scholarly journals Deep Video Frame Interpolation Using Cyclic Frame Generation

2019 ◽  
Vol 33 ◽  
pp. 8794-8802 ◽  
Author(s):  
Yu-Lun Liu ◽  
Yi-Tung Liao ◽  
Yen-Yu Lin ◽  
Yung-Yu Chuang
Keyword(s):  
State Of The Art ◽  
Experimental Results ◽  
Training Data ◽  
Video Frame ◽  
High Quality ◽  
Edge Information ◽  
Frame Interpolation ◽  
Source Codes ◽  
Qualitative And Quantitative ◽  
Loss Term

Video frame interpolation algorithms predict intermediate frames to produce videos with higher frame rates and smooth view transitions given two consecutive frames as inputs. We propose that: synthesized frames are more reliable if they can be used to reconstruct the input frames with high quality. Based on this idea, we introduce a new loss term, the cycle consistency loss. The cycle consistency loss can better utilize the training data to not only enhance the interpolation results, but also maintain the performance better with less training data. It can be integrated into any frame interpolation network and trained in an end-to-end manner. In addition to the cycle consistency loss, we propose two extensions: motion linearity loss and edge-guided training. The motion linearity loss approximates the motion between two input frames to be linear and regularizes the training. By applying edge-guided training, we further improve results by integrating edge information into training. Both qualitative and quantitative experiments demonstrate that our model outperforms the state-of-the-art methods. The source codes of the proposed method and more experimental results will be available at https://github.com/alex04072000/CyclicGen.

scholarly journals ERNIE 2.0: A Continual Pre-Training Framework for Language Understanding

2020 ◽  
Vol 34 (05) ◽  
pp. 8968-8975 ◽  
Author(s):  
Yu Sun ◽  
Shuohuan Wang ◽  
Yukun Li ◽  
Shikun Feng ◽  
Hao Tian ◽  
...  
Keyword(s):  
Semantic Information ◽  
State Of The Art ◽  
Experimental Results ◽  
Training Data ◽  
Language Understanding ◽  
Named Entities ◽  
Source Codes ◽  
Task Learning ◽  
Discourse Relations

Recently pre-trained models have achieved state-of-the-art results in various language understanding tasks. Current pre-training procedures usually focus on training the model with several simple tasks to grasp the co-occurrence of words or sentences. However, besides co-occurring information, there exists other valuable lexical, syntactic and semantic information in training corpora, such as named entities, semantic closeness and discourse relations. In order to extract the lexical, syntactic and semantic information from training corpora, we propose a continual pre-training framework named ERNIE 2.0 which incrementally builds pre-training tasks and then learn pre-trained models on these constructed tasks via continual multi-task learning. Based on this framework, we construct several tasks and train the ERNIE 2.0 model to capture lexical, syntactic and semantic aspects of information in the training data. Experimental results demonstrate that ERNIE 2.0 model outperforms BERT and XLNet on 16 tasks including English tasks on GLUE benchmarks and several similar tasks in Chinese. The source codes and pre-trained models have been released at https://github.com/PaddlePaddle/ERNIE.

scholarly journals Video Frame Interpolation via Deformable Separable Convolution

2020 ◽  
Vol 34 (07) ◽  
pp. 10607-10614 ◽  
Author(s):  
Xianhang Cheng ◽  
Zhenzhong Chen
Keyword(s):  
State Of The Art ◽  
Video Frame ◽  
Kernel Size ◽  
Frame Interpolation ◽  
Interpolation Methods ◽  
Video Frames ◽  
Convolution Process ◽  
Strong Performance ◽  
Existing Frames ◽  
Better Than

Learning to synthesize non-existing frames from the original consecutive video frames is a challenging task. Recent kernel-based interpolation methods predict pixels with a single convolution process to replace the dependency of optical flow. However, when scene motion is larger than the pre-defined kernel size, these methods yield poor results even though they take thousands of neighboring pixels into account. To solve this problem in this paper, we propose to use deformable separable convolution (DSepConv) to adaptively estimate kernels, offsets and masks to allow the network to obtain information with much fewer but more relevant pixels. In addition, we show that the kernel-based methods and conventional flow-based methods are specific instances of the proposed DSepConv. Experimental results demonstrate that our method significantly outperforms the other kernel-based interpolation methods and shows strong performance on par or even better than the state-of-the-art algorithms both qualitatively and quantitatively.

scholarly journals AI-Sketcher : A Deep Generative Model for Producing High-Quality Sketches

2019 ◽  
Vol 33 ◽  
pp. 2564-2571 ◽  
Author(s):  
Nan Cao ◽  
Xin Yan ◽  
Yang Shi ◽  
Chaoran Chen
Keyword(s):  
Artificial Intelligence ◽  
Large Scale ◽  
State Of The Art ◽  
Positional Information ◽  
Generative Model ◽  
Training Data ◽  
Creative Design ◽  
High Quality ◽  
User Input ◽  
Variational Autoencoder

Sketch drawings play an important role in assisting humans in communication and creative design since ancient period. This situation has motivated the development of artificial intelligence (AI) techniques for automatically generating sketches based on user input. Sketch-RNN, a sequence-to-sequence variational autoencoder (VAE) model, was developed for this purpose and known as a state-of-the-art technique. However, it suffers from limitations, including the generation of lowquality results and its incapability to support multi-class generations. To address these issues, we introduced AI-Sketcher, a deep generative model for generating high-quality multiclass sketches. Our model improves drawing quality by employing a CNN-based autoencoder to capture the positional information of each stroke at the pixel level. It also introduces an influence layer to more precisely guide the generation of each stroke by directly referring to the training data. To support multi-class sketch generation, we provided a conditional vector that can help differentiate sketches under various classes. The proposed technique was evaluated based on two large-scale sketch datasets, and results demonstrated its power in generating high-quality sketches.

scholarly journals A Fast 4K Video Frame Interpolation Using a Multi-Scale Optical Flow Reconstruction Network

Symmetry ◽  
2019 ◽  
Vol 11 (10) ◽  
pp. 1251 ◽  
Author(s):  
Ahn ◽  
Jeong ◽  
Kim ◽  
Kwon ◽  
Yoo
Keyword(s):  
High Resolution ◽  
Optical Flow ◽  
State Of The Art ◽  
Interpolation Method ◽  
Video Frame ◽  
Frame Interpolation ◽  
Multi Scale ◽  
Reconstruction Scheme ◽  
Flow Reconstruction

Recently, video frame interpolation research developed with a convolutional neural network has shown remarkable results. However, these methods demand huge amounts of memory and run time for high-resolution videos, and are unable to process a 4K frame in a single pass. In this paper, we propose a fast 4K video frame interpolation method, based upon a multi-scale optical flow reconstruction scheme. The proposed method predicts low resolution bi-directional optical flow, and reconstructs it into high resolution. We also proposed consistency and multi-scale smoothness loss to enhance the quality of the predicted optical flow. Furthermore, we use adversarial loss to make the interpolated frame more seamless and natural. We demonstrated that the proposed method outperforms the existing state-of-the-art methods in quantitative evaluation, while it runs up to 4.39× faster than those methods for 4K videos.

Language-Independent Type Inference of the Instances from Multilingual Wikipedia

2019 ◽  
Vol 15 (2) ◽  
pp. 22-46 ◽  
Author(s):  
Tianxing Wu ◽  
Guilin Qi ◽  
Bin Luo ◽  
Lei Zhang ◽  
Haofen Wang
Keyword(s):  
Knowledge Base ◽  
State Of The Art ◽  
The State ◽  
Type Inference ◽  
Experimental Results ◽  
High Quality ◽  
New Approach ◽  
Semantic Associations ◽  
Quality Type ◽  
Type Information

Extracting knowledge from Wikipedia has attracted much attention in recent ten years. One of the most valuable kinds of knowledge is type information, which refers to the axioms stating that an instance is of a certain type. Current approaches for inferring the types of instances from Wikipedia mainly rely on some language-specific rules. Since these rules cannot catch the semantic associations between instances and classes (i.e. candidate types), it may lead to mistakes and omissions in the process of type inference. The authors propose a new approach leveraging attributes to perform language-independent type inference of the instances from Wikipedia. The proposed approach is applied to the whole English and Chinese Wikipedia, which results in the first version of MulType (Multilingual Type Information), a knowledge base describing the types of instances from multilingual Wikipedia. Experimental results show that not only the proposed approach outperforms the state-of-the-art comparison methods, but also MulType contains lots of new and high-quality type information.

scholarly journals Dialogue Generation: From Imitation Learning to Inverse Reinforcement Learning

2019 ◽  
Vol 33 ◽  
pp. 6722-6729 ◽  
Author(s):  
Ziming Li ◽  
Julia Kiseleva ◽  
Maarten De Rijke
Keyword(s):  
Reinforcement Learning ◽  
State Of The Art ◽  
The State ◽  
Experimental Results ◽  
Imitation Learning ◽  
Local Optimum ◽  
Inverse Reinforcement Learning ◽  
High Quality ◽  
Overall Performance

The performance of adversarial dialogue generation models relies on the quality of the reward signal produced by the discriminator. The reward signal from a poor discriminator can be very sparse and unstable, which may lead the generator to fall into a local optimum or to produce nonsense replies. To alleviate the first problem, we first extend a recently proposed adversarial dialogue generation method to an adversarial imitation learning solution. Then, in the framework of adversarial inverse reinforcement learning, we propose a new reward model for dialogue generation that can provide a more accurate and precise reward signal for generator training. We evaluate the performance of the resulting model with automatic metrics and human evaluations in two annotation settings. Our experimental results demonstrate that our model can generate more high-quality responses and achieve higher overall performance than the state-of-the-art.

scholarly journals MetaCoAG: Binning Metagenomic Contigs via Composition, Coverage and Assembly Graphs

2021 ◽  
Author(s):  
Vijini Mallawaarachchi ◽  
Yu Lin
Keyword(s):  
Microbial Communities ◽  
De Novo ◽  
State Of The Art ◽  
Genetic Material ◽  
Single Copy ◽  
Experimental Results ◽  
Marker Genes ◽  
High Quality ◽  
Second Best ◽  
Direct Use

ABSTRACTMetagenomics binning has allowed us to study and characterize various genetic material of different species and gain insights into microbial communities. While existing binning tools bin metagenomics de novo assemblies, they do not make use of the assembly graphs that produce such assemblies. Here we propose MetaCoAG, a tool that utilizes assembly graphs with the composition and coverage information to bin metagenomic contigs. MetaCoAG uses single-copy marker genes to estimate the number of initial bins, assigns contigs into bins iteratively and adjusts the number of bins dynamically throughout the binning process. Experimental results on simulated and real datasets demonstrate that MetaCoAG significantly outperforms state-of-the-art binning tools, producing more high-quality bins than the second-best tool, with an average median F1-score of 88.40%. To the best of our knowledge, MetaCoAG is the first stand-alone binning tool to make direct use of the assembly graph information. MetaCoAG is available at https://github.com/Vini2/MetaCoAG.

scholarly journals An Improved Fingerprinting Algorithm for Detection of Video Frame Duplication Forgery

2012 ◽  
Vol 4 (3) ◽  
pp. 20-32 ◽  
Author(s):  
Yongjian Hu ◽  
Chang-Tsun Li ◽  
Yufei Wang ◽  
Bei-bei Liu
Keyword(s):  
Computational Efficiency ◽  
State Of The Art ◽  
Experimental Results ◽  
Video Frame ◽  
Detection Accuracy ◽  
Forgery Detection ◽  
Detection Algorithms ◽  
Dct Coefficients ◽  
Duplication Detection ◽  
Frame Duplication

Frame duplication is a common way of digital video forgeries. State-of-the-art approaches of duplication detection usually suffer from heavy computational load. In this paper, the authors propose a new algorithm to detect duplicated frames based on video sub-sequence fingerprints. The fingerprints employed are extracted from the DCT coefficients of the temporally informative representative images (TIRIs) of the sub-sequences. Compared with other similar algorithms, this study focuses on improving fingerprints representing video sub-sequences and introducing a simple metric for the matching of video sub-sequences. Experimental results show that the proposed algorithm overall outperforms three related duplication forgery detection algorithms in terms of computational efficiency, detection accuracy and robustness against common video operations like compression and brightness change.

scholarly journals A Topic-Aware Reinforced Model for Weakly Supervised Stance Detection

2019 ◽  
Vol 33 ◽  
pp. 7249-7256
Author(s):  
Penghui Wei ◽  
Wenji Mao ◽  
Guandan Chen
Keyword(s):  
Reinforcement Learning ◽  
Opinion Mining ◽  
State Of The Art ◽  
Public Attitudes ◽  
Representation Learning ◽  
Experimental Results ◽  
Training Data ◽  
Policy Network ◽  
Proposed Model ◽  
Weakly Supervised

Analyzing public attitudes plays an important role in opinion mining systems. Stance detection aims to determine from a text whether its author is in favor of, against, or neutral towards a given target. One challenge of this task is that a text may not explicitly express an attitude towards the target, but existing approaches utilize target content alone to build models. Moreover, although weakly supervised approaches have been proposed to ease the burden of manually annotating largescale training data, such approaches are confronted with noisy labeling problem. To address the above two issues, in this paper, we propose a Topic-Aware Reinforced Model (TARM) for weakly supervised stance detection. Our model consists of two complementary components: (1) a detection network that incorporates target-related topic information into representation learning for identifying stance effectively; (2) a policy network that learns to eliminate noisy instances from auto-labeled data based on off-policy reinforcement learning. Two networks are alternately optimized to improve each other’s performances. Experimental results demonstrate that our proposed model TARM outperforms the state-of-the-art approaches.

Language-Independent Type Inference of the Instances from Multilingual Wikipedia

2022 ◽  
pp. 580-606
Author(s):  
Tianxing Wu ◽  
Guilin Qi ◽  
Bin Luo ◽  
Lei Zhang ◽  
Haofen Wang
Keyword(s):  
Knowledge Base ◽  
State Of The Art ◽  
The State ◽  
Type Inference ◽  
Experimental Results ◽  
High Quality ◽  
New Approach ◽  
Semantic Associations ◽  
Quality Type ◽  
Type Information

Extracting knowledge from Wikipedia has attracted much attention in recent ten years. One of the most valuable kinds of knowledge is type information, which refers to the axioms stating that an instance is of a certain type. Current approaches for inferring the types of instances from Wikipedia mainly rely on some language-specific rules. Since these rules cannot catch the semantic associations between instances and classes (i.e. candidate types), it may lead to mistakes and omissions in the process of type inference. The authors propose a new approach leveraging attributes to perform language-independent type inference of the instances from Wikipedia. The proposed approach is applied to the whole English and Chinese Wikipedia, which results in the first version of MulType (Multilingual Type Information), a knowledge base describing the types of instances from multilingual Wikipedia. Experimental results show that not only the proposed approach outperforms the state-of-the-art comparison methods, but also MulType contains lots of new and high-quality type information.

Sign in / Sign up

Export Citation Format

Share Document