AI Paper Atlas

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

MTFH: A Matrix Tri-Factorization Hashing Framework for Efficient Cross-Modal Retrieval

Xin Liu, Zhikai Hu, Haibin Ling, Yiu‐ming Cheung

TPAMI 2019 · Vision-language and multimodal › Cross-modal learning · approach: Cross-modal hashing · 226 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
use unequal hash lengths (text 64 bits, image 128 bits) instead of equal 128 bits (ablation)MTFH · Wiki I→T recall top-500recall: 0.3876 -> 0.4093Improved
shrink text code to 16 bits with 128-bit image code instead of 128 bits (ablation)MTFH · Wiki I→T recall top-500recall: 0.3876 -> 0.3041Hurt
use unequal code length 32 for text instead of equal 128 at top-2000 (ablation)MTFH · Wiki I→T recall top-2000recall: 0.9554 -> 0.9640Improved
k-means instead of random sampling in kernel logistic regression (ablation)MTFH · NUS-WIDE-All I→T (128 bits)mAP: 0.6228 -> 0.6271Improved
k-means instead of random sampling in kernel logistic regression (ablation)MTFH · Wiki I→T (128 bits)mAP: 0.3388 -> 0.3349Hurt
k-means instead of random sampling in kernel logistic regression (ablation)MTFH · MIRFlickr T→I (128 bits)mAP: 0.8303 -> 0.8352Improved
MTFH versus DCH (joint hash function and unified code learning), single-label dataMTFH_km · Wiki I→T (128 bits)mAP: 0.3783 -> 0.3349Hurt
MTFH versus DCH on multi-label large datasetMTFH_km · NUS-WIDE-All T→I (128 bits)mAP: 0.5298 -> 0.7307Improved
MTFH versus SePH on multi-label datasetMTFH_km · MIRFlickr I→T (128 bits)mAP: 0.6851 -> 0.7676Improved
MTFH versus DCH at 32 bits, top-50 precisionTMFH_rnd · NUS-WIDE-100k I→TmAP@50: 0.6396 -> 0.7337Improved
MTFH versus DCH at 32 bits, top-50 precisionMTFH · MIRFlickr T→I (32 bits)mAP@50: 0.8923 -> 0.8624Hurt
use unequal code lengths 80 and 100 instead of 100 and 100 (ablation)MTFH · MIRFlickrmAPImproved

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