PBVS/CVPR '22 will be a hybrid conference, with both in-person and virtual attendance options, please NOTE:
Welcome Message from the Chairs (08:30-08:45)
Keynote Talk (08:45-09:30)
| AI based Medical Image Reconstruction | Prof. Dinggang Shen Shanghai Tech University, China |
|
Session 1: Remote Presentations (09:30 - 10:30)
| From Less to More: Spectral Splitting and Aggregation Network for Hyperspectral Face Super-Resolution (09:30) | Junjun Jiang, Chenyang Wang, Xianming Liu, Kui Jiang, Jiayi Ma |
| Pseudo-label Generation and Various Data Augmentation for Semi-Supervised Hyperspectral Object Detection (09:40) | Jun Yu, Liwen Zhang, Shenshen Du, Hao Chang, Keda Lu, Zhong Zhang, Ye Yu,Lei Wang, Qiang Ling |
| CIPPSRNet: A Camera Internal Parameters Perception Network Based Contrastive Learning for Thermal Image Super-Resolution (09:50) | Kai Wang, Qigong Sun, Yicheng Wang, Huiyuan Wei, Chonghua Lv, Xiaolin Tian, Xu Liu |
| HSI-Guided Intrinsic Image Decomposition for Outdoor Scenes (10:00) | Fan Zhang, Shaodi You, Yu Li, Ying Fu |
| A Two-Stage Shake-Shake Network for Long-tailed Recognition of SAR Aerial View Objects (10:10) | Gongzhe, Li, Linpeng Pan, Linwei Qiu, Zhiwen Tan, Fengying Xie, Haopeng Zhang |
| AquaGAN: Restoration of Underwater Images (10:20) | Chaitra D. Desai, Badduri Sai Sudheer Reddy, Ramesh Tabib, Ujwala Patil, Uma Mudenagudi |
Coffee Break (10:30-11:00)
Session 2: Remote Presentations (11:00 - 12:00)
| Deep Neural Network with Walsh-Hadamard Transform Layer For Ember Detection during a Wildfire (11:00) | Hongyi Pan, Diaa Badawi, Chang Chen; Adam Watts, Erdem Koyuncu, Ahmet E. Cetin |
| Augmentation of Atmospheric Turbulence Effects on Thermal Adapted Object Detection Models (11:10) | Engin Uzun, Dursun, Ahmet Anil Dursun, Erdem Akagündüz |
| Semantic Segmentation for Thermal Images: A Comparative Survey (11:20) | Zülfiye Kütük, Görkem Algan |
| 3DRRDB: Super Resolution of Multiple Remote Sensing Images using 3D Residual in Residual Dense Blocks (11:30) | Mohamed Ramzy Ibrahim, Robert Benavente, Felipe Lumbreras, Daniel Ponsa |
| Depthwise Convolution For Compact Object Detector In Night-time Images (11:40) | Heena Patel, Kishor Upla, Kiran Raja, Kalpesh J. Prajapati, Anjali Sarvaiya, Raghavendra Ramachandra, Christoph Busch |
| ActAR: Actor-Driven Pose Embeddings for Video Action Recognition (11:50) | Soufiane Lamghari, Guillaume-Alexandre Bilodeau, Nicolas Saunier |
Lunch Break (12:00-13:30)
Keynote Talk (13:30-14:15)
| Media Authentication and Explainable AI: Applications Beyond the Visible Spectrum | Dr. Matt Turek DARPA, USA |
|
Announcement of the Challenge Winners (14:15 - 15:00)
| Thermal Image Super-Resolution Challenge Results - PBVS 2022 (14:15) | Rafael E. Rivadeneira et al. |
| Multi-modal Aerial View Object Classification Challenge Results - PBVS 2022 (14:30) | Spencer Low et al. |
| Semi-Supervised Hyperspectral Object Detection Challenge Results - PBVS 2022 (14:45) | Aneesh Rangnekar et al. |
Keynote Talk (15:00-15:45)
| Picture Quality Prediction Outside the Visible Spectrum | Prof. Alan Bovik UT Austin, USA |
|
Coffee Break (15:45-16:00)
Session 3: In-person Presentations (16:00 - 17:30)
| Multiple Object Detection and Tracking in the Thermal Spectrum (16:00) | Wassim El Ahmar, Dhanvin Kolhatkar, Farzan Nowruzi, Hamzah AlGhamdi, Jonathan Hou, Robert Laganiere |
| Lost in Compression: the Impact of Lossy Image Compression on Variable Size Object Detection within Infrared Imagery (16:10) | Neelanjan Bhowmik, Jack Barker, Yona Falinie A. Gaus, Toby P. Breckon |
| Cross-modal Image Synthesis within Dual-Energy X-Ray Security Imagery (16:20) | Brian Kostadinov Isaac Medina, Neelanjan Bhowmik, Chris G. Willcocks, Toby P. Breckon |
| A Multiview Depth-based Motion Capture Benchmark Dataset for Human Motion Denoising and Enhancement Research (16:30) | Nate C. Lannan, Le Zhou, Guoliang Fan |
| Unsupervised Anomaly Detection from Time-of-Flight Depth Images (16:40) | Pascal Schneider, Jason Rambach, Bruno Mirbach, Didier Stricker |
| Lidar Positioning for Indoor Precision Navigation (16:50) | Max Holmberg, Oskar E. Karlsson, Michael Tulldahl |
| TMVNet : Using Transformers for Multi-view Voxel-based 3D Reconstruction (17:00) | Kebin Peng, Rifatul Islam, John P. Quarles, Kevin Desai |
| GAF-NAU: Gramian Angular Field encoded Neighborhood Attention U-Net for Pixel-Wise Hyperspectral Image Classification (17:10) | Sidike Paheding, Abel Reyes, Anush Kasaragod, Thomas Oommen |
| Variational Autoencoders for Generating Hyperspectral Imaging Honey Adulteration Data (17:20) | Tessa Phillips, Waleed Abdulla [remote presentation] |
Closing Remarks (17:30-17:45)
The End of PBVS '22 (17:45)