Mingliang Liang

According to our database, Mingliang Liang authored at least 12 papers between 2021 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

Dynamic Cluster Data Sampling for Efficient and Long-Tail-Aware Vision-Language Pre-training.

Mingliang Liang, Zhuoran Liu, Arjen P. de Vries, Martha A. Larson

CoRR, April, 2026

Frequency Is What You Need: Considering Word Frequency When Text Masking Benefits Vision-Language Model Pre-training.

Mingliang Liang, Martha A. Larson

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2026

2025

Enhancing Vision-Language Model Pre-Training with Image-Text Pair Pruning Based on Word Frequency.

Mingliang Liang, Martha A. Larson

Proceedings of the International Conference on Content-Based Multimedia Indexing, 2025

2024

Frequency Is What You Need: Word-frequency Masking Benefits Vision-Language Model Pre-training.

Mingliang Liang, Martha A. Larson

CoRR, 2024

Centered Masking for Language-Image Pre-training.

Mingliang Liang, Martha A. Larson

Proceedings of the Machine Learning and Knowledge Discovery in Databases. Research Track and Demo Track, 2024

Mutant Texts: A Technique for Uncovering Unexpected Inconsistencies in Large-Scale Vision-Language Models.

Mingliang Liang, Zhouran Liu, Martha A. Larson

Proceedings of the MultiMedia Modeling - 30th International Conference, 2024

2023

Textual Concept Expansion with Commonsense Knowledge to Improve Dual-Stream Image-Text Matching.

Mingliang Liang, Zhuoran Liu, Martha A. Larson

Proceedings of the MultiMedia Modeling - 29th International Conference, 2023

Investigating the Performance of the CLIP Model and Concept Matching in Text-Image Retrieval Systems.

Xiaomeng Wang, Mingliang Liang, Martha A. Larson

Proceedings of the Working Notes Proceedings of the MediaEval 2023 Workshop, 2023

Subsampling of Frequent Words in Text for Pre-training a Vision-Language Model.

Mingliang Liang, Martha A. Larson

Proceedings of the 1st Workshop on Large Generative Models Meet Multimodal Applications, 2023

2022

NewsImages: addressing the depiction gap with an online news dataset for text-image rematching.

Andreas Lommatzsch, Benjamin Kille, Özlem Özgöbek, Yuxiao Zhou, Jelena Tesic, Cláudio Bartolomeu, David Semedo, Lidia Pivovarova, Mingliang Liang, Martha A. Larson

Proceedings of the MMSys '22: 13th ACM Multimedia Systems Conference, Athlone, Ireland, June 14, 2022

Textual Concept Expansion for Text-Image Matching within Online News Content.

Mingliang Liang, Martha A. Larson

Proceedings of the Working Notes Proceedings of the MediaEval 2022 Workshop, 2022

2021

Exploring a Pre-trained Model for Re-Matching News Texts and Images.

Mingliang Liang, Martha A. Larson

Proceedings of the Working Notes Proceedings of the MediaEval 2021 Workshop, 2021