COCO + Places 2017
Joint Workshop of the COCO and Places Challenges at ICCV 2017

1. Overview

The goal of the joint COCO and Places Challenge is to study object recognition in the context of scene understanding.

2. COCO Challenges

COCO is an image dataset designed to spur object detection research with a focus on detecting objects in context. The annotations include pixel-level segmentation of object belonging to 80 categories, keypoint annotations for person instances, stuff segmentations for 91 categories, and five image captions per image. The specific tracks in the COCO 2017 Challenges are (1) object detection with bounding boxes and segmentation masks, (2) joint detection and person keypoint estimation, and (3) stuff segmentation. We describe each next.

2.1. COCO Detection Challenge

The COCO 2017 Detection Challenge is designed to push the state of the art in object detection forward. Teams are encouraged to compete in either (or both) of two object detection challenges: using bounding box output or object segmentation output. For full details of this task please see the COCO Detection Challenge page.

2.2. COCO Keypoint Challenge

The COCO 2017 Keypoint Challenge requires localization of person keypoints in challenging, uncontrolled conditions. The keypoint challenge involves simultaneously detecting people and localizing their keypoints (person locations are not given at test time). For full details of this task please see the COCO Keypoints Challenge page.

2.3. COCO Stuff Challenge

The COCO 2017 Stuff Segmentation Challenge is designed to push the state of the art in semantic segmentation of stuff classes. Whereas the COCO 2017 Detection Challenge addresses thing classes (person, car, elephant), this challenge focuses on stuff classes (grass, wall, sky). For full details of this task please see the COCO Stuff Challenge page.

3. Places Challenges

The Places Challenge will host three tracks meant to complement the COCO Challenges. The data for the 2017 Places Challenge is from the pixel-wise annotated image dataset ADE20K, in which there are 20K images for training, 2K validation images, and 3K testing images. The three specific tracks in the Places Challenge 2017 are: (1) scene parsing, (2) instance segmentation, and (3) semantic boundary detection. See the Places Challenge Page for detailed information.

4. Challenge Dates

September 30, 2017
Detection & Keypoints Submission deadline (11:59 PST)
September 30, 2017
[Extended] Places Submission deadline (11:59 PST)
October 8, 2017
[Extended] Stuff Submission deadline (11:59 PST)
October 15, 2017
Challenge winners notified
October 29, 2017
Winners present at ICCV 2017 Workshop

5. Workshop Schedule - 10.29.2017

8:50 Opening Comments
9:00 Detection Challenge Track Tsung-Yi Lin (Cornell Tech, Google Research)
9:10 Detection/Segmentation and Places Challenge Competitor Team Megvii (Face++)
9:30 Detection/Segmentation Challenge Competitor Team UCenter (CUHK & Peking University)
9:50 Detection/Segmentation Challenge Competitor Team MSRA
10:00 Detection/Segmentation Challenge Competitor Team FAIR
10:10 Morning Break: Coffee + Posters
10:40 Keypoints Challenge Track Matteo Ronchi (Caltech)
10:50 Keypoints Challenge Competitor Team Megvii (Face++)
11:05 Keypoints Challenge Competitor Team OKS (Beihang University & SenseTime)
11:20 Stuff Challenge Track Holger Caesar (University of Edinburgh)
11:30 Stuff Challenge Competitor Team FAIR
11:45 Stuff Challenge Competitor Team Oxford
12:00 Invited Talk Vladlen Koltun (Intel Labs)
12:30 Lunch
14:00 Invited Talk Raquel Urtasun (University of Toronto, Vector Institute, Uber ATG Toronto)
14:30 Places Challenge Track Bolei Zhou (MIT), Hang Zhao (MIT)
14:40 Places Challenge Competitor Team CASIA_IVA_JD (Institute of Automation, Chinese Academy of Sciences, & JD)
15:00 Places Challenge Competitor Team WinterIsComing (ByteDance)
15:20 Places Challenge Competitor Team G-RMI (Google Research)
15:45 Afternoon Break: Coffee + Posters
16:15 Discussion Panel Genevieve Patterson (MSR NE), Hang Zhao (MIT),

Note: schedule subject to change.

6. Invited Speakers

Raquel Urtasun

University of Toronto, Vector Institute, Uber ATG Toronto

Raquel Urtasun is the Head of Uber ATG Toronto. She is also an Associate Professor in the Department of Computer Science at the University of Toronto, a Canada Research Chair in Machine Learning and Computer Vision and a co-founder of the Vector Institute for AI.

Vladlen Koltun

Intel Labs

I direct a basic research lab at Intel Labs. We are based in two locations: Santa Clara, California and Munich, Germany. We are hiring interns, postdocs, and staff researchers in both locations. We are broadly interested in visual computing and intelligent systems. Our work is usually published in computer vision, machine learning, and computer graphics conferences.