Alert button

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

Alleviating Noisy Data in Image Captioning with Cooperative Distillation

Dec 21, 2020
Pierre Dognin, Igor Melnyk, Youssef Mroueh, Inkit Padhi, Mattia Rigotti, Jarret Ross, Yair Schiff

Figure 1 for Alleviating Noisy Data in Image Captioning with Cooperative Distillation
Figure 2 for Alleviating Noisy Data in Image Captioning with Cooperative Distillation
Figure 3 for Alleviating Noisy Data in Image Captioning with Cooperative Distillation
Viaarxiv icon

Depth estimation of endoscopy using sim-to-real transfer

Dec 27, 2021
Bong Hyuk Jeong, Hang Keun Kim, Young Don Son

Figure 1 for Depth estimation of endoscopy using sim-to-real transfer
Figure 2 for Depth estimation of endoscopy using sim-to-real transfer
Figure 3 for Depth estimation of endoscopy using sim-to-real transfer
Figure 4 for Depth estimation of endoscopy using sim-to-real transfer
Viaarxiv icon

MDA-Net: Multi-Dimensional Attention-Based Neural Network for 3D Image Segmentation

May 10, 2021
Rutu Gandhi, Yi Hong

Figure 1 for MDA-Net: Multi-Dimensional Attention-Based Neural Network for 3D Image Segmentation
Figure 2 for MDA-Net: Multi-Dimensional Attention-Based Neural Network for 3D Image Segmentation
Figure 3 for MDA-Net: Multi-Dimensional Attention-Based Neural Network for 3D Image Segmentation
Figure 4 for MDA-Net: Multi-Dimensional Attention-Based Neural Network for 3D Image Segmentation
Viaarxiv icon

Training Quantised Neural Networks with STE Variants: the Additive Noise Annealing Algorithm

Mar 21, 2022
Matteo Spallanzani, Gian Paolo Leonardi, Luca Benini

Figure 1 for Training Quantised Neural Networks with STE Variants: the Additive Noise Annealing Algorithm
Figure 2 for Training Quantised Neural Networks with STE Variants: the Additive Noise Annealing Algorithm
Figure 3 for Training Quantised Neural Networks with STE Variants: the Additive Noise Annealing Algorithm
Figure 4 for Training Quantised Neural Networks with STE Variants: the Additive Noise Annealing Algorithm
Viaarxiv icon

Learnability Lock: Authorized Learnability Control Through Adversarial Invertible Transformations

Feb 03, 2022
Weiqi Peng, Jinghui Chen

Figure 1 for Learnability Lock: Authorized Learnability Control Through Adversarial Invertible Transformations
Figure 2 for Learnability Lock: Authorized Learnability Control Through Adversarial Invertible Transformations
Figure 3 for Learnability Lock: Authorized Learnability Control Through Adversarial Invertible Transformations
Figure 4 for Learnability Lock: Authorized Learnability Control Through Adversarial Invertible Transformations
Viaarxiv icon

Topology-Preserving Shape Reconstruction and Registration via Neural Diffeomorphic Flow

Mar 21, 2022
Shanlin Sun, Kun Han, Deying Kong, Hao Tang, Xiangyi Yan, Xiaohui Xie

Figure 1 for Topology-Preserving Shape Reconstruction and Registration via Neural Diffeomorphic Flow
Figure 2 for Topology-Preserving Shape Reconstruction and Registration via Neural Diffeomorphic Flow
Figure 3 for Topology-Preserving Shape Reconstruction and Registration via Neural Diffeomorphic Flow
Figure 4 for Topology-Preserving Shape Reconstruction and Registration via Neural Diffeomorphic Flow
Viaarxiv icon

Heterogeneous Visible-Thermal and Visible-Infrared Face Recognition using Unit-Class Loss and Cross-Modality Discriminator

Nov 29, 2021
Usman Cheema, Mobeen Ahmad, Dongil Han, Seungbin Moon

Figure 1 for Heterogeneous Visible-Thermal and Visible-Infrared Face Recognition using Unit-Class Loss and Cross-Modality Discriminator
Figure 2 for Heterogeneous Visible-Thermal and Visible-Infrared Face Recognition using Unit-Class Loss and Cross-Modality Discriminator
Figure 3 for Heterogeneous Visible-Thermal and Visible-Infrared Face Recognition using Unit-Class Loss and Cross-Modality Discriminator
Figure 4 for Heterogeneous Visible-Thermal and Visible-Infrared Face Recognition using Unit-Class Loss and Cross-Modality Discriminator
Viaarxiv icon

Robust Visual Tracking by Segmentation

Mar 21, 2022
Matthieu Paul, Martin Danelljan, Christoph Mayer, Luc Van Gool

Figure 1 for Robust Visual Tracking by Segmentation
Figure 2 for Robust Visual Tracking by Segmentation
Figure 3 for Robust Visual Tracking by Segmentation
Figure 4 for Robust Visual Tracking by Segmentation
Viaarxiv icon

Style and Pose Control for Image Synthesis of Humans from a Single Monocular View

Feb 22, 2021
Kripasindhu Sarkar, Vladislav Golyanik, Lingjie Liu, Christian Theobalt

Figure 1 for Style and Pose Control for Image Synthesis of Humans from a Single Monocular View
Figure 2 for Style and Pose Control for Image Synthesis of Humans from a Single Monocular View
Figure 3 for Style and Pose Control for Image Synthesis of Humans from a Single Monocular View
Figure 4 for Style and Pose Control for Image Synthesis of Humans from a Single Monocular View
Viaarxiv icon

End-to-end video instance segmentation via spatial-temporal graph neural networks

Mar 07, 2022
Tao Wang, Ning Xu, Kean Chen, Weiyao Lin

Figure 1 for End-to-end video instance segmentation via spatial-temporal graph neural networks
Figure 2 for End-to-end video instance segmentation via spatial-temporal graph neural networks
Figure 3 for End-to-end video instance segmentation via spatial-temporal graph neural networks
Figure 4 for End-to-end video instance segmentation via spatial-temporal graph neural networks
Viaarxiv icon