CVPR 2020

Challenges and Promises of

Inferring Emotion from Images and Video

When: June 15, 2020

Where: Seattle, WA

Paper Submission Deadline: March 19, 2020 (11:59 pm PST)

Notification to authors: April 14, 2020

Camera Ready Deadline: April 20, 2020

Program

Keynotes and Orals are served asynchronously.
If you do not have CVPR 2020 registration, please check our YouTube Playlist, which will be updated throughout June 15th.
If you have questions to the speakers, please submit your questions here.
We will answer your questions during our Discussion session (11:30am-12:15pm PDT, June 15 at Zoom Entrance).

 
8:30 am [talk&slide] Welcom message from the chairs
8:45 am [talk&slide] Invited speaker: Lisa Feldman Barrett
9:30 am [talk&slide] Invited speaker: Ralph Adolph
10:15 am Coffee break
10:45 am [talk&slide] Invited speaker: Racheal Jack
11:30 am [Zoom Entrance] Discussion. Please join us live for Q&A and discussion with all speakers.
12:15 pm Lunch break
1:15 pm [talk&slide] Summary of the EmotioNet challenge and results 2017-2020
Qianli Feng
1:30 pm [talk&slide] 1st place in the 2020 EmotioNet challenge:
TAL EmotioNet Challenge 2020 Rethinking the Model Chosen Problem in Multi-Task Learning
Pengcheng Wang, Zihao Wang, Zhilong Ji, Xiao Liu, Songfan Yang, and Zhongqin Wu
1:45 pm [talk&slide] 2nd place in the 2020 EmotioNet challenge:
Facial Action Unit Recognition in the Wild with Multi-Task CNN Self-Training for the EmotioNet Challenge
Philipp Werner, Frerk Saxen, and Ayoub Al-Hamadi
2:00 pm [talk&slide] 3rd place in the 2020 EmotioNet challenge:
Multiple Transfer Learning and Multi-label Balanced Training Strategies for Facial AU Detection In the Wild
Sijie Ji, Kai Wang, Xiaojiang Peng, Jianfei Yang, Zhaoyang Zeng, and Yu Qiao
2:15 pm Coffee Break
2:30 pm [talk&slide] Invited speaker: Agata Laperdiza
3:15 pm Coffee Break
3:30 pm [talk&slide] Challenges in Recognizing Spontaneous and Intentionally Expressed Reactions to Positive and Negative Images
Jennifer Healey, Haoliang Wang, and Niyati Chhaya
3:45 pm [talk&slide] Discriminant Distribution-Agnostic Loss for Facial Expression Recognition in the Wild
Amir Hossein Farzaneh, and Xiaojun Qi
4:00 pm [talk&slide] Predicting Sentiments in Image Advertisements using Semantic Relations among Sentiment Labels
Stephen Philip Pilli, Manasi Patwardhan, Niranjan Pedanekar, and Shirish Karande
4:15 pm [Zoom Entrance] Final Remarks

Overview

There is a disconnect between what computer vision (and AI) researchers think emotions are and how they are conveyed through facial expressions and body pose, and what the actual science tells us.

Take faces as an example. Undoubtedly, faces offer information that helps us navigate our social world, influence whom we love, and determine who we trust or who we believe to be guilty of a crime. But to what extent does an individual’s face reveal the person’s internal emotions? To what extent (and how) can we design computer vision systems to accurately interpret an emotion or intention from a raised eyebrow, a curled lip, or a narrowed eye? And to what degree are these visual cues influenced by body pose and context?

Recent research shows that faces or body expressions alone are insufficient to perform a reverse inference of image to emotion, and that context, personal believes, and cultural must be accounted for. This workshop will present these limitations and examine several alternative approaches to successfully interpret the emotion and intent of others.

Invited Speakers

Avatar

Prof. Lisa Feldman Barrett

University Distinguished Professor of psychology at Northeastern University, with appointments at Harvard Medical School and Massachusetts General Hospital in psychiatry and radiology.

Avatar

Prof. Agata Lapedriza Garcia

Associate professor, Universitat Oberta de Catalunya (Barcelona).

Avatar

Prof. Ralph Adolphs

Bren Professor of Psychology, Neuroscience, and Biology; Allen V. C. Davis and Lenabelle Davis Leadership Chair, Caltech Brain Imaging Center; Director, Caltech Brain Imaging Center.

Avatar

Prof. Rachael Jack

Reader at University of Glasgow; and associate member of the Institute of Neuroscience and Psychology.

Topics of Interests

(include but are not limited to)

Submission Guidelines

All submissions will be handled electronically via the conference's CMT Website. By submitting a paper, the authors agree to the policies stipulated in this website.

Papers are limited to eight pages, including figures and tables, in the CVPR style. Additional pages containing only cited references are allowed. Please refer to the following files for detailed formatting instructions:

Papers that are not properly anonymized, or do not use the template, or have more than eight pages (excluding references) will be rejected without review.

Your submission must follow the CVPR guidelines given here.