The 2007 IEEE International Workshop on Analysis and Modeling of Faces andGestures (AMFG) is the third workshop of its type organized in conjunction withICCV, this time in Rio de Janeiro, Brazil. Our primary goal is to bring togetherresearchers and research groups to review the status of recognition, analysis andmodeling of face, gesture, activity, and behavior; to discuss the challenges thatwe are facing; and to explore future directions.This year we received 55 submissions. Each paper was reviewed by threeprogram committee members. The whole reviewing process was double blind.However, due to size limit, we were only able to accommodate 22 papers, amongwhich 8 are orals and 14 are posters. The topics covered by these acceptedpapers include feature representation, 3D face, robust recognition under poseand illumination variations, video-based face recognition, learning, facial motionanalysis, body pose estimation, and sign recognition.A special word of thanks goes to Dr. Feng Zhao, our organizing chair, for hisdedication and great efforts in maintaining both the online submission systemand workshop website and in handling most of the author contacts. We areindebted to the advisory committee members for their valuable suggestions andto the program committee members for their hard work and timely reviews.Finally, we thank Cognitec System GmbH and Siemens Corporate Research fortheir sponsorship.