Alert button

"Image": models, code, and papers
Alert button

Context-Aware Visual Policy Network for Sequence-Level Image Captioning

Aug 22, 2018
Daqing Liu, Zheng-Jun Zha, Hanwang Zhang, Yongdong Zhang, Feng Wu

Figure 1 for Context-Aware Visual Policy Network for Sequence-Level Image Captioning
Figure 2 for Context-Aware Visual Policy Network for Sequence-Level Image Captioning
Figure 3 for Context-Aware Visual Policy Network for Sequence-Level Image Captioning
Figure 4 for Context-Aware Visual Policy Network for Sequence-Level Image Captioning
Viaarxiv icon

Deep Domain Generalization with Feature-norm Network

Apr 28, 2021
Mohammad Mahfujur Rahman, Clinton Fookes, Sridha Sridharan

Figure 1 for Deep Domain Generalization with Feature-norm Network
Figure 2 for Deep Domain Generalization with Feature-norm Network
Figure 3 for Deep Domain Generalization with Feature-norm Network
Figure 4 for Deep Domain Generalization with Feature-norm Network
Viaarxiv icon

Multi-view analysis of unregistered medical images using cross-view transformers

Mar 21, 2021
Gijs van Tulder, Yao Tong, Elena Marchiori

Figure 1 for Multi-view analysis of unregistered medical images using cross-view transformers
Figure 2 for Multi-view analysis of unregistered medical images using cross-view transformers
Figure 3 for Multi-view analysis of unregistered medical images using cross-view transformers
Figure 4 for Multi-view analysis of unregistered medical images using cross-view transformers
Viaarxiv icon

Specular reflections removal in colposcopic images based on neural networks: Supervised training with no ground truth previous knowledge

Jun 04, 2021
Lauren Jimenez-Martin, Daniel A. Valdés Pérez, Ana M. Solares Asteasuainzarra, Ludwig Leonard, Marta L. Baguer Díaz-Romañach

Figure 1 for Specular reflections removal in colposcopic images based on neural networks: Supervised training with no ground truth previous knowledge
Figure 2 for Specular reflections removal in colposcopic images based on neural networks: Supervised training with no ground truth previous knowledge
Figure 3 for Specular reflections removal in colposcopic images based on neural networks: Supervised training with no ground truth previous knowledge
Figure 4 for Specular reflections removal in colposcopic images based on neural networks: Supervised training with no ground truth previous knowledge
Viaarxiv icon

More Is Better: An Analysis of Instance Quantity/Quality Trade-off in Rehearsal-based Continual Learning

May 28, 2021
Francesco Pelosin, Andrea Torsello

Figure 1 for More Is Better: An Analysis of Instance Quantity/Quality Trade-off in Rehearsal-based Continual Learning
Figure 2 for More Is Better: An Analysis of Instance Quantity/Quality Trade-off in Rehearsal-based Continual Learning
Figure 3 for More Is Better: An Analysis of Instance Quantity/Quality Trade-off in Rehearsal-based Continual Learning
Figure 4 for More Is Better: An Analysis of Instance Quantity/Quality Trade-off in Rehearsal-based Continual Learning
Viaarxiv icon

ConTNet: Why not use convolution and transformer at the same time?

May 06, 2021
Haotian Yan, Zhe Li, Weijian Li, Changhu Wang, Ming Wu, Chuang Zhang

Figure 1 for ConTNet: Why not use convolution and transformer at the same time?
Figure 2 for ConTNet: Why not use convolution and transformer at the same time?
Figure 3 for ConTNet: Why not use convolution and transformer at the same time?
Figure 4 for ConTNet: Why not use convolution and transformer at the same time?
Viaarxiv icon

Texture Based Classification of High Resolution Remotely Sensed Imagery using Weber Local Descriptor

Apr 18, 2021
Decky Aspandi-Latif, Sally Goldin, Preesan Rakwatin, Kurt Rudahl

Figure 1 for Texture Based Classification of High Resolution Remotely Sensed Imagery using Weber Local Descriptor
Figure 2 for Texture Based Classification of High Resolution Remotely Sensed Imagery using Weber Local Descriptor
Figure 3 for Texture Based Classification of High Resolution Remotely Sensed Imagery using Weber Local Descriptor
Figure 4 for Texture Based Classification of High Resolution Remotely Sensed Imagery using Weber Local Descriptor
Viaarxiv icon

TextureWGAN: Texture Preserving WGAN with MLE Regularizer for Inverse Problems

Aug 12, 2020
Masaki Ikuta, Jun Zhang

Figure 1 for TextureWGAN: Texture Preserving WGAN with MLE Regularizer for Inverse Problems
Figure 2 for TextureWGAN: Texture Preserving WGAN with MLE Regularizer for Inverse Problems
Viaarxiv icon

Omnimatte: Associating Objects and Their Effects in Video

May 14, 2021
Erika Lu, Forrester Cole, Tali Dekel, Andrew Zisserman, William T. Freeman, Michael Rubinstein

Figure 1 for Omnimatte: Associating Objects and Their Effects in Video
Figure 2 for Omnimatte: Associating Objects and Their Effects in Video
Figure 3 for Omnimatte: Associating Objects and Their Effects in Video
Figure 4 for Omnimatte: Associating Objects and Their Effects in Video
Viaarxiv icon

Improving the Fairness of Deep Generative Models without Retraining

Dec 09, 2020
Shuhan Tan, Yujun Shen, Bolei Zhou

Figure 1 for Improving the Fairness of Deep Generative Models without Retraining
Figure 2 for Improving the Fairness of Deep Generative Models without Retraining
Figure 3 for Improving the Fairness of Deep Generative Models without Retraining
Figure 4 for Improving the Fairness of Deep Generative Models without Retraining
Viaarxiv icon