Mengjiao Wang
4 papers · 2017–2023 · 2 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(16)
🐣
Hot Topic Early Bird
Top co-authors
Research topics
Computer Vision
(4)
Deep Learning
(4)
Machine Learning
(4)
Learning Types · Machine Learning
(4)
Learning Types · Deep Learning
(4)
Core AI · Computer Vision
(3)
Core Methods
(3)
Artificial Intelligence
(2)
Core AI · Artificial Intelligence
(2)
Mathematics & Optimization
(1)
Natural Language Processing
(1)
Analysis
(1)
Generation
(1)
Mathematics
(1)
Processing
(1)
Keywords
vision-language pre-training
(2)
image-text alignment
(2)
unsupervised learning
(2)
weakly supervised learning
(1)
image captioning
(1)
cross-modal retrieval
(1)
scene graph
(1)
cross-modal representation
(1)
tensor decomposition
(1)
vision-language model
(1)
systematic generalization
(1)
compositional reasoning
(1)
attribute binding
(1)
higher-order svd
(1)
multimodal pretraining
(1)
visual data
(1)
fashion retrieval
(1)
vision-and-language pretraining
(1)
retrieval-based alignment
(1)
multi-granular alignment
(1)
Papers
Coarse-to-Fine Contrastive Learning in Image-Text-Graph Space for Improved Vision-Language Compositionality
EMNLP 2023
FaD-VLP: Fashion Vision-and-Language Pre-training towards Unified Retrieval and Captioning
EMNLP 2022
Unsupervised Vision-and-Language Pre-Training via Retrieval-Based Multi-Granular Alignment
CVPR 2022
Learning the Multilinear Structure of Visual Data
CVPR 2017