Prediction of Image Preferences from Spontaneous Facial Expressions

Satō, Yoshiyuki; Horaguchi, Yuta; VANEL, Lorraine; Shioiri, Satoshi

doi:10.4036/iis.2022.a.02

Cited by 7 publications

(2 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These algorithms are constantly being improved, allowing deep reinforcement learning techniques to play an essential role in an increasing number of areas. Many excellent algorithms are still being proposed and applied in various fields [13]. Deep reinforcement learning is still developing rapidly, and there are still many challenges to be overcome, such as how to accelerate the training process more effectively, how to make the trained model more general, how to set a more accurate and reasonable reward function, and how to choose the current strategy according to the longer-term return.…”

Section: Related Workmentioning

confidence: 99%

Evolutionary Deep Learning for Sequential Data Processing in Music Education

Jing

2024

IJCAI

View full text Add to dashboard Cite

In response to the shortcomings of insufficient music structure, this article proposes a structured model based on motivational phrases and phrases. Starting from the composition structure of motivational phrases, deep learning techniques are used to learn composition. In the music generation model, a Scratch music generation model that can generate Pianoroll format music is constructed by using a generative adversarial network based on emotions and time structures. And use convolutional neural networks in the generator and discriminator to improve training speed. The effectiveness and practicality of the two algorithm models were verified through multiple comparative experiments and algorithm effectiveness experiments. This method achieves structural feature extraction of music by designing feature extractors at different music granularities. By designing feature expression functions at multi-scale music granularity, the music structure embedded in the music itself is incorporated into the reward function. Use forward backward propagation method to update the parameters of the model, and use dropout technique to improve the model's ability to resist overfitting. The test results show that the model has specific generalization ability, with an accuracy rate of 90%, and high recall and accuracy of the model.The experimental results show that this method can achieve better music generation results than the reward function method based on manual rules and before and after relationships. Solved the problem of lacking knowledge of music theory to propose rules, and compensated for the pain of insufficient utilization of music structure information in network models based on context. Povzetek: Študija uvaja evolucijsko globoko učenje za glasbeno izobraževanje, ki uporablja GAN za generiranje glasbe in CNN za izboljšanje hitrosti učenja.

show abstract

Section: Related Workmentioning

confidence: 99%

Evolutionary Deep Learning for Sequential Data Processing in Music Education

Jing

2024

IJCAI

View full text Add to dashboard Cite

show abstract

“…The internal architecture of the Convolutional Neural Network is designed based on the Inception V3 architecture [25]. This architecture is modified to have a factorized 3 × 3 convolutional filter for improved granularity of convergence and also has features like label smoothing and auxiliary classifiers to propagate the information obtained from the ensemble learners down the pipeline along the network.…”

Section: Modelling and Training The Convolutional Neural Networkmentioning

confidence: 99%

Facial Emotion Recognition Using Swarm Optimized Multi-Dimensional DeepNets with Losses Calculated by Cross Entropy Function

Arun¹,

Maheswaravenkatesh²,

Jayasankar³

2023

Computer Systems Science and Engineering

View full text Add to dashboard Cite

The human face forms a canvas wherein various non-verbal expressions are communicated. These expressional cues and verbal communication represent the accurate perception of the actual intent. In many cases, a person may present an outward expression that might differ from the genuine emotion or the feeling that the person experiences. Even when people try to hide these emotions, the real emotions that are internally felt might reflect as facial expressions in the form of micro expressions. These micro expressions cannot be masked and reflect the actual emotional state of a person under study. Such micro expressions are on display for a tiny time frame, making it difficult for a typical person to spot and recognize them. This necessitates a place for Machine Learning, where machines can be trained to look for these micro expressions and categorize them once they are on display. The study's primary purpose is to spot and correctly classify these micro expressions, which are very difficult for a casual observer to identify. This research improves upon the accuracy of the recognition by using a novel learning technique that not only captures and recognizes multimodal facial micro expressions but also has features for aligning, cropping, and superimposing these feature frames to produce highly accurate and consistent results. A modified variant of the deep learning architecture of Convolutional Neural Networks combined with the swarm-based optimality technique of the Artificial Bee Colony Algorithm is proposed to effectively get an accuracy of more than 85% in identifying and classifying these micro expressions in contrast to other algorithms that have relatively less accuracy. One of the main aspects of processing these expressions from video or live feeds is aligning the frames homographically and identifying these concise bursts of micro expressions, which significantly increases the accuracy of the outcomes. The proposed swarm-based technique handles this in the research to precisely align and crop the subsequent frames, resulting in much superior detection rates in identifying the micro expressions when on display.

show abstract