DescriptionRecognizing facial expressions from facial video sequences is an important and unsolved problem. Among many factors that contribute to the challenges of this task are: non-frontal facial poses, poorly aligned face images, large variations in the temporal scale of facial expressions, and the subtle differences between different subjects for the same facial expression etc. A successful video-based facial expression analysis system should be able to handle at least the following problems: robust face tracking, or spatial alignment of the faces, video segmentation, effective feature representation and selection schemes which are robust to face mis-alignment and temporal normalization by sequential classifier. In this work we report several advances we made in building various components of a system for classifying facial expressions from video inputs. Particularly, my work focus on robust face tracking, facial feature representation and selection under different face alignment conditions, sequential modeling for facial expression recognition. We performed extensive experiments using the proposed algorithms on publicly available dataset and achieved state of the art performances.