http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Deepfake Detection using Supervised Temporal Feature Extraction model and LSTM
Chunghwan Lee(이정환),Jaihoon Kim(김재훈),Kijung Yoon(윤기중) 한국방송·미디어공학회 2021 한국방송공학회 학술발표대회 논문집 Vol.2021 No.11
As deep learning technologies becoming developed, realistic fake videos synthesized by deep learning models called “Deepfake” videos became even more difficult to distinguish from original videos. As fake news or Deepfake blackmailing are causing confusion and serious problems, this paper suggests a novel model detecting Deepfake videos. We chose Residual Convolutional Neural Network (Resnet50) as an extraction model and Long Short-Term Memory (LSTM) which is a form of Recurrent Neural Network (RNN) as a classification model. We adopted cosine similarity with hinge loss to train our extraction model in embedding the features of Deepfake and original video. The result in this paper demonstrates that temporal features in the videos are essential for detecting Deepfake videos.
Jaihoon Kim(김재훈),Chunghwan Lee(이정환),Sangmin Kim(김상민),Jechang Jeong(정제창) 한국방송·미디어공학회 2020 한국방송공학회 학술발표대회 논문집 Vol.2020 No.11
With the advent of deep learning, a lot of attempts have been made in computer vision to substitute deep learning models for conventional algorithms. Among them, image classification, object detection, and image restoration have received a lot of attention from researchers. However, most of the contributions were refined in one of the fields only. We propose a new paradigm of model structure. End-to-end model which we will introduce classifies noise of an image and restores accordingly. Through this, the model enhances universality and efficiency. Our proposed model is an One-For-All model which classifies weather condition in an image and returns clean image accordingly. By separating weather conditions, restoration model became more compact as well as effective in reducing raindrops, snowflakes, or haze in an image which degrade the quality of the image.