Jesse Brizzi
Automatic Expression Spotting in Videos
Automatic Expression Spotting in Videos -(Second Author)
In this paper, we propose a novel solution for the problem of segmenting macro- and microexpressions frames (or retrieving the expression intervals) in video sequences, which is a prior step for many expression recognition algorithms. The proposed method exploits the non-rigid facial motion that occurs during facial expressions by capturing the optical strain corresponding to the elastic deformation of facial skin tissue. The method is capable of spotting both macro expressions which are typically associated with expressed emotions and rapid micro- expressions which are typically (but not always) associated with semi-suppressedmacro-expressions. We test our algorithm on three datasets, including a newly released hour-long video with two subjects recorded in a natural setting that includes spontaneous facial expressions. We also report results on a dataset that contains 75 feigned macro-expressions and 37 feigned micro-expressions. We achieve over a 75% true positive rate with a 1% false positive rate for macro-expressions, and nearly 80% true positive rate for spotting microexpressions with a .3% false positive rate. For the spontaneous expression dataset, we achieve an average TPR of 68% at roughly a 10% FPR.
Machine Learning Engineer && Software Engineer
Machine Learning, Computer Vision, Full Stack/Backend Engineering, Data Science
Machine Learning Software Engineer @ Instagram
Founder @ inferdo
jessebrizzi@{ gmail | fb | inferdo }.com
-
2019 Aug 26
Serving deep learning at Curalate with Apache MXNet, AWS Lambda, and Amazon Elastic Inference
-
2019 Mar 27
How to Setup a Scheduled Scala Spark Job on AWS
-
2019 Mar 6
(meetup talk) Choosing a Deep Learning Library: There are a Lot of Them
-
2018 Aug 13
(Interview) Curalate makes social sell with AI using Apache MXNet on AWS
-
2018 Aug 1
How Curalate uses MXNet on AWS for some Deep Learning Magic
-
2018 Mar 23
Choosing a Deep Learning library for developing and deploying your App/Service
-
2017 Feb 1
Mechanical Turk Lessons Learned
-
2014 Dec 8
Optical Flow based Facial Expression Suppression in Videos
-
2014 Aug 10
Automatic Expression Spotting in Videos
-
2013 Jul 31
Expression Detection in Infants Through Facial Deformation Performance Analysis