搜索Transformer共有 44 个结果
1
Multi-emotion driven virtual speaker generation method integrating mul-tiple emotions
Accepted Paper
2024年第8期 :
doi:10.19734/j.issn.1001-3695.2023.10.0559
2
Ct-jie: collaborative transformers for joint information extraction from patient-doctor dialogues
Accepted Paper
2024年第8期 :
doi:10.19734/j.issn.1001-3695.2023.12.0591
3
Bidirectional Transformer-based precipitation nowcasting model
Accepted Paper
2024年第8期 :
doi:10.19734/j.issn.1001-3695.2023.12.0613
4
Diverse image description generation via global and sequential latent embedding
Accepted Paper
2024年第7期 :
doi:10.19734/j.issn.1001-3695.2023.09.0510
5
Online-updating monocular visual odometry
Accepted Paper
2024年第7期 :
doi:10.19734/j.issn.1001-3695.2023.09.0512
6
Building change detection in remote sensing images based on local-global feature coupling and boundary guidance
Accepted Paper
2024年第6期 :
doi:10.19734/j.issn.1001-3695.2023.09.0407
7
Remaining useful life prediction method of Web system based on transmp model
Accepted Paper
2024年第6期 :
doi:10.19734/j.issn.1001-3695.2023.10.0437
8
TCSNGAN: image generation model based on Transformer and CNN with spectral normalization
2024年第4期 : 1221-1227
doi:10.19734/j.issn.1001-3695.2023.07.0357
9
Video frame interpolation method based on improved visual Transformer
2024年第4期 : 1252-1257
doi:10.19734/j.issn.1001-3695.2023.07.0344
10
XLNet-Transformer optimization method for Chinese-Malay low-resource neural machine translation based on deep coded attention
2024年第3期 : 799-804,810
doi:10.19734/j.issn.1001-3695.2023.08.0331
11
Flexible modal face presentation attack detection based on atrous single stream vision Transformer network
2024年第3期 : 916-922
doi:10.19734/j.issn.1001-3695.2023.07.0319
12
Bird’s eye view map semantic segmentation algorithm based on Transformer and edge decoupling
2023年第11期 : 3432-3436
doi:10.19734/j.issn.1001-3695.2023.02.0071
13
Stereo matching network based on multilevel cascaded recurrent
2023年第11期 : 3462-3466
doi:10.19734/j.issn.1001-3695.2023.02.0043
14
Refining Transformer for weakly supervised image semantic segmentation
2023年第11期 : 3515-3520
doi:10.19734/j.issn.1001-3695.2023.05.0218
15
Application of layer by layer Transformer in class-imbalanced data
2023年第10期 : 3047-3052
doi:10.19734/j.issn.1001-3695.2023.01.0056
16
Fine-grained visual classification method based on knowledge distillation and target regions selection
2023年第9期 : 2863-2868
doi:10.19734/j.issn.1001-3695.2022.12.0809
17
Chest X-ray images and diagnostic reports for twin-towers cross-modal retrieval
2023年第8期 : 2543-2548
doi:10.19734/j.issn.1001-3695.2022.12.0786
18
Full-reference video quality assessment combining spatio-temporal features and visual perception
2023年第7期 : 2198-2203,2222
doi:10.19734/j.issn.1001-3695.2022.11.0631
19
Research on facial landmarks detection network based on Transformer
2023年第6期 : 1870-1875,1881
doi:10.19734/j.issn.1001-3695.2022.10.0501
20
Trust region pseudo-labels strategy for semi-supervised 3D object detection
2023年第6期 : 1888-1893,1899
doi:10.19734/j.issn.1001-3695.2022.09.0487
21
Chinese sign language translation method fusing adaptive graph convolution and Transformer sequence model
2023年第5期 : 1589-1594,1600
doi:10.19734/j.issn.1001-3695.2022.08.0463
22
Research progress of surface defect detection based on machine vision technology
2023年第4期 : 967-977
doi:10.19734/j.issn.1001-3695.2022.08.0426
23
Spinal image segmentation method with multi-attention
2023年第4期 : 1256-1262
doi:10.19734/j.issn.1001-3695.2022.07.0409
24
Image caption generation method based on spatial correlation attention
2023年第4期 : 1275-1280
doi:10.19734/j.issn.1001-3695.2022.07.0408
25
Code completion method based on multi-task learning
2023年第3期 : 863-867
doi:10.19734/j.issn.1001-3695.2022.08.0396
26
Based on U-Net multi-scale self-calibrating attention retinal segmentation algorithm
2023年第3期 : 943-948
doi:10.19734/j.issn.1001-3695.2022.05.0317
27
Lightweight Chinese speech recognition with Transformer
2023年第2期 : 424-429
doi:10.19734/j.issn.1001-3695.2022.06.0340
28
Traffic flow prediction method based on multi-channel Transformer
2023年第2期 : 435-439
doi:10.19734/j.issn.1001-3695.2022.06.0306
29
FuseNet:lightweight image recognition network for mobile applications
2023年第1期 : 288-293,298
doi:10.19734/j.issn.1001-3695.2022.05.0230
30
Hierarchical boundary guided multi-scale Transformer for salient object detection
2022年第12期 : 3820-3824,3836
doi:10.19734/j.issn.1001-3695.2022.04.0162
31
Hand mesh reconstruction based on Transformer with assist of multi task learning CNN
2022年第12期 : 3830-3836
doi:10.19734/j.issn.1001-3695.2022.04.0161
32
New hierarchical interactive answer selection model based on Transformer and dual attention fusion
2022年第11期 : 3320-3326
doi:10.19734/j.issn.1001-3695.2022.04.0183
33
End-to-end deep reinforcement learning framework for multi-depot vehicle routing problem
2022年第10期 : 3013-3019
doi:10.19734/j.issn.1001-3695.2022.03.0095
34
MultiFormer: image classification network based on Transformer
2022年第10期 : 3191-3195
doi:10.19734/j.issn.1001-3695.2022.03.0133
35
Review of video action recognition technology based on deep learning
2022年第9期 : 2561-2569
doi:10.19734/j.issn.1001-3695.2022.03.0077
36
Multi-branch single image deraining network based on Transformer
2022年第8期 : 2500-2505,2519
doi:10.19734/j.issn.1001-3695.2021.12.0695
37
Detection method for small-size surface defects based on Smooth-DETR
2022年第8期 : 2520-2525
doi:10.19734/j.issn.1001-3695.2022.01.0011
38
Text-guided image manipulation with Transformer
2022年第5期 : 1563-1568
doi:10.19734/j.issn.1001-3695.2021.10.0455
39
Research on image captioning method based on sparse self-attention mechanism of integrated geometric relationship
2022年第4期 : 1132-1136
doi:10.19734/j.issn.1001-3695.2021.07.0339
40
TCN-Transformer-CTC for end-to-end speech recognition
2022年第3期 : 699-703
doi:10.19734/j.issn.1001-3695.2021.08.0323
41
Separate structure machine translation model based on fusion of CNN and Transformer
2022年第2期 : 432-435
doi:10.19734/j.issn.1001-3695.2021.07.0274
42
Improved Transformer based model for click-through rate prediction
2021年第8期 : 2386-2389,2400
doi:10.19734/j.issn.1001-3695.2020.09.0355
43
Expression-oriented ROI region secondary voting mechanism
2019年第9期 : 2861-2865
doi:10.19734/j.issn.1001-3695.2018.03.0189
44
Application of cyber physical system on transformer constant voltage modulation control
2019年第2期 : 456-460
doi:10.19734/j.issn.1001-3695.2017.08.0719