.7236 -> 0.7902Improved
use CMDVH instead of DCMHDCMH · NUS-WIDE image-to-text, 64 bitsmAP: 0.6720 -> 0.8801Improved

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