AI Paper Atlas

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

Attention-aware Deep Adversarial Hashing for Cross-Modal Retrieval

Xi Zhang, Hanjiang Lai, Jiashi Feng

ECCV 2018 · Vision-language and multimodal › Cross-modal learning · approach: Cross-modal hashing · 140 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 HashGAN attention-aware adversarial hashing instead of DCMHDCMH · IAPR TC-12 text->image 16 bitsMAP: 0.5185 -> 0.5358Improved
add HashGAN instead of DCMHDCMH · IAPR TC-12 image->text 16 bitsMAP: 0.4526 -> 0.5293Improved
add HashGAN instead of DCMHDCMH · MIR-Flickr 25k text->image 32 bitsMAP: 0.7900 -> 0.8062Improved
add HashGAN instead of DCMHDCMH · MIR-Flickr 25k image->text 64 bitsMAP: 0.7485 -> 0.7720Improved
add HashGAN instead of DCMHDCMH · NUS-WIDE text->image 64 bitsMAP: 0.6571 -> 0.6939Improved
add HashGAN instead of DCMHDCMH · NUS-WIDE image->text 32 bitsMAP: 0.6031 -> 0.6258Improved
use VGG instead of smaller CNN-F image network (ablation)HashGAN · IAPR TC-12 text->image 16 bitsMAP: 0.5267 -> 0.5358Improved
use VGG instead of smaller CNN-F image network (ablation)HashGAN · IAPR TC-12 text->image 64 bitsMAP: 0.5538 -> 0.5648Improved
use VGG instead of smaller CNN-F image network (ablation)HashGAN · IAPR TC-12 image->text 32 bitsMAP: 0.5168 -> 0.5283Improved
use VGG instead of smaller CNN-F image network (ablation)HashGAN · IAPR TC-12 image->text 64 bitsMAP: 0.5208 -> 0.5439Improved
increase hash code length from 16 to 64 bitsHashGAN · MIR-Flickr 25k text->imageMAP: 0.7922 -> 0.8074Improved
increase hash code length from 16 to 64 bitsHashGAN · NUS-WIDE image->textMAP: 0.6300 -> 0.6468Improved

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