Alert button

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

Comprehensive Image Captioning via Scene Graph Decomposition

Jul 23, 2020
Yiwu Zhong, Liwei Wang, Jianshu Chen, Dong Yu, Yin Li

Figure 1 for Comprehensive Image Captioning via Scene Graph Decomposition
Figure 2 for Comprehensive Image Captioning via Scene Graph Decomposition
Figure 3 for Comprehensive Image Captioning via Scene Graph Decomposition
Figure 4 for Comprehensive Image Captioning via Scene Graph Decomposition
Viaarxiv icon

Highly-Efficient Binary Neural Networks for Visual Place Recognition

Feb 24, 2022
Bruno Ferrarini, Michael Milford, Klaus D. McDonald-Maier, Shoaib Ehsan

Figure 1 for Highly-Efficient Binary Neural Networks for Visual Place Recognition
Figure 2 for Highly-Efficient Binary Neural Networks for Visual Place Recognition
Figure 3 for Highly-Efficient Binary Neural Networks for Visual Place Recognition
Figure 4 for Highly-Efficient Binary Neural Networks for Visual Place Recognition
Viaarxiv icon

Adversarial Dual-Student with Differentiable Spatial Warping for Semi-Supervised Semantic Segmentation

Mar 05, 2022
Cong Cao, Tianwei Lin, Dongliang He, Fu Li, Huanjing Yue, Jingyu Yang, Errui Ding

Figure 1 for Adversarial Dual-Student with Differentiable Spatial Warping for Semi-Supervised Semantic Segmentation
Figure 2 for Adversarial Dual-Student with Differentiable Spatial Warping for Semi-Supervised Semantic Segmentation
Figure 3 for Adversarial Dual-Student with Differentiable Spatial Warping for Semi-Supervised Semantic Segmentation
Figure 4 for Adversarial Dual-Student with Differentiable Spatial Warping for Semi-Supervised Semantic Segmentation
Viaarxiv icon

NeRF-Pose: A First-Reconstruct-Then-Regress Approach for Weakly-supervised 6D Object Pose Estimation

Mar 09, 2022
Fu Li, Hao Yu, Ivan Shugurov, Benjamin Busam, Shaowu Yang, Slobodan Ilic

Figure 1 for NeRF-Pose: A First-Reconstruct-Then-Regress Approach for Weakly-supervised 6D Object Pose Estimation
Figure 2 for NeRF-Pose: A First-Reconstruct-Then-Regress Approach for Weakly-supervised 6D Object Pose Estimation
Figure 3 for NeRF-Pose: A First-Reconstruct-Then-Regress Approach for Weakly-supervised 6D Object Pose Estimation
Figure 4 for NeRF-Pose: A First-Reconstruct-Then-Regress Approach for Weakly-supervised 6D Object Pose Estimation
Viaarxiv icon

CDGNet: Class Distribution Guided Network for Human Parsing

Nov 28, 2021
Kunliang Liu, Ouk Choi, Jianming Wang, Wonjun Hwang

Figure 1 for CDGNet: Class Distribution Guided Network for Human Parsing
Figure 2 for CDGNet: Class Distribution Guided Network for Human Parsing
Figure 3 for CDGNet: Class Distribution Guided Network for Human Parsing
Figure 4 for CDGNet: Class Distribution Guided Network for Human Parsing
Viaarxiv icon

IFOR: Iterative Flow Minimization for Robotic Object Rearrangement

Feb 01, 2022
Ankit Goyal, Arsalan Mousavian, Chris Paxton, Yu-Wei Chao, Brian Okorn, Jia Deng, Dieter Fox

Figure 1 for IFOR: Iterative Flow Minimization for Robotic Object Rearrangement
Figure 2 for IFOR: Iterative Flow Minimization for Robotic Object Rearrangement
Figure 3 for IFOR: Iterative Flow Minimization for Robotic Object Rearrangement
Figure 4 for IFOR: Iterative Flow Minimization for Robotic Object Rearrangement
Viaarxiv icon

A Comparison for Anti-noise Robustness of Deep Learning Classification Methods on a Tiny Object Image Dataset: from Convolutional Neural Network to Visual Transformer and Performer

Jun 03, 2021
Ao Chen, Chen Li, Haoyuan Chen, Hechen Yang, Peng Zhao, Weiming Hu, Wanli Liu, Shuojia Zou, Marcin Grzegorzek

Figure 1 for A Comparison for Anti-noise Robustness of Deep Learning Classification Methods on a Tiny Object Image Dataset: from Convolutional Neural Network to Visual Transformer and Performer
Figure 2 for A Comparison for Anti-noise Robustness of Deep Learning Classification Methods on a Tiny Object Image Dataset: from Convolutional Neural Network to Visual Transformer and Performer
Figure 3 for A Comparison for Anti-noise Robustness of Deep Learning Classification Methods on a Tiny Object Image Dataset: from Convolutional Neural Network to Visual Transformer and Performer
Figure 4 for A Comparison for Anti-noise Robustness of Deep Learning Classification Methods on a Tiny Object Image Dataset: from Convolutional Neural Network to Visual Transformer and Performer
Viaarxiv icon

In-Bed Human Pose Estimation from Unseen and Privacy-Preserving Image Domains

Nov 30, 2021
Ting Cao, Mohammad Ali Armin, Simon Denman, Lars Petersson, David Ahmedt-Aristizabal

Figure 1 for In-Bed Human Pose Estimation from Unseen and Privacy-Preserving Image Domains
Figure 2 for In-Bed Human Pose Estimation from Unseen and Privacy-Preserving Image Domains
Figure 3 for In-Bed Human Pose Estimation from Unseen and Privacy-Preserving Image Domains
Figure 4 for In-Bed Human Pose Estimation from Unseen and Privacy-Preserving Image Domains
Viaarxiv icon

Context-Preserving Instance-Level Augmentation and Deformable Convolution Networks for SAR Ship Detection

Feb 14, 2022
Taeyong Song, Sunok Kim, SungTai Kim, Jaeseok Lee, Kwanghoon Sohn

Figure 1 for Context-Preserving Instance-Level Augmentation and Deformable Convolution Networks for SAR Ship Detection
Figure 2 for Context-Preserving Instance-Level Augmentation and Deformable Convolution Networks for SAR Ship Detection
Figure 3 for Context-Preserving Instance-Level Augmentation and Deformable Convolution Networks for SAR Ship Detection
Figure 4 for Context-Preserving Instance-Level Augmentation and Deformable Convolution Networks for SAR Ship Detection
Viaarxiv icon

Fully automatic integration of dental CBCT images and full-arch intraoral impressions with stitching error correction via individual tooth segmentation and identification

Dec 03, 2021
Tae Jun Jang, Hye Sun Yun, Jong-Eun Kim, Sang-Hwy Lee, Jin Keun Seo

Figure 1 for Fully automatic integration of dental CBCT images and full-arch intraoral impressions with stitching error correction via individual tooth segmentation and identification
Figure 2 for Fully automatic integration of dental CBCT images and full-arch intraoral impressions with stitching error correction via individual tooth segmentation and identification
Figure 3 for Fully automatic integration of dental CBCT images and full-arch intraoral impressions with stitching error correction via individual tooth segmentation and identification
Figure 4 for Fully automatic integration of dental CBCT images and full-arch intraoral impressions with stitching error correction via individual tooth segmentation and identification
Viaarxiv icon