Search Result

1

Review of research on fake news detection based on multimodal dynamic graph learning

基于多模态动态图学习的假新闻检测研究综述

Yang Yu

Guo Rui

Gao Minna

Wang Yifan

Lu Yaolin

fake news detection

multimodal Fusion

dynamic graph learning

lightweight design

Accepted Paper No. 12, 2025 : doi:10.19734/j.issn.1001-3695.2025.04.0136

2

Photovoltaic power prediction based on finite scalar quantization and staged cross-modal attention fusion

基于有限标量量化与分阶段跨模态注意力融合的光伏功率预测

Zhang Haiqing

Liu Jialing

Tang Dan

Xiang Xiaoming

Yang Dong

Guo Benjun

photovoltaic power prediction

multi-modal fusion

information alignment

finite scalar quantization

Accepted Paper No. 12, 2025 : doi:10.19734/j.issn.1001-3695.2025.05.0159

3

SFN-D: depth completion method for sparse depth maps in autonomous driving

面向自动驾驶的稀疏深度图补全方法SFN-D

Wu Bin

Zhao Haiyan

Cao Jian

Chen Qingkui

depth completion

multimodal Fusion

autonomous driving

sparse depth map

Accepted Paper No. 10, 2025 : doi:10.19734/j.issn.1001-3695.2025.02.0053

4

Multimodal named entity recognition method based on multi-granularity progressive fusion

基于多粒度渐进式融合的多模态命名实体识别方法

Ying Xujian

Zhu Yanhui

Chen Hao

Man Fangteng

Zhang Zhixuan

multimodal named entity recognition

multimodal fusion

multi-granularity

progressive fusion

named entity recognition

Accepted Paper No. 10, 2025 : doi:10.19734/j.issn.1001-3695.2025.03.0071

5

Multimodal sentiment analysis model based on multi-task joint learning and adaptive fusion

基于多任务联合学习与自适应融合的多模态情感分析模型

Fan Jidong

Zhong Zhaoman

Han Tianle

Li Menghan

Cui Xinru

Xu Jin

multimodal emotion analysis

multi-tasking

heterogeneous characteristics

self-adaptive fusion

multiscale feature

multimodal fusion

Accepted Paper No. 9, 2025 : doi:10.19734/j.issn.1001-3695.2025.03.0038

6

Multimodal medical image fusion algorithm for edge texture preservation

针对边缘纹理保留的多模态医学图像融合算法

Ke Changhao

Wang Xiaoming

deep learning

medical image

multimodal Fusion

edge texture preservation

texture information mask

feature Fusion

feature extraction

Accepted Paper No. 8, 2025 : doi:10.19734/j.issn.1001-3695.2024.11.0507

7

Review of multimodal pedestrian re-identification

多模态行人重识别研究综述

Shi Ruixin

Zhi Min

Yin Yanjun

RE-ID

multimodal fusion

data fusion

feature fusion

model fusion

No. 7, 2025 : 1921-1929 doi:10.19734/j.issn.1001-3695.2024.11.0433

8

Human emotion recognition in images based on text-image contrastive fusion

基于图文对比融合的图像人物情感识别

Tian Yule

Wang Yiding

emotion recognition

vision-language model

context awareness

multimodal fusion

No. 7, 2025 : 1972-1977 doi:10.19734/j.issn.1001-3695.2024.12.0497

9

Deep feature interaction and hierarchical multimodal fusion for emotion recognition

基于深度特征交互与层次化多模态融合的情感识别模型

Wang Jian

Zhao Xiaoming

Wang Chenglong

Zhang Shiqing

Zhao Shuchang

multimodal emotion recognition

hierarchical fusion

multi-scale fusion

feature fusion

No. 7, 2025 : 1978-1985 doi:10.19734/j.issn.1001-3695.2024.11.0487

10

Multi-modal pedestrian crossing intention prediction model based on pre-normalization Transformer

基于前置归一化Transformer的融合多模态行人过街意图预测模型

Chen Zhendong

Liu Guangcong

Ye Zhenyu

pedestrian crossing

intention prediction

multi-model fusion

Transformer

No. 5, 2025 : 1378-1384 doi:10.19734/j.issn.1001-3695.2024.10.0428

11

3D multi-object tracking with multi-modal embedding and trajectory correction

多模态嵌入与轨迹修正的三维多目标跟踪

Zhao Guowei

Liu Hengyuan

Li Hui

Qin Xiugong

Yang Haoran

Tao Ye

multi-object tracking

multi-modal fusion

track embedding

trajectory correction

No. 12, 2024 : 3859-3865 doi:10.19734/j.issn.1001-3695.2024.01.0066

12

Multimodal misinformation detection model with social network graph

结合社交网络图的多模态虚假信息检测模型

Ye Zhoubo

Luo Shun

Yu Juan

online public opinion

misinformation detection

multimodal fusion

multimodal co-attention

social network graph

No. 7, 2024 : 1992-1998 doi:10.19734/j.issn.1001-3695.2023.11.0565

13

Textual-visual semantics-enhanced multimodal named entity recognition method

图文语义增强的多模态命名实体识别方法

Xu Xi

Wang Hairong

Wang Tong

Ma He

multimodal named entity recognition

multimodal representation

multimodal fusion

multi-task learning

named entity recognition

No. 6, 2024 : 1679-1685 doi:10.19734/j.issn.1001-3695.2023.09.0439

14

Multimodal sentiment analysis based on non-text modality reinforcement and gating fusion method

基于非文本模态强化和门控融合方法的多模态情感分析

Wei Jinlong

Shao Xinhui

multimodal sentiment analysis

multimodal fusion

modality reinforcement

gating mechanism

No. 1, 2024 : 39-44 doi:10.19734/j.issn.1001-3695.2023.04.0213

15

MP3DVG：modal pre-fusion for 3D visual grounding

基于模态预融合的三维指称表达理解

Yuan Kunpeng

Mi Jinpeng

Chen Zhiqian

3D visual grounding

multi-modal fusion

overfitting

attention

No. 12, 2023 : 3666-3671,3677 doi:10.19734/j.issn.1001-3695.2023.04.0150

16

Continuous emotion recognition based on perceiver resampling and multimodal fusion

基于感知重采样和多模态融合的连续情感识别

Li Jian

Zhang Qian

Chen Haifeng

Li Jing

Wang Liyan

Pei Ercheng

emotion recognition

perceiver resampling

multimodal fusion

attention mechanism

No. 12, 2023 : 3816-3820 doi:10.19734/j.issn.1001-3695.2023.04.0217

17

Fine-grained classification based on modal correlation learning

基于模态相关性学习的细粒度分类

Zhang Tianshu

Liu Fan

Dai Wenwen

Gao Ruizhuo

fine-grained classification

multimodal fusion

correspondence learning

No. 11, 2023 : 3450-3455,3461 doi:10.19734/j.issn.1001-3695.2023.03.0137

18

Speech emotion recognition based on multi-modal fusion of graph neural network

基于图神经网络多模态融合的语音情感识别模型

Li Zijing

Chen Ning

speech emotion recognition

multi-modal feature

graph neural network

graph augmentation

No. 8, 2023 : 2286-2291,2310 doi:10.19734/j.issn.1001-3695.2023.01.0002

19

Multimodal sentiment analysis based on cross-modal gating mechanism and improved fusion method

基于跨模态门控机制和改进融合方法的多模态情感分析

Miao Yuqing

Yang Shuang

Liu Tonglai

Zhang Wanzhen

Zhu Lin

Zhou Ming

multimodal sentiment analysis

inter-modal noise

cross-modal gating mechanism

multimodal fusion

No. 7, 2023 : 2025-2030,2038 doi:10.19734/j.issn.1001-3695.2022.12.0766

20

Group activity recognition based on selective fusion and relational reasoning

基于选择性融合及关系推理的群组行为识别

Liu Sifan

Lin Guocheng

Qin Jianwei

Wang Chuanxu

group activity recognition

multi-modal fusion

interaction relation reasoning

behavior recognition

No. 3, 2023 : 914-918,924 doi:10.19734/j.issn.1001-3695.2022.07.0346

21

Multimodal fusion for video captioning on urban road scene

基于多模态融合的城市道路场景视频描述模型研究

Li Mingxing

Xu Cheng

Li Xuewei

Liu Hongzhe

Yan Chenyang

Liao Wensen

video caption

multimodal fusion

attention mechanism

intelligent driving

No. 2, 2023 : 607-611,640 doi:10.19734/j.issn.1001-3695.2022.06.0275

22

Matrix factorized bilinear pooling for multi-modal fusion fake news detection

基于矩阵分解双线性池化的多模态融合虚假新闻检测

Wang Jie

Liu Yun

Ji Shujuan

fake news detection

social media

multi-modal

bilinear pooling

deep learning

No. 10, 2022 : 2968-2973,2978 doi:10.19734/j.issn.1001-3695.2022.03.0139

23

Research on visual question answering model based on composite graphic features

基于复合图文特征的视觉问答模型研究

Qiu Nan

Gu Yuwan

Shi Lin

Li Ning

Zhuang Lihua

Xu Shoukun

visual question answering

composite vision linguistic feature

regional feature

multimodal fusion

No. 8, 2021 : 2293-2298 doi:10.19734/j.issn.1001-3695.2020.12.0537

24

3D model retrieval algorithm based on multimodal fusion

基于多模态融合的三维模型检索算法研究

Wang Ya

Zheng Bowen

Zhang Xin

3D models

multi-modal

deep-learning

information fusion

No. 3, 2021 : 685-688,695 doi:10.19734/j.issn.1001-3695.2020.02.0086

25

Hard attention based multi-modal fusion for video caption generation

基于硬注意力机制的多模态视频字幕的处理

Guo Ningning

Jiang Linhua

encoder-decoder

multi-modal fusion

attention mechanism

No. 3, 2021 : 956-960 doi:10.19734/j.issn.1001-3695.2019.11.0691

26

Survey of multimodal deep learning

多模态深度学习综述

Liu Jianwei

Ding Xihao

Luo Xionglin

multimodal

deep learning

neural network

multimodal representation

multimodal interpretation

multimodal fusion

multimodal alignment

No. 6, 2020 : 1601-1614 doi:10.19734/j.issn.1001-3695.2018.12.0857

Search 多模态融合

Search多模态融合returned 26 results

Review of research on fake news detection based on multimodal dynamic graph learning

Photovoltaic power prediction based on finite scalar quantization and staged cross-modal attention fusion

SFN-D: depth completion method for sparse depth maps in autonomous driving

Multimodal named entity recognition method based on multi-granularity progressive fusion

Multimodal sentiment analysis model based on multi-task joint learning and adaptive fusion

Multimodal medical image fusion algorithm for edge texture preservation

Review of multimodal pedestrian re-identification

Human emotion recognition in images based on text-image contrastive fusion

Deep feature interaction and hierarchical multimodal fusion for emotion recognition

Multi-modal pedestrian crossing intention prediction model based on pre-normalization Transformer

3D multi-object tracking with multi-modal embedding and trajectory correction

Multimodal misinformation detection model with social network graph

Textual-visual semantics-enhanced multimodal named entity recognition method

Multimodal sentiment analysis based on non-text modality reinforcement and gating fusion method

MP3DVG：modal pre-fusion for 3D visual grounding

Continuous emotion recognition based on perceiver resampling and multimodal fusion

Fine-grained classification based on modal correlation learning

Speech emotion recognition based on multi-modal fusion of graph neural network

Multimodal sentiment analysis based on cross-modal gating mechanism and improved fusion method

Group activity recognition based on selective fusion and relational reasoning

Multimodal fusion for video captioning on urban road scene

Matrix factorized bilinear pooling for multi-modal fusion fake news detection

Research on visual question answering model based on composite graphic features

3D model retrieval algorithm based on multimodal fusion

Hard attention based multi-modal fusion for video caption generation

Survey of multimodal deep learning