Min Peng, Chongyang Wang, Tong Chen, Guangyuan Liu, Xiaolan Fu
Abstract
Facial micro-expression is a brief involuntary facial movement and can reveal the genuine emotion that people try to conceal. Traditional methods of spontaneous micro-expression recognition rely excessively on sophisticated hand-crafted feature design and the recognition rate is not high enough for its practical application. In this paper, we proposed a Dual Temporal Scale Convolutional Neural Network (DTSCNN) for spontaneous micro-expressions recognition. The DTSCNN is a two-stream network. Different of stream of DTSCNN is used to adapt to different frame rate of micro-expression video clips. Each stream of DSTCNN consists of independent shallow network for avoiding the overfitting problem. Meanwhile, we fed the networks with optical-flow sequences to ensure that the shallow networks can further acquire higher-level features. Experimental results on spontaneous micro-expression databases (CASME I/II) showed that our method can achieve a recognition rate almost 10% higher than what some state-of-the-art method can achieve.
This research output has an Altmetric Attention Score of 4. This is our high-level measure of the quality and quantity of online attention that it has received. This Attention Score, as well as the ranking and number of research outputs shown below, was calculated when the research output was last mentioned on 16 October 2017.
All research outputs
#7,293,043
of 23,003,906 outputs
Outputs from Frontiers in Psychology
#10,531
of 30,241 outputs
Outputs of similar age
#119,222
of 325,878 outputs
Outputs of similar age from Frontiers in Psychology
#298
of 599 outputs
Altmetric has tracked 23,003,906 research outputs across all sources so far. This one has received more attention than most of these and is in the 67th percentile.
So far Altmetric has tracked 30,241 research outputs from this source. They typically receive a lot more attention than average, with a mean Attention Score of 12.5. This one has gotten more attention than average, scoring higher than 64% of its peers.
Older research outputs will score higher simply because they've had more time to accumulate mentions. To account for age we can compare this Altmetric Attention Score to the 325,878 tracked outputs that were published within six weeks on either side of this one in any source. This one has gotten more attention than average, scoring higher than 62% of its contemporaries.
We're also able to compare this research output to 599 others from the same source and published within six weeks on either side of this one. This one is in the 49th percentile – i.e., 49% of its contemporaries scored the same or lower than it.
