Combining active learning and local patch alignment for data-driven facial animation with fine-grained local detail

Zhang, Jian; Liao, Guihua; Li, Na

doi:10.1016/j.neucom.2019.05.102

Cited by 15 publications

(18 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Adanya media video animasi dalam pembelajaran dapat membantu guru dalam menyampaikan materi dan membantu siswa agar lebih paham materi yang disampaikan oleh guru (Imamah, 2012;Sanchez & Weber, 2019;Trianawati, 2019). Pemanfaatan media video animasi dalam pembelajaran dapat mempermudah pemahaman serta memperkuat ingatan siswayang dimana materi dalam video animasi mengaitkan kegiatan yang ada dikehidupan siswa seharihari (Lin & Li, 2018;Zhang, Liao, & Li, 2020). Selain itu, media video animasi sudah sesuai dengan konsep dan desain pembelajaran.…”

Section: Gambar 1 Video Animasi Yang Dikembangkanunclassified

Pengembangan Media Video Animasi IPA pada Pokok Bahasan Sistem Pernapasan Kelas V

Dewi

Negara

2021

j. edutech.

View full text Add to dashboard Cite

Penelitian ini dilatar belakangi oleh kurangnya pemanfaatan media sebagai sarana pendukung pembelajaran dimasa pandemi saat ini. Media yang digunakan masih menggunakan buku siswa sehingga siswa belum memahami materi secara optimal. Penelitian ini bertujuan untuk mengembangkan video animasi IPA pada materi Sistem Pernapasan untuk siswa kelas V. Penelitian ini menggunakan model Hannafin and Peck (Analysist, Design, Implementation & Development). Metode pengumpulan data penelitian ini menggunakan wawancara, observasi, dan kuesioner. Metode analisis data yang digunakan adalah analisis deskriptif kualitatif dan analisis deskriptif kuantitatif. Hasil penelitian ini menyimpulkan bahwa pada hasil uji ahli isi pembelajaran memperoleh skor 98,20% dengan kualifikasi sangat baik, hasil uji ahli desain pembelajaran memperoleh skor 100% dengan kualifikasi sangat baik, hasil uji ahli media pembelajaran memperoleh skor 98,6% dengan kualifikasi sangat baik, hasil uji coba perorangan memperoleh skor 95% dengan kualifikasi sangat baik, dan hasil uji coba kelompok kecil memperoleh skor 95% dengan kualifikasi sangat baik. Berdasarkan hasil analisis data uji produk oleh para ahli dan hasil uji coba siswa disimpulkan bahwa media video animasi hasil penelitian ini sangat baik sehingga layak digunakan dalam pembelajaran IPA di sekolah dasar. Implikasi dari penelitian ini yaitu secara empiris terbukti bahwa penggunaan media video animasi dapat meningkatkan hasil belajar dan motivasi belajar siswa.

show abstract

Section: Gambar 1 Video Animasi Yang Dikembangkanunclassified

Pengembangan Media Video Animasi IPA pada Pokok Bahasan Sistem Pernapasan Kelas V

Dewi

Negara

2021

j. edutech.

View full text Add to dashboard Cite

show abstract

“…In the second group, there are those that use modeling and/or 3D animations as input data. In Reference 16 is presented an automatic approach for obtaining correspondences of three‐dimensional points between the three‐dimensional modeling of a character used as input data and another that will be used as a destination, obtaining as a result an accuracy similar to that obtained if the correspondence mapping was carried out manually. In Reference 17 an active learning method based on the local linear reconstruction algorithm is proposed for the detection of the optimal positions of the features of the face, which uses as data of input three‐dimensional modeling of a face.…”

Section: Related Workmentioning

confidence: 99%

DeepHistory: A convolutional neural network for automatic animation of museum paintings

Ysique‐Neciosup

Mercado‐Chavez

Ugarte

2022

Computer Animation & Virtual

View full text Add to dashboard Cite

Deep learning models have shown that it is possible to train neural networks to dispense, to a lesser or greater extent, with the need for human intervention for the task of image animation, which helps to reduce not only the production time of these audiovisual pieces, but also presents benefits with respect to the economic investment they require to be made. However, these models suffer from two common problems: the animations they generate are of very low resolution and they require large amounts of training data to generate good results. To deal with these issues, this article introduces the architectural modification of a state-of-the-art image animation model integrated with a video super-resolution model to make the generated videos more visually pleasing to viewers. Although it is possible to train the animation models with higher resolution images, the time it would take to train them would be much longer, which does not necessarily benefit the quality of the animation, so it is more efficient to complement it with another model focused on improving the animation resolution of the generated video as we demonstrate in our results. We present the design and implementation of a convolutional neural network based on an state-of-art model focused on the image animation task, which is trained with a set of facial data from videos extracted from the YouTube platform. To determine which of all the modifications to the selected state-of-the-art model architecture is better, the results are compared with different metrics that evaluate the performance in image animation and video quality enhancement tasks. The results show that modifying the architecture of the model focused on the detection of characteristic points significantly helps to generate more anatomically and visually attractive videos. In addition, perceptual testing with users shows that using a super-resolution video model as a plugin helps generate more visually appealing videos.

show abstract

“…The findings of previous research stated that Realistic Mathematical Education (RME) is an approach to learning mathematics that can facilitate students learning mathematics (Faidah et al, 2019;Sulastri & Kusmanto, 2016). Other research findings also state that animation can attract students' attention, making it easier to learn (Hanif, 2020;Kühl, 2021;Zhang et al, 2020). It can be concluded that animation-assisted Realistic Mathematical Education can help students learn, especially in mathematics.…”

Section: Introductionmentioning

confidence: 99%

Online Learning Based on Realistic Mathematic Education (RME) Assisted Animation Media in Improving Student Learning Outcomes

Amir

Syamsuddin

Sulfansyah

2021

j. ilm. sekol. dasar

View full text Add to dashboard Cite

There are still many teachers who have difficulty determining appropriate learning methods and learning media for mathematics lessons. This has an impact on student learning outcomes are low. This study aims to analyze the effect of the Realistic Mathematical Education (RME) approach assisted by animation media on students' mathematics learning outcomes. This research is a quantitative research with a quasi-experimental research design with a non-equivalent control group design research design. This study involved 30 students as the research sample with a simple random sampling technique (Simple Random Sampling). This study uses data collection techniques, namely observation and written tests by giving five essay questions with different weights for each question. The data obtained were analyzed using the SPSS v.22 application by looking for the results of the normality test, homogeneity test, N-Gain test and finally the t-test (Independent Sample Test) to test the hypothesis. The results showed that there was a difference between the students' average scores by applying the Realistic Mathematical Education (RME) approach with the aid of animation media, obtaining an average score of 74.60 in the medium category. Based on the results of data analysis, there is a significant effect on mathematics learning outcomes which can be proven from the significance value at the output of the Independent Sample Test, namely 0.000 < 0.05, which means that H0 is rejected and Ha is accepted. It can be concluded that the Realistic Mathematical Education (RME) approach assisted by animation media can improve mathematics learning outcomes.

show abstract

Combining active learning and local patch alignment for data-driven facial animation with fine-grained local detail

Cited by 15 publications

References 26 publications

Pengembangan Media Video Animasi IPA pada Pokok Bahasan Sistem Pernapasan Kelas V

Pengembangan Media Video Animasi IPA pada Pokok Bahasan Sistem Pernapasan Kelas V

DeepHistory: A convolutional neural network for automatic animation of museum paintings

Online Learning Based on Realistic Mathematic Education (RME) Assisted Animation Media in Improving Student Learning Outcomes

Contact Info

Product

Resources

About