Submission
Deadline: April 10,
2016
Please click on the session links
for more details on each session Focus and Aims.
Session Chairs:
Zakia Hammal , Merlin
Teodosia Suarez, Ognjen Rudovic
There is a growing research
interest of the computer vision and machine learning community in modeling
context in various vision-based domains. While significant advances in this
direction have been made for object detection and recognition, there has been
little progress in leveraging context to improve the computer vision and
machine-learning algorithms for automatic affect recognition. This is despite a
large body of cognitive evidence emphasizing the importance of context for
successful interpretation of human affect. To this end, CVPR provides an ideal
environment to gather researchers working on different domains (from low-level
image modeling for object detection to high-level modeling of complex
spatio-temporal dependencies in human-interaction data) to share their vision
on and propose novel approaches for modeling context in affect recognition,
such as: modeling human affect in group activities, its temporal
reasoning, different levels of hierarchies (from low-level image descriptors to
high level interpretation of human affect), as well as context-sensitive fusion
of multiple modalities.
The first session will focus on:
§
Context-sensitive affect recognition from still images or videos
§
Audio and/or physiological data modeling for context-sensitive
affect recognition
§
Affect tagging in images, videos or speech using context
§
Modeling human-object interactions for affect recognition
§
Modeling scene context for affect recognition
§
Modeling social contexts for affect recognition
§
Domain adaptation for context-aware affect recognition
§
Deep networks for context-aware affect recognition
§
Multi-modal context-aware fusion for affect recognition
§
Context based corpora recording and annotation
§
Theoretical and empirical analysis of influence of context on
affect recognition
§
Context based and affect-aware applications
1:30 - 2:15 Keynote speaker1
Oral presentations session
1
2:15 - 2:30 Paper 1
2:30 - 2:45 Paper 2
2:45 - 3:00 Paper 3
3:00 - 3:15 Paper 4
3:15 - 3:35 Afternoon break
Session Chairs:
Irene Kotsia, Mihalis Nicolaou,
Guoying Zhao, Stefanos Zafeiriou
Human face is probably the most researched object in image
analysis and computer vision. One of the main reasons behind its popularity is
that the applications of automatic face analysis algorithms are numerous and
span several fields, from Human Computer Interaction (expression recognition
for automatic analysis of affect) to law enforcement (face recognition). Until
less than a decade ago the majority of face analysis algorithms have been
evaluated in databases that were captured in constrained conditions. The research
has gradually shifted to facial images captured “in-the-wild”. For certain
tasks, mostly revolving around analysis of facial affect, such as estimation of
continuous emotion dimensions, as well as detection of activation of FAUs,
research results are still mainly reported in datasets that contain facial
images of a small number of people captured in laboratory conditions. The
second session solicits papers on databases on vision based affect analysis in
unconstrained conditions.
The second session will focus on:
§
Databases for
spontaneous and naturalistic facial expression analysis
"in-the-wild".
§
Databases for
spontaneous and naturalistic facial action unit detection
"in-the-wild".
§
Databases for valence
and arousal from face/body "in-the-wild".
§
Databases for
micro-expression analysis.
§
Methodologies for
facial expression analysis "in the wild".
§
Methodologies for
valence and arousal estimation "in the wild".
§
Methodologies for body
expression analysis "in the wild".
§
Deep learning for the
above tasks.
§
Facial/body
deformation analysis "in-the-wild" (include dense flow computation).
3:35 - 4:20 Keynote speaker2
Oral presentations session
2
4:20 - 4:35 Description of the
challenge, dataset and results
4:35 - 4:50 Paper 1
4:50 - 5:05 Paper 2
5:05 - 5:20 Paper 3
Combined Poster Session (CBAR & Wild )
5:20 - 18:20
Program Committee
Busso Carlos, UT-Dallas, USA
Bianchi-Berthouze Nadia, University College
London, UK
Heylen Dirk, University of Twente, The
Netherlands
Hess Ursula, Humboldt University, Berlin
Martinez Aleix, The Ohio State
University, USA
Mahoor Mohammad, University of
Denver, USA
Narayanan Shrikanth, University of
Southern California, USA
Pavlovic Vladimir, Rutgers
University, USA
Rodrigo Ma. Mercedes, Ateneo
de Manila University
Schuller Bjoern, Imperial College
London, UK
Truong Khiet, University of
Twente, The Netherlands
Whitehill Jacob, Harvard
University, USA
Yin Lijun, Binghamton University,
USA
Organizers
Zakia Hammal,
Merlin Teodosia Suarez,
Ognjen Rudovic
Irene Kotsia,
Mihalis Nicolaou,
Guoying Zhao,
Stefanos Zafeiriou