CAS(ME)2: A Database of Spontaneous Macro-expressions and Micro-expressions

نویسندگان

  • Fangbing Qu
  • Sujing Wang
  • Wen-Jing Yan
  • Xiaolan Fu
چکیده

Micro-expressions are facial expressions that are characterized by short durations, involuntary generation and low intensity, and they are regarded as unique cues revealing one’s hidden emotions. Although methods for the recognition of general facial expressions have been intensively investigated, little progress has been made in the automatic recognition of micro-expressions. To further facilitate development in this field, we present a new facial expression database, CAS(ME), which includes 250 spontaneous macro-expression samples and 53 micro-expression samples. The CAS(ME) database offers both macro-expression and micro-expression samples collected from the same participants. The emotion labels in the current database are based on a combination of Action Units (AUs), self-reports of every facial movement and the emotion types of the emotion-evoking videos to improve the validity of the labeling. Baseline evaluation was also provided. This database may provide more valid and ecological expression samples for the development of automatic facial recognition systems.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A Main Directional Maximal Difference Analysis for Spotting Micro-expressions

Micro-expressions are facial expressions that have a short duration (generally less than 0.5 seconds), involuntary appearance and low intensity of movement. They are regarded as unique cues revealing the hidden emotions of an individual. Although methods for the spotting and recognition of general facial expressions have been investigated, little progress has been made in the automatic spotting...

متن کامل

A main directional maximal difference analysis for spotting facial movements from long-term videos

There is an increasing interests in micro-expression researches. Spotting micro-expressions in long-term videos is very important, not only for providing clues for lie detection, but also for reducing the labor required to collect micro-expression data. However, little progress has been made in spotting micro-expressions. In this paper, we propose a Main Directional Maximal Difference (MDMD) An...

متن کامل

Bio-functions of carvacrol-supplemented feeds on lipopolysaccharide-induced rainbow trout (Oncorhynchus mykiss Walbaum, 1792)

To investigate the effects of carvacrol supplementation in rainbow trout induced by lipopolysaccharide (LPS), relative gene expressions levels of some pro-inflammatory cytokines and apoptosis markers in kidney and liver were measured. Fish with a mean weight of 44.71±1.33 g were studied using four different treatments with three replicates each. Inflammation and apoptosis were performed using L...

متن کامل

Bio-functions of carvacrol-supplemented feeds on lipopolysaccharide-induced rainbow trout (Oncorhynchus mykiss Walbaum, 1792)

To investigate the effects of carvacrol supplementation diets in rainbow trout induced by LPS, we measured gene expressions relative to pro-inflammatory and apoptosis in kidney and liver. Fish, which that were studied by four different treatments with three replicates each, was 44.71±1.33 gr. All fish were infected with E. coli LPS (25 µg ml-1) expect control and only carvacrol containing diet ...

متن کامل

For micro-expression recognition: Database and suggestions

Micro-expression is gaining more attention in both the scientific field and the mass media. It represents genuine emotions that people try to conceal, thus making it a promising cue for lie detection. Since micro-expressions are considered almost imperceptible to naked eyes, researchers have sought to automatically detect and recognize these fleeting facial expressions to help people make use o...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2016