Alert button

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

Modular Meta-Learning with Shrinkage

Sep 12, 2019
Yutian Chen, Abram L. Friesen, Feryal Behbahani, David Budden, Matthew W. Hoffman, Arnaud Doucet, Nando de Freitas

Figure 1 for Modular Meta-Learning with Shrinkage
Figure 2 for Modular Meta-Learning with Shrinkage
Figure 3 for Modular Meta-Learning with Shrinkage
Figure 4 for Modular Meta-Learning with Shrinkage
Viaarxiv icon

Deep, robust and single shot 3D multi-person human pose estimation in complex images

Nov 08, 2019
Abdallah Benzine, Bertrand Luvison, Quoc Cuong Pham, Catherine Achard

Figure 1 for Deep, robust and single shot 3D multi-person human pose estimation in complex images
Figure 2 for Deep, robust and single shot 3D multi-person human pose estimation in complex images
Figure 3 for Deep, robust and single shot 3D multi-person human pose estimation in complex images
Figure 4 for Deep, robust and single shot 3D multi-person human pose estimation in complex images
Viaarxiv icon

Hallucinating Statistical Moment and Subspace Descriptors from Object and Saliency Detectors for Action Recognition

Jan 14, 2020
Lei Wang, Piotr Koniusz

Figure 1 for Hallucinating Statistical Moment and Subspace Descriptors from Object and Saliency Detectors for Action Recognition
Figure 2 for Hallucinating Statistical Moment and Subspace Descriptors from Object and Saliency Detectors for Action Recognition
Figure 3 for Hallucinating Statistical Moment and Subspace Descriptors from Object and Saliency Detectors for Action Recognition
Figure 4 for Hallucinating Statistical Moment and Subspace Descriptors from Object and Saliency Detectors for Action Recognition
Viaarxiv icon

Video synthesis of human upper body with realistic face

Sep 12, 2019
Zhaoxiang Liu, Huan Hu, Zipeng Wang, Kai Wang, Jinqiang Bai, Shiguo Lian

Figure 1 for Video synthesis of human upper body with realistic face
Figure 2 for Video synthesis of human upper body with realistic face
Figure 3 for Video synthesis of human upper body with realistic face
Figure 4 for Video synthesis of human upper body with realistic face
Viaarxiv icon

Automatic Registration between Cone-Beam CT and Scanned Surface via Deep-Pose Regression Neural Networks and Clustered Similarities

Jul 29, 2019
Minyoung Chung, Jingyu Lee, Wisoo Song, Youngchan Song, Il-Hyung Yang, Jeongjin Lee, Yeong-Gil Shin

Figure 1 for Automatic Registration between Cone-Beam CT and Scanned Surface via Deep-Pose Regression Neural Networks and Clustered Similarities
Figure 2 for Automatic Registration between Cone-Beam CT and Scanned Surface via Deep-Pose Regression Neural Networks and Clustered Similarities
Figure 3 for Automatic Registration between Cone-Beam CT and Scanned Surface via Deep-Pose Regression Neural Networks and Clustered Similarities
Figure 4 for Automatic Registration between Cone-Beam CT and Scanned Surface via Deep-Pose Regression Neural Networks and Clustered Similarities
Viaarxiv icon

DeepOtsu: Document Enhancement and Binarization using Iterative Deep Learning

Jan 18, 2019
Sheng He, Lambert Schomaker

Figure 1 for DeepOtsu: Document Enhancement and Binarization using Iterative Deep Learning
Figure 2 for DeepOtsu: Document Enhancement and Binarization using Iterative Deep Learning
Figure 3 for DeepOtsu: Document Enhancement and Binarization using Iterative Deep Learning
Figure 4 for DeepOtsu: Document Enhancement and Binarization using Iterative Deep Learning
Viaarxiv icon

Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders

Dec 05, 2018
Edgar Schönfeld, Sayna Ebrahimi, Samarth Sinha, Trevor Darrell, Zeynep Akata

Figure 1 for Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders
Figure 2 for Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders
Figure 3 for Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders
Figure 4 for Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders
Viaarxiv icon

Multiview Cross-supervision for Semantic Segmentation

Dec 04, 2018
Yuan Yao, Hyun Soo Park

Figure 1 for Multiview Cross-supervision for Semantic Segmentation
Figure 2 for Multiview Cross-supervision for Semantic Segmentation
Figure 3 for Multiview Cross-supervision for Semantic Segmentation
Figure 4 for Multiview Cross-supervision for Semantic Segmentation
Viaarxiv icon

Optimal checkpointing for heterogeneous chains: how to train deep neural networks with limited memory

Nov 27, 2019
Julien Herrmann, Olivier Beaumont, Lionel Eyraud-Dubois, Julien Hermann, Alexis Joly, Alena Shilova

Figure 1 for Optimal checkpointing for heterogeneous chains: how to train deep neural networks with limited memory
Figure 2 for Optimal checkpointing for heterogeneous chains: how to train deep neural networks with limited memory
Figure 3 for Optimal checkpointing for heterogeneous chains: how to train deep neural networks with limited memory
Figure 4 for Optimal checkpointing for heterogeneous chains: how to train deep neural networks with limited memory
Viaarxiv icon

Assessing four Neural Networks on Handwritten Digit Recognition Dataset (MNIST)

Nov 16, 2018
Feiyang Chen, Nan Chen, Hanyang Mao, Hanlin Hu

Figure 1 for Assessing four Neural Networks on Handwritten Digit Recognition Dataset (MNIST)
Figure 2 for Assessing four Neural Networks on Handwritten Digit Recognition Dataset (MNIST)
Figure 3 for Assessing four Neural Networks on Handwritten Digit Recognition Dataset (MNIST)
Figure 4 for Assessing four Neural Networks on Handwritten Digit Recognition Dataset (MNIST)
Viaarxiv icon