AMFG 2018 - 8th IEEE Workshop on Analysis and Modeling of Faces and Gestures

Over the past five years, we have experienced rapid advances in facial recognition technologies. This due with many thanks to the deep learning (i.e., dating back to 2012, AlexNet) and large-scale, labeled facial image collections. The progress made in deep learning continues to push renown public facial recognition databases to near saturation which, thus, calls more evermore challenging image collections to be compiled as databases. To name a few: Labeled Faces in the Wild (LFW) database, YouTube Faces database, and, more recently, CASIA WebFace, MegaFace, MS-Celeb-1M. In practice, and even widely in applied research, using off-the-shelf deep learning models has become the norm, as numerous pre-trained networks are available for download and are readily deployed to new, unseen data (e.g., VGG-Face, ResNet, amongst other types). We have almost grown “spoiled” from such luxury, which, in all actuality, has enabled us to stay hidden from many truths. Theoretically, the truth behind what makes neural networks more discriminant than ever before is still, in all fairness, unclear—rather, they act as a sort of black box to most practitioners and even researchers, alike. More troublesome is the absence of tools to quantitatively and qualitatively characterize existing deep models, which, in itself, could yield greater insights about these all so familiar “black boxes”. With the frontier moving forward at rates incomparable to any spurt of the past, challenges such as high variations in illuminations, pose, age, etc., now confront us. However, state-of-the-art deep learning models often fail when faced with such challenges owed to the difficulties in modeling structured data and visual dynamics.
Alongside the effort spent on conventional face recognition is the research done to automatically understand social media content. This line of work has attracted attention from industry and academic researchers from all sorts of domains. To understand social media the following capabilities must be satisfied: face and body tracking (e.g., facial expression analysis, face detection, gesture recognition), face and body characterization (e.g., behavioral understanding, emotion recognition), face, body and gesture characteristic analysis (e.g., gait, age, gender and ethnicity recognition), group understanding via social cues (e.g., kinship, non-blood relationships, personality), and visual sentiment analysis (e.g., temperament, arrangement). Thus, needing to be able to create effective models for visual certainty has significant value in both the scientific communities and the commercial market, with applications that span topics of human-computer interaction, social media analytics, video indexing, visual surveillance, and Internet vision. Currently researchers have made significant progress addressing the many problems in the social domain, and especially when considering off-the-shelf and cost-efficient vision HW products available these days, e.g. Kinect, Leap, SHORE, and Affdex. Nonetheless, serious challenges still remain, which only amplifies when considering the unconstrained imaging conditions captured by different sources focused on non-cooperative subjects. It is these latter challenges that especially grabs our interest, as we sought out to bring together the cutting-edge techniques and recent advances of deep learning to solve the challenges above in social media.
This one-day serial workshop (i.e., AMFG2018) will provide a forum for researchers to review the recent progress of recognition, analysis and modeling of face, body, and gesture, while embracing the most advanced deep learning systems available for face and gesture analysis, particularly, under unconstrained environment such as social media. The workshop includes up to two keynotes, along with peer-reviewed papers (oral and poster). Original high-quality contributions are solicited on the following topics:​
Novel deep model, deep learning survey, or comparative study for face/gesture recognition;
Deep learning methodology, theory, and its application to social media analytics;
Deep learning for internet-scale soft biometrics and profiling: age, gender, ethnicity, personality, kinship, occupation, beauty ranking, and fashion classification by facial or body descriptor;
Deep learning for detection and recognition of faces and bodies with large 3D rotation, illumination change, partial occlusion, unknown/changing background, and aging (i.e., in the wild); special attention will be given large 3D rotation robust face and gesture recognition;
Motion analysis, tracking and extraction of face and body models captured by mobile devices;
Face, gait, and action recognition in low-quality (e.g., blurred), or low-resolution video from fixed or mobile device cameras;
Novel mathematical models and algorithms, sensors and modalities for face & body gesture and action representation, analysis, and recognition for cross-domain social media;
Social/psychological based studies that aids in understanding computational modeling and building better automated face and gesture systems with interactive features;
Novel social applications involving detection, tracking & recognition of face, body, and action;
Face and gesture analysis for sentiment analysis in social media;
Other applications involving face and gesture analysis in social media content.