Micro-Expression Spotting Using the Riesz Pyramid

Duque, Carlos Arango; Alata, Olivier; Emonet, Rémi; Legrand, Anne-Claire; Konik, Hubert

doi:10.1109/wacv.2018.00014

Cited by 32 publications

(15 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It is a multi-scale and multi-orientation image decomposition method, used in a wide variety of image processing and computer vision tasks, such as motion magnification (Wadhwa et al 2016). The recent paper (Duque et al 2018) used Riesz Pyramid (a variant of Complex Steerable Pyramid) for micro-expression spotting, which supports our expectation that phase differences will be useful for emotion recognition.…”

Section: Related Workmentioning

confidence: 72%

See 1 more Smart Citation

MIMAMO Net: Integrating Micro- and Macro-Motion for Video Emotion Recognition

Deng

Chen

Zhou

et al. 2020

AAAI

View full text Add to dashboard Cite

Spatial-temporal feature learning is of vital importance for video emotion recognition. Previous deep network structures often focused on macro-motion which extends over long time scales, e.g., on the order of seconds. We believe integrating structures capturing information about both micro- and macro-motion will benefit emotion prediction, because human perceive both micro- and macro-expressions. In this paper, we propose to combine micro- and macro-motion features to improve video emotion recognition with a two-stream recurrent network, named MIMAMO (Micro-Macro-Motion) Net. Specifically, smaller and shorter micro-motions are analyzed by a two-stream network, while larger and more sustained macro-motions can be well captured by a subsequent recurrent network. Assigning specific interpretations to the roles of different parts of the network enables us to make choice of parameters based on prior knowledge: choices that turn out to be optimal. One of the important innovations in our model is the use of interframe phase differences rather than optical flow as input to the temporal stream. Compared with the optical flow, phase differences require less computation and are more robust to illumination changes. Our proposed network achieves state of the art performance on two video emotion datasets, the OMG emotion dataset and the Aff-Wild dataset. The most significant gains are for arousal prediction, for which motion information is intuitively more informative. Source code is available at https://github.com/wtomin/MIMAMO-Net.

show abstract

Section: Related Workmentioning

confidence: 72%

“…In our proposed method, we integrate a Complex Steerable Pyramid with a Convolutional Neural Network as a cascade in the temporal stream. In terms of using phases or phase differences to detect emotion, our work is most similar to the work of (Duque et al 2018). They first computed the phases of facial images in the video.…”

Section: Related Workmentioning

confidence: 99%

MIMAMO Net: Integrating Micro- and Macro-Motion for Video Emotion Recognition

Deng

Chen

Zhou

et al. 2020

AAAI

View full text Add to dashboard Cite

show abstract

“…Hal ini karena berkaitan dengan pengamatan gerakan yang sangat halus dan durasi yang sangat cepat. Basis data seperti CASME II telah banyak digunakan pada banyak penelitian terdahulu (Li et al, 2018), (Duque et al, 2018). Pada beberapa sampel video yang dihasilkan oleh CASME II menunjukkan gerakan ekspresi mikro yang diikuti dengan gerakan kecil pada bagian kepala.…”

Section: Pendahuluanunclassified

Detection and Tracking of Face Location in the Pre-processing Stage of Recognition of Micro Expressions Using the Kanade-Lucas-Tomasi (KLT) Method

Choirina¹,

Rosiani²

2020

JIP

View full text Add to dashboard Cite

Penelitian dan pengamatan gerakan ekspresi mikro memerlukan tahap pre-proses yang cermat, karena berkaitan dengan pengamatan gerakan yang sangat halus dan durasi yang sangat cepat. Pada tahap ini, pendeteksian dan pelacakan area wajah harus selalu tepat agar pengamatan gerakan yang dilakukan di area wajah bisa akurat. Beberapa sampel video dataset ekspresi mikro menunjukkan adanya gerakan wajah yang diikuti dengan gerakan kecil pada bagian kepala. Gerakan-gerakan diluar gerakan pada area wajah ini akan mempengaruhi kinerja dari sistem pengenalan ekspresi mikro. Penelitian ini melakukan pendeteksian dan pelacakan lokasi wajah selama terjadinya gerakan ekspresi mikro. Digunakan metode Viola-Jones untuk deteksi wajah dan metode Kanade Lucas Tomasi (KLT) untuk melacak titik fitur. Setelah wajah terdeteksi dengan tepat, dilakukan pelacakan titik pada ujung hidung. Pelacakan gerakan pada ujung hidung ini diikuti oleh pembentukan area wajah. Sehingga area wajah akan selalu tepat posisinya walaupun ada gerakan di kepala. Data uji dan testing yang digunakan dalam penelitian ini adalah dataset CASME II. Pengujian dari penelitian ini diperoleh hasil bahwa pedeteksian dan pelacakan area wajah dapat dilakukan dengan tepat dan akurat pada semua data uji. Diharapkan dengan pembentukan area wajah yang selalu terlacak dengan tepat ini, proses berikutnya dari pengenalan ekspresi mikro dapat berjalan dengan baik.

show abstract

“…In another approach, Xia et al (2016) applied random walk model to compute the probability of frames containing MEs by considering the geometrical deformation correlation between frames in a temporal window. Duque et al (2018) designed a system that is able to differentiate between MEs and eye movements by analyzing the phase variations between frames based on the Riesz Pyramid.…”

Section: Spotting Of Facial Micro-expressionsmentioning

confidence: 99%

A Survey of Automatic Facial Micro-Expression Analysis: Databases, Methods, and Challenges

et al. 2018

View full text Add to dashboard Cite

Over the last few years, automatic facial micro-expression analysis has garnered increasing attention from experts across different disciplines because of its potential applications in various fields such as clinical diagnosis, forensic investigation and security systems. Advances in computer algorithms and video acquisition technology have rendered machine analysis of facial micro-expressions possible today, in contrast to decades ago when it was primarily the domain of psychiatrists where analysis was largely manual. Indeed, although the study of facial micro-expressions is a well-established field in psychology, it is still relatively new from the computational perspective with many interesting problems. In this survey, we present a comprehensive review of state-of-the-art databases and methods for micro-expressions spotting and recognition. Individual stages involved in the automation of these tasks are also described and reviewed at length. In addition, we also deliberate on the challenges and future directions in this growing field of automatic facial micro-expression analysis.

show abstract

Micro-Expression Spotting Using the Riesz Pyramid

Cited by 32 publications

References 18 publications

MIMAMO Net: Integrating Micro- and Macro-Motion for Video Emotion Recognition

MIMAMO Net: Integrating Micro- and Macro-Motion for Video Emotion Recognition

Detection and Tracking of Face Location in the Pre-processing Stage of Recognition of Micro Expressions Using the Kanade-Lucas-Tomasi (KLT) Method

A Survey of Automatic Facial Micro-Expression Analysis: Databases, Methods, and Challenges

Contact Info

Product

Resources

About