Challenges



Emotion Recognition in the Wild Challenge 2016

The fourth Emotion Recognition in the Wild (EmotiW) 2016 Grand Challenge consists of an all-day event with a focus on affective sensing in unconstrained conditions. There are two sub-challenges: audio-video based emotion classification sub-challenge and image based group emotion recognition sub-challenge. EmotiW 2016 extends the platform introduced in EmotiW challenges 2013-15 and this year a new image based group emotion based sub-challenge has been added.

Challenge website: https://sites.google.com/site/emotiw2016

Contact email: emotiw2014[AT]gmail.com

Grand Challenge Program

Saturday, 12 November 2016

All sessions will take place in the Time24 Room 183

                   
09:00-09:10 EmotiW 2016: Video and Group-Level Emotion Recognition Challenges
Abhinav Dhall (University of Waterloo), Roland Goecke (University of Canberra), Jyoti Joshi (University of Waterloo), Jesse Hoey (University of Waterloo), Tom Gedeon (Australian National University) 
09:10-10:10 Keynote talk : Human-Centered Computing: Using Speech to Understand Behavior
 Prof. Emily Mower Provost
University of Michigan Ann Arbor
10:10-10:30 AM coffee break 
10:30-10:45 Emotion Recognition in the Wild from Videos using Images
Sarah Adel Bargal (Boston University), Emad Barsoum (Microsoft Research), Cristian Canton Ferrer (Microsoft Research), Cha Zhang (Microsoft Research) 
10:45-11:00 A deep look into group happiness prediction from images
Aleksandra Cerekovic
11:00-11:15 Video-based Emotion Recognition Using CNN-RNN and C3D Hybrid Networks
Yin Fan (iQiyi.com), Xiangju Lu (iQiyi.com), Dian Li (iQiyi.com), Yuanliu Liu (iQiyi.com) 
11:15-11:30 LSTM for Dynamic Emotion and Group Emotion Recognition in the Wild
Bo Sun (Beijing Normal University), Qinglan Wei (Beijing Normal University), Liandong Li (Beijing Normal University), Qihua Xu (Beijing Normal University), Jun He (Beijing Normal University), Lejun Yu (Beijing Normal University) 
11:30-11:45 Multi-Clue Fusion for Emotion Recognition in the Wild
Jingwei Yan (Southeast University), Wenming Zheng (Southeast University), Zhen Cui (Southeast University), Chuangao Tang (Southeast University), Tong Zhang (Southeast University), Yuan Zong (Southeast University) 
11:45-12:00 Multi-view Common Space Learning for Emotion Recognition in the Wild
Jianlong Wu (Peking University), Zhouchen Lin (Peking University), Hongbin Zha (Peking University) 
12:00-13:20 Lunch 
13:20-14:20 Keynote talk : Learning Representations of Human Behavior
Prof. Stefan Scherer
University of Southern California
14:20-14:35
Anbang Yao (Intel Research Lab China) 
14:35-14:50 Group happiness assessment using geometric features and dataset balancing
Vassilios Vonikakis (ADSC), Yasin Yazici (ADSC), Viet Dung Nguyen (ADSC), Stefan Winkler (ADSC)
14:50-15:05 Happiness Level Prediction with Sequential Inputs via Multiple Regressions
Jianshu Li (National University of Singapore), Sujoy Roy (SAP Labs), Jiashi Feng (National University of Singapore), Terence Sim (National University of Singapore) 
15:05-15:30 PM coffee break 
15:30-16:30 Keynote talk : Insights from Large-scale Analysis of Facial Expressions "In-the-Wild"
Dr. Daniel Mcduff
Microsoft Research 
16:30-16:40 Wild Wild Emotion: A Multimodal Ensemble Approach
John Gideon (University of Michigan Ann Arbor), Biqiao Zhang (University of Michigan Ann Arbor), Zakaria Aldeneh (University of Michigan Ann Arbor), Yelin Kim (State University of New York Albany) , Soheil Khorram (University of Michigan Ann Arbor), Duc Le (University of Michigan Ann Arbor), Emily Mower Provost (University of Michigan Ann Arbor)
16:40-16:50 Video Emotion Recognition in the Wild based on Fusion of Multimodal Features
Shizhe Chen (Renmin University of China), Xinrui Li (Renmin University of China), Qin Jin (Renmin University of China), Shilei Zhang (Intel Research Lab), Yong Qin (Intel Research Lab) 
16:50-17:00 Audio and Face Video Emotion Recognition in the Wild Using Deep Neural Networks and Small Datasets
Wan Ding (Central China Normal University), Dong-Yan Huang (Institute of Infocomm Research), Mingyu Xu (University of British Columbia), Weisi Lin (Nanyang Technical University), XInguo Yu (Central China Normal University) 
17:00-17:10 Automatic Emotion Recognition in the Wild Using an Ensemble of Static and Dynamic Representations
Mostafa Mehdipour Ghazi (Sabanci University), Hazim Ekenel (Istanbul Technical University) 
17:10-17:30 Challenge results

Timeline

Challenge website up mid February 2016
Train and validate data available mid April 2016
Test data available 30 June 2016
Last date for uploading the results 15 July 2016
Paper submission deadline 25 July 2016
Notification 25 August 2016
Camera-ready papers 15 September 2016

Organizers

  • Abhinav Dhall (University of Canberra)
  • Roland Goecke (University of Canberra and Australian National University)
  • Jyoti Joshi (University of Canberra)
  • Tom Gedeon (Australian National University)


ICMI 2016 ACM International Conference on Multimodal Interaction. Copyright © 2015-2017