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) Talk
9:10 Detection/Segmentation/Places Competitor Team Megvii (Face++) Talk
9:30 Detection/Segmentation Competitor Team UCenter (CUHK & Peking University) Talk
9:50 Detection/Segmentation Competitor Team MSRA Talk
10:00 Detection/Segmentation Competitor Team FAIR Talk
10:10 Morning Break: Coffee + Posters
10:40 Keypoints Challenge Track Matteo Ronchi (Caltech) Talk
10:50 Keypoints Competitor Team Megvii (Face++) Talk
11:05 Keypoints Competitor Team OKS (Beihang University & SenseTime) Talk
11:20 Stuff Challenge Track Holger Caesar (University of Edinburgh) Talk
11:30 Stuff Competitor Team FAIR Talk
11:45 Stuff Competitor Team Oxford Active Vision Lab ——
12:00 Invited Talk Vladlen Koltun (Intel Labs) Talk
12:30 Lunch
14:00 Invited Talk Genevieve Patterson (MSR NE) Talk
14:15 Invited Talk Alexander Kirillov (University of Heidelberg & FAIR) Talk
14:30 Places Challenge Track Bolei Zhou (MIT), Hang Zhao (MIT) Talk
14:45 Places Competitor Team G-RMI (Google Research) Talk
15:05 Places Competitor Team WinterIsComing (ByteDance) Talk
15:25 Places Competitor Team CASIA_IVA_JD (Institute of Automation,
Chinese Academy of Sciences, & JD)
Talk
15:45 Afternoon Break: Coffee + Posters
16:15 Discussion Panel Genevieve Patterson (MSR NE), Hang Zhao (MIT)

6. Invited Speakers

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.

Genevieve Patterson

MSR NE

Genevieve is a postdoc at MSR New England. She studies crowd-driven Computer Vision systems and deep learning models for medical and cultural problems. Her interests include visual attribute discovery, crowd-powered dataset annotation, fine-grained object recognition, medical network interpretability, multimodal networks, and active learning. Her work has appeared at CVPR, ECCV, NIPS, IJCV, and HCOMP, where her paper introducing a system for crowdsourced fine-grained one-shot object detection was finalist for Best Paper in 2015. She received her PhD from Brown University in 2016 under the direction James Hays (now of Georgia Tech).

Alex Kirillov

University of Heidelberg & FAIR

Alex is a last year PhD student at the University of Heidelberg (Germany) supervised by Carsten Rother. He is currently an intern in Facebook AI Research working with Piotr Dollár, Kaiming He, and Ross Girshick. He has published numerous papers in top-tier Computer Vision and Machine Learning venues such as CVPR, ICCV, and NIPS. Alex also helped organize a CVPR tutorial on diversity in Computer Vision systems in 2016. His main research interests are deep learning models for structured output and diversity modeling for Computer Vision applications. Alex is currently looking for a full-time research position in industry starting from Spring 2018.