Static Facial Expressions In The Wild: Data and Experiment Protocol Abhinav Dhall 1 and Roland Goecke 2,1 and Simon Lucey 3 and Tom Gedeon 1 1 School of Computer Science, CECS, Australian National University, Australia 2 Vision & Sensing, ISE, University of Canberra, Australia 3 CSIRO, Australia Email: abhinav.dhall@anu.edu.au, roland.goecke@ieee.org, simon.lucey@csiro.au, tom.gedeon@anu.edu.au 1 Introduction Quality data recorded in varied realistic environments is vital for effective human face related research. Facial expression analysis has been a very active field of research and many robust methods have been reported in the literature in the past. However these methods have been experimented on different databases and using different protocols within the same databases. The lack of a standard protocol makes it difficult to compare systems and acts as a hinderance in the progress of the field. Therefore, we propose a facial expression challenge in the Wild. Currently available datasets for human facial expression analysis have been generated in highly controlled lab environments. We present a new static facial expression database Static Facial Expressions In The Wild (SFEW) [2] extracted from a temporal facial expressions database Acted Facial Expressions In the Wild (AFEW)[1] which we have extracted from movies. We propose a person independent training and testing protocol for expression recognition. Fig. 1. Sample images from SFEW database.