Výsledky vyhledávání

Report

M2-Encoder: Advancing Bilingual Image-Text Understanding by Large-scale Efficient Pretraining

Autor: Guo, Qingpei, Xu, Furong, Zhang, Hanxiao, Ren, Wang, Ma, Ziping, Ju, Lin, Wang, Jian, Chen, Jingdong, Yang, Ming

Vision-language foundation models like CLIP have revolutionized the field of artificial intelligence. Nevertheless, VLM models supporting multi-language, e.g., in both Chinese and English, have lagged due to the relative scarcity of large-scale pretr

Externí odkaz: http://arxiv.org/abs/2401.15896

Zobrazit plný text záznamu

Report

SyCoCa: Symmetrizing Contrastive Captioners with Attentive Masking for Multimodal Alignment

Autor: Ma, Ziping, Xu, Furong, Liu, Jian, Yang, Ming, Guo, Qingpei

Multimodal alignment between language and vision is the fundamental topic in current vision-language model research. Contrastive Captioners (CoCa), as a representative method, integrates Contrastive Language-Image Pretraining (CLIP) and Image Caption

Externí odkaz: http://arxiv.org/abs/2401.02137

Zobrazit plný text záznamu

Akademický článek

Sparse Feature-Weighted Double Laplacian Rank Constraint Non-Negative Matrix Factorization for Image Clustering.

Autor: Ma, Hu¹ (AUTHOR), Ma, Ziping¹ (AUTHOR) 2006041@nmu.edu.cn, Li, Huirong² (AUTHOR), Wang, Jingyu¹ (AUTHOR)

Publikováno v: Mathematics (2227-7390). Dec2024, Vol. 12 Issue 23, p3656. 32p.

Zobrazit plný text záznamu

Plný text ve formátu HTML

Akademický článek

Pre-weighted Modulated Dense Graph Convolutional Networks for 3D Human Pose Estimation

Autor: MA Jinlin, CUI Qilei, MA Ziping, YAN Qi, CAO Haojie, WU Jiangtao

Publikováno v: Jisuanji kexue yu tansuo, Vol 18, Iss 4, Pp 963-977 (2024)

Graph convolutional networks (GCN) have increasingly become one of the main research hotspots in 3D human pose estimation. The method of modeling the relationship between human joint points by GCN has achieved good performance in 3D human pose estima

Externí odkaz: https://doaj.org/article/cd8fb109de014457ba97cbff59595c49

Zobrazit plný text záznamu

Akademický článek

Unsupervised feature selection based on minimum-redundant subspace learning with self-weighted adaptive graph

Autor: Ma, Ziping, Wei, Yilong, Huang, Yulei, Wang, Jingyu

Publikováno v: In Digital Signal Processing December 2024 155

Zobrazit plný text záznamu

Akademický článek

HSKDLR: Lightweight Lip Reading Method Based on Homogeneous Self-Knowledge Distillation

Autor: MA Jinlin, LIU Yuhao, MA Ziping, GONG Yuanwen, ZHU Yanbin

Publikováno v: Jisuanji kexue yu tansuo, Vol 17, Iss 11, Pp 2689-2702 (2023)

In order to solve the problems of low recognition rate and large amount of calculation in lip reading, this paper proposes a lightweight model for lip reading named HSKDLR （homogeneous self-knowledge distillation for lip reading）. Firstly, the S-

Externí odkaz: https://doaj.org/article/9954e5d7425c477d9761efe66c82ae59

Zobrazit plný text záznamu