Introduction
The purpose of the workshop is to present the methods and results of the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) 2016 and Common Objects in Context (COCO) 2016 Detection Challenge. Challenge participants with the most successful and innovative entries will be invited to present. We encourage team to participate in both the ImageNet and COCO detection challenges. This year we are also pleased to announce the new COCO 2016 Keypoint Challenge.History
2015Download data
- To download challenge data for ILSVRC2016, please register at here.
- To download challenge data for COCO, please click here.
News
- September 26, 2016: Results for ILSVRC2016 and Places2 are announced!
- October 2, 2016: Results for COCO detection challenge and keypoint challenge are announced!
Workshop Schedule
The workshop will be on Sunday, October 9th at Grand Hotel Krasnapolsky.| 8:30-8:50 |
|
Alex Berg and Ross Girshick: Opening remarks | slide |
| ILSVRC Localization/Classification Challenge | |||
| 8:50-9:00 |
|
Jia Deng: ILSVRC2016 object localization: introduction, results | slide |
| 9:00-9:15 |
|
Dahua Lin: PolyNet: A Pursuit of Structural Diversity within a Single Network | slide |
| 9:15-9:30 |
|
Shicai Yang: Towards good practices for deep visual recognition | slide |
|
Xiaoteng Zhang: Good practices for deep feature fusion | slide video | |
| 9:30-10:00 Coffee + Posters | |||
| 10:00-10:30 |
|
Keynote speaker: Sanja Fidler | |
| Object Detection from Video Challenge | |||
| 10:30-10:40 |
|
Alex Berg: ILSVRC2016 object detection from video: introduction, results | slide |
| 10:40-11:00 |
|
Byungjae Lee: MCMOT: Multi-Class Multi-Object Tracking with Bayesian Framework | slide |
|
Jiankang Deng: Efficient Object Detection From Videos | slide | |
| Scene Classification/Parsing Challenge | |||
| 11:00-11:15 |
|
Bolei Zhou: Places scene classification/parsing: introduction, results | slide |
| 11:15-11:30 |
|
Jianping Shi: Understanding scene in the wild | slide |
| 11:40-1:00 Lunch | |||
| 1:00-1:30 |
|
Keynote speaker: Vittorio Ferrari | |
| ILSVRC & COCO Object Detection and Segmentation Challenges | |||
| 1:30-2:00 |
|
Alex Berg, Genevieve Patterson and Matteo Ruggero Ronchi: ILSVRC & COCO object detection/segmentation: introduction, results | slide |
| 2:00-2:15 |
|
Wanli Ouyang: CRAFTing GBD-Net | slide |
| 2:15-2:30 |
|
Tang Sheng: MCG-ICT-CAS Object Detection at ILSVRC 2016 | slide |
| 2:30-2:45 |
|
Jonathan Huang: G-RMI Object Detection | slide |
| 2:45-3:00 |
|
MSRA Object Segmentation | slide |
| 3:00-3:30 Coffee + Posters | |||
| COCO Person Keypoint Detection Challenge | |||
| 3:30-4:00 |
|
Genevieve Patterson and Matteo Ruggero Ronchi: COCO person keypoint detection: introduction, results | slide |
| 4:00-4:15 |
|
Zhe Cao, Tomas Simon, and Shih-En Wei: Multi-Person Pose Estimation with Part Affinity Field | slide |
| 4:15-4:30 |
|
George Papandreou: G-RMI Keypoints Detection | slide |
| 4:30-4:45 |
|
Jia Deng, Bolei Zhou and Genevieve Patterson: Award | |
| 4:45-5:00 |
|
Ross Girshick and Alex Berg: Future Plans & Discussion | |
| 5:00-6:00 Posters | |||
|
| |||