Alert button

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

EventGAN: Leveraging Large Scale Image Datasets for Event Cameras

Dec 03, 2019
Alex Zihao Zhu, Ziyun Wang, Kaung Khant, Kostas Daniilidis

Figure 1 for EventGAN: Leveraging Large Scale Image Datasets for Event Cameras
Figure 2 for EventGAN: Leveraging Large Scale Image Datasets for Event Cameras
Figure 3 for EventGAN: Leveraging Large Scale Image Datasets for Event Cameras
Figure 4 for EventGAN: Leveraging Large Scale Image Datasets for Event Cameras
Viaarxiv icon

Newer is not always better: Rethinking transferability metrics, their peculiarities, stability and performance

Oct 25, 2021
Shibal Ibrahim, Natalia Ponomareva, Rahul Mazumder

Figure 1 for Newer is not always better: Rethinking transferability metrics, their peculiarities, stability and performance
Figure 2 for Newer is not always better: Rethinking transferability metrics, their peculiarities, stability and performance
Figure 3 for Newer is not always better: Rethinking transferability metrics, their peculiarities, stability and performance
Figure 4 for Newer is not always better: Rethinking transferability metrics, their peculiarities, stability and performance
Viaarxiv icon

Robotic Grasping through Combined image-Based Grasp Proposal and 3D Reconstruction

Mar 03, 2020
Tarik Tosun, Daniel Yang, Ben Eisner, Volkan Isler, Daniel Lee

Figure 1 for Robotic Grasping through Combined image-Based Grasp Proposal and 3D Reconstruction
Figure 2 for Robotic Grasping through Combined image-Based Grasp Proposal and 3D Reconstruction
Figure 3 for Robotic Grasping through Combined image-Based Grasp Proposal and 3D Reconstruction
Figure 4 for Robotic Grasping through Combined image-Based Grasp Proposal and 3D Reconstruction
Viaarxiv icon

Real World Robustness from Systematic Noise

Sep 02, 2021
Yan Wang, Yuhang Li, Ruihao Gong

Figure 1 for Real World Robustness from Systematic Noise
Figure 2 for Real World Robustness from Systematic Noise
Figure 3 for Real World Robustness from Systematic Noise
Figure 4 for Real World Robustness from Systematic Noise
Viaarxiv icon

Forward-Looking Sonar Patch Matching: Modern CNNs, Ensembling, and Uncertainty

Aug 02, 2021
Arka Mallick, Paul Plöger, Matias Valdenegro-Toro

Figure 1 for Forward-Looking Sonar Patch Matching: Modern CNNs, Ensembling, and Uncertainty
Figure 2 for Forward-Looking Sonar Patch Matching: Modern CNNs, Ensembling, and Uncertainty
Figure 3 for Forward-Looking Sonar Patch Matching: Modern CNNs, Ensembling, and Uncertainty
Figure 4 for Forward-Looking Sonar Patch Matching: Modern CNNs, Ensembling, and Uncertainty
Viaarxiv icon

Character Spotting Using Machine Learning Techniques

Jul 28, 2021
P Preethi, Hrishikesh Viswanath

Figure 1 for Character Spotting Using Machine Learning Techniques
Figure 2 for Character Spotting Using Machine Learning Techniques
Viaarxiv icon

Non-local Attention Optimized Deep Image Compression

Apr 22, 2019
Haojie Liu, Tong Chen, Peiyao Guo, Qiu Shen, Xun Cao, Yao Wang, Zhan Ma

Figure 1 for Non-local Attention Optimized Deep Image Compression
Figure 2 for Non-local Attention Optimized Deep Image Compression
Figure 3 for Non-local Attention Optimized Deep Image Compression
Figure 4 for Non-local Attention Optimized Deep Image Compression
Viaarxiv icon

Investigating Image Applications Based on Spatial-Frequency Transform and Deep Learning Techniques

Mar 20, 2020
Qinkai Zheng, Han Qiu, Gerard Memmi, Isabelle Bloch

Figure 1 for Investigating Image Applications Based on Spatial-Frequency Transform and Deep Learning Techniques
Figure 2 for Investigating Image Applications Based on Spatial-Frequency Transform and Deep Learning Techniques
Figure 3 for Investigating Image Applications Based on Spatial-Frequency Transform and Deep Learning Techniques
Figure 4 for Investigating Image Applications Based on Spatial-Frequency Transform and Deep Learning Techniques
Viaarxiv icon

Shifting Capsule Networks from the Cloud to the Deep Edge

Oct 06, 2021
Miguel Costa, Diogo Costa, Tiago Gomes, Sandro Pinto

Figure 1 for Shifting Capsule Networks from the Cloud to the Deep Edge
Figure 2 for Shifting Capsule Networks from the Cloud to the Deep Edge
Figure 3 for Shifting Capsule Networks from the Cloud to the Deep Edge
Figure 4 for Shifting Capsule Networks from the Cloud to the Deep Edge
Viaarxiv icon

ZSD-YOLO: Zero-Shot YOLO Detection using Vision-Language KnowledgeDistillation

Sep 24, 2021
Johnathan Xie, Shuai Zheng

Figure 1 for ZSD-YOLO: Zero-Shot YOLO Detection using Vision-Language KnowledgeDistillation
Figure 2 for ZSD-YOLO: Zero-Shot YOLO Detection using Vision-Language KnowledgeDistillation
Figure 3 for ZSD-YOLO: Zero-Shot YOLO Detection using Vision-Language KnowledgeDistillation
Figure 4 for ZSD-YOLO: Zero-Shot YOLO Detection using Vision-Language KnowledgeDistillation
Viaarxiv icon