- GC1 – The CORSMAL Challenge: Multi-modal Fusion and Learning for Robotics
- GC2 – QA4 CAMERA – Quality Assessment for Smartphone Cameras
- GC3 – PAIR Competition: Embedded Deep Learning Object Detection Model Compression Competition for Traffic in Asian Countries
- GC4- Encoding in the Dark
- GC5 – Densely-sampled Light Field Reconstruction
Organisers
- Apostolos Modas
- Pascal Frossard
- Ricardo Sánchez Matilla
- Andrea Cavallaro
- Riccardo Mazzon
- Alessio Xompero
Schedule:
Wednesday, 8 July – London (BST time zone)
| Time | Talk/Paper | Speaker(s) |
|---|---|---|
| 10:00 | Welcome and Introduction | Andrea Cavallaro (QMUL & Alan Turing) |
| 10:10 | Unknown Object Grasping: Techniques and Benchmarks for Challenging Robotic Platforms | Giulia Vezzani (Istituto Italiano di Tecnologia & DeepMind) |
| 10:25 | Learning and Multi-Modal Sensing for Robotic Grasping and Manipulation | Yasemin Bekiroğlu (UCL & Chalmers) |
| 10:40 | Automatic 3D Annotations Applied to 3D Hand+Object Pose Estimation | Vincent Lepetit (École des Ponts ParisTech) |
| 10:55 | Touch, Interaction, and Presence In Telerobotics - Some Challenges From the Field | Rich Walker (Shadow Robot Company Ltd) |
| 11:10 | Q&A with the Speakers and Discussion | |
| 11:30 | Break | |
| 12:00 | Learning Robotic Interaction Tasks with Stability Guarantees | Shahbaz Abdul Khader (KTH) |
| 12:10 | Corsmal Dataset: Containers Manipulation | Apostolos Modas (EPFL) |
| 12:20 | Corsmal Demo: Localisation and Shape Estimation of Containers | Alessio Xompero (QMUL) |
| 12:30 | Corsmal Benchmark for Human-Robot Handover | Ricardo Sanchez-Matilla (QMUL) |
| 12:40 | Q&A with the Speakers and Discussion | |
| 13:00 | End of the Session | |
Organisers
- Guangtao Zhai
- Wenhan Zhu
- Xiongkuo Min
Schedule:
Wednesday, 8 July – London (BST time zone)
| Time | Talk/Paper | Speaker(s) |
|---|---|---|
| 11:00 | Introduction and Overview of Grand Challenge | Guangtao Zhai, Wenhan Zhu, Xiongkuo Min (SJTU) |
| 11:10 | Convolutional Neural Networks Based on Residual Block cor No-Reference Image Quality Assessment Of Smartphone Camera Images | Chang Yao, Yuri Lu, Hang Liu, Menghan Hu, Qingli Li (East China Normal University) |
| 11:20 | Q&A | |
| 11:25 | Multi-Indicator Image Quality Assessment of Smartphone Camera Based on Human Subjective Behavior And Perception | Yuwen Zhou, Yunlu Wang, Youyong Kong, Menghan Hu (Southeast University) |
| 11:35 | Q&A | |
| 11:40 | Quality Difference Ranking Model for Smartphone Camera Photo Quality Assessment | Zefeng Ying, Da Pan, Ping Shi (Communications University China) |
| 11:50 | Q&A | |
| 11:55 | Opinion-Unaware No-Reference Image Quality Assessment of Smartphone Camera Images Based On Aesthetics And Human Perception | Zifeng Yuan, Yi Qi, Menghan Hu, Qingli Li (East China Normal University) |
| 12:05 | Q&A | |
| 12:10 | Quality Assessment Model for Smartphone Camera Photo based on Inception Network with Residual Module and Batch Normalization | Shuning Xu, Junbing Yan, Menghan Hu, Qingli Li, Jiantao Zhou (University of Macau) |
| 12:20 | Q&A | |
| 12:25 | Award Ceremony | |
| 12:30 | Close | |
Organisers
- Prof. Ted T. Kuo (Chair)
- Prof. Jenq-Neng Hwang
- Prof. Jiun-In Guo
- Prof Chia-Chi Tsai
Schedule:
Wednesday, 8 July – London (BST time zone)
| Time | Talk/Paper | Speaker(s) |
|---|---|---|
| 09:30 | Welcome and Introduction | Prof. Ted T. Kuo, Prof. Jenq-Neng Hwang, Prof. Jiun-In Guo (NCTU) |
| 09:35 | Award Ceremony | Prof. Juin-In Guo (NCTU) |
| 09:45 | Overview of GC - The 2020 Embedded Deep Learning Object Detection Model Compression Competition for Traffic in Asian Countries | Chia-Chi Tsai (NCTU) |
| 09:57 | Brief Q&A | Chia-Chi Tsai (NCTU) |
| 10:00 | Efficient YOLO: A Lightweight Model for Embedded Deep Learning Object Dtection | Zixuan Wang (Bejing University of Posts and Telecommunications) |
| 10:12 | Brief Q&A | |
| 10:15 | Real Time Object Detection for Traffic Based on Knowledge Distillation: 3rd Place Solution to PAIR Competition | Yuan Zhao (AI Labs, Didi Chuxing) |
| 10:27 | Brief Q&A | |
| 10:30 | An Embedded Deep Learning Object Detection Model for Traffic in Asian Countries | Wei-Ju Chen (Foxconn) |
| 10:42 | Brief Q&A | |
| 10:45 | An Empirical Study of Object Detectors and Its Verification on the Embedded Object Detection Model Competition. | Junda Ren (Xiangtan University) |
| 10:57 | Brief Q&A | |
| 11:00 | Mobile CenterNet for Embedded Deep Learning Object Detection | Haonian Xie (University of Science and Technology of China) |
| 11:12 | Brief Q&A | |
| 11:15 | Discussion, Follow Up | Prof. Juin-In Guo (NCTU) |
| 11:20 | Close | Prof. Juin-In Guo (NCTU) |
Organisers
- Angeliki Katsenou (Co-Chair)
- Paul Hill (Co-Chair)
- Natheera Anantrsirichai
- Fan Zhang
- Alexandra Malyugina
Schedule:
Wednesday, 8 July – London (BST time zone)
| Time | Talk/Paper | Speaker(s) |
|---|---|---|
| 14.30 | Welcome and Introduction | A. Katsenou, P. Hill |
| 14.35 | Encoding in the Dark Grand Challenge: an Overview | N. Anantrasirichai, F. Zhang, A. Malyugina, P. Hill, A. Katsenou |
| 14.45 | Enhancement and Encoding of Low Light Videos based on a Dehazing algorithm | Hong Gao, Yuan Zhang, Jin Wei, Boya Cheng |
| 14.55 | Q&A | |
| 15.00 | A CNN-based Post-Processing Algorithm for Dark Videos | Li Song, Donghui Feng, Yiwei Zhang |
| 15.10 | Q&A | |
| 15.15 | Benchmarking and Results from Quality Assessment | Alexandra Malyugina, Fan Zhang |
| 15.23 | Q&A (Brief) | |
| 15.25 | Presentation of Awards | Ioannis Katsavounidis1, Joel Sole2 (1Facebook, 2 Netflix) |
| 15:30 | Close | A. Katsenou |
Organisers
- Prof. Atanas Gotchev (Chair)
- Robert Bregovic
Schedule:
Wednesday, 8 July – London (BST time zone)
| Start | Talk/Paper | Speaker(s) |
|---|---|---|
| 10:00 | Welcome and Introduction | |
| 10:05 | Overview of Grand Challenge | A. Gotchev |
| 10:15 | Datasets | Robert Bregovic (TAU) |
| 10:30 | Overview of Proposed Solutions, Assessment Methodology, Benchmarking, Results and Demonstration | Yuan Gao (TAU) |
| 10:55 | Q&A | |
| 11:10 | Awards and Plenary Discussion | |
| 11:25 | Closing Remarks and Follow Up | A. Gotchev |
| 11:30 | Close | |