They adopt a sub-optimal uniform sampling point allocation, limiting the expressiveness of the learned LUTs since the (tri-)linear interpolation between uniform sampling points in the LUT transform might fail to model local non-linearities of the color transform.
As a widely studied task, video restoration aims to enhance the quality of the videos with multiple potential degradations, such as noises, blurs and compression artifacts.
2 code implementations • 20 Apr 2022 • Ren Yang, Radu Timofte, Meisong Zheng, Qunliang Xing, Minglang Qiao, Mai Xu, Lai Jiang, Huaida Liu, Ying Chen, Youcheng Ben, Xiao Zhou, Chen Fu, Pei Cheng, Gang Yu, Junyi Li, Renlong Wu, Zhilu Zhang, Wei Shang, Zhengyao Lv, Yunjin Chen, Mingcai Zhou, Dongwei Ren, Kai Zhang, WangMeng Zuo, Pavel Ostyakov, Vyal Dmitry, Shakarim Soltanayev, Chervontsev Sergey, Zhussip Magauiya, Xueyi Zou, Youliang Yan, Pablo Navarrete Michelini, Yunhua Lu, Diankai Zhang, Shaoli Liu, Si Gao, Biao Wu, Chengjian Zheng, Xiaofeng Zhang, Kaidi Lu, Ning Wang, Thuong Nguyen Canh, Thong Bach, Qing Wang, Xiaopeng Sun, Haoyu Ma, Shijie Zhao, Junlin Li, Liangbin Xie, Shuwei Shi, Yujiu Yang, Xintao Wang, Jinjin Gu, Chao Dong, Xiaodi Shi, Chunmei Nian, Dong Jiang, Jucai Lin, Zhihuai Xie, Mao Ye, Dengyan Luo, Liuhan Peng, Shengjie Chen, Qian Wang, Xin Liu, Boyang Liang, Hang Dong, Yuhao Huang, Kai Chen, Xingbei Guo, Yujing Sun, Huilei Wu, Pengxu Wei, Yulin Huang, Junying Chen, Ik Hyun Lee, Sunder Ali Khowaja, Jiseok Yoon
This challenge includes three tracks.
In this work, a Pyramid Frequency Network(PFN) with Spatial Attention Residual Refinement Module(SARRM) is proposed to deal with the weak robustness of existing deep-learning methods.
In the first component, we introduce a theoretical function-preserving transformation of recurrent neural networks (RNN) to the literature for capturing the hidden temporal patterns within the time-series data.
To ensure the quality of our benchmark and address the shortcomings in other existing datasets, we (1) reduce the false negatives in development and testing sets by pooling the results from multiple retrievers with human annotations, (2) and remove the semantically similar questions between training with development and testing sets.
The blockchain and artificial intelligence (AI) are innovative technologies to fulfil these two factors, by which the blockchain provides decentralised trading platforms for energy markets and the AI supports the optimal operational control of power systems.
The importance of the dynamics of the viewport pose, i. e., the location and the orientation of users' points of view, for virtual reality (VR) experiences calls for the development of VR viewport pose models.
For this purpose, we create a Chinese dataset namely DuQM which contains natural questions with linguistic perturbations to evaluate the robustness of question matching models.
In the context of high penetration of renewables and power electronics, the need to build dynamic models of power system components based on accessible measurement data has become urgent.
We demonstrate that the proposed approach outperforms state-of-the-art methods on two common synthetic-to-real semantic segmentation benchmarks.
no code implementations • 11 Oct 2021 • Xianghua Ye, Dazhou Guo, Chen-Kan Tseng, Jia Ge, Tsung-Min Hung, Ping-Ching Pai, Yanping Ren, Lu Zheng, Xinli Zhu, Ling Peng, Ying Chen, Xiaohua Chen, Chen-Yu Chou, Danni Chen, Jiaze Yu, Yuzhen Chen, Feiran Jiao, Yi Xin, Lingyun Huang, Guotong Xie, Jing Xiao, Le Lu, Senxiang Yan, Dakai Jin, Tsung-Ying Ho
252 institution-1 patients had a treatment planning-CT (pCT) and a pair of diagnostic FDG-PETCT; 354 patients from other 3 institutions had only pCT.
With the rapid development of Artificial Intelligence (AI), it is foreseeable that the accuracy and efficiency of future power system dynamic analysis will be greatly improved by the integration of dynamic simulators and AI.
Therefore, in order to systematically evaluate the factors for building trustworthy systems, we propose a novel and well-annotated sentiment analysis dataset to evaluate robustness and interpretability.
Considering the fact that students have different abilities to understand the knowledge imparted by teachers, a multi-granularity distillation mechanism is proposed for transferring more understandable knowledge for student networks.
Knowledge distillation pursues a diminutive yet well-behaved student network by harnessing the knowledge learned by a cumbersome teacher model.
We propose a deep switching state space model (DS$^3$M) for efficient inference and forecasting of nonlinear time series with irregularly switching among various regimes.
Next generation beyond 5G networks are expected to provide both Terabits per second data rate communication services and centimeter-level accuracy localization services in an efficient, seamless and cost-effective manner.
Knowledge distillation (KD) has recently emerged as an efficacious scheme for learning compact deep neural networks (DNNs).
Factors that influenced high performance of a well-designed integration of spectral learning and machine learning included: 1) use of eigenvectors corresponding to several of the largest eigenvalues of sample covariance matrix (spike eigenvectors) to choose input attributes in classification training, taking into account only the fundamental information of the raw images with less noise; 2) removal of irrelevant pixels based on mean-level spectral test to lower the challenges of memory capacity and enhance computational efficiency while maintaining superior classification accuracy; 3) adoption of state-of-the-art machine learning classification, gradient boosting and random forest.
This corpus is expected to promote the research of automatic simultaneous translation as well as the development of practical systems.
However, such a regularization technique lacks flexibility and coverage, since only importance scores towards a pre-defined list of features are adjusted, while more complex human knowledge such as feature interaction and pattern generalization can hardly be incorporated.
We develop a variational Bayesian (VB) approach for estimating large-scale dynamic network models in the network autoregression framework.
We propose an Exclusive Topic Modeling (ETM) for unsupervised text classification, which is able to 1) identify the field-specific keywords though less frequently appeared and 2) deliver well-structured topics with exclusive words.
Training a CNN to perform semantic segmentation requires a large amount of labeled data, where the production of such labeled data is both costly and labor intensive.
Neural trees aim at integrating deep neural networks and decision trees so as to bring the best of the two worlds, including representation learning from the former and faster inference from the latter.
Recently end-to-end scene text spotting has become a popular research topic due to its advantages of global optimization and high maintainability in real applications.
In this paper, we propose a novel unsupervised domain adaptation framework to address domain shift in the context of aerial semantic image segmentation.
Emotion-cause pair extraction (ECPE), which aims at simultaneously extracting emotion-cause pairs that express emotions and their corresponding causes in a document, plays a vital role in understanding natural languages.
Weakly supervised object detection (WSOD) aims to classify and locate objects with only image-level supervision.
By doing so, we effectively replace the handcrafted filter in the SISR pipeline with more lossy down-sampling filters specifically trained for each feature map, whilst also reducing the information loss of the overall SISR operation.
To deal with this problem, we propose a semantic Difficulty-awarE Active Learning (DEAL) network composed of two branches: the common segmentation branch and the semantic difficulty branch.
Moreover, RTL identifies a small set of word features, corresponding to 3% for Restaurant and 20% for Hotel, which boosts working efficiency by allowing managers to drill down into a much smaller set of important customer reviews.
When applying to one day ahead forecasting for the French daily electricity load curves, PPC outperform several state-of-the-art predictive methods in terms of forecasting accuracy, coverage rate and average length of the predictive bands.
Finally, the hierarchical feature learning module is designed to obtain a multi-scale features from the high to low-level convolutional layers, which are integrated to predict pixel-wise crack detection.
In VVC, the quad-tree plus multi-type tree (QTMT) structure of coding unit (CU) partition accounts for over 97% of the encoding time, due to the brute-force search for recursive rate-distortion (RD) optimization.
Moreover, in the inference phase, the depthwise convolution is folded into the conventional convolution, reducing the computation to be exactly equivalent to that of a convolutional layer without over-parameterization.
Considering the overfitting issue, we propose a new moving window-based algorithm using a validation set in the first stage to update the training data in both stages with two different moving window processes. Experiments were conducted at three wind farms, and the results demonstrate that the model with single input multiple output structure obtains better forecasting accuracy compared to existing models.
Existing CNN-based methods for pixel labeling heavily depend on multi-scale features to meet the requirements of both semantic comprehension and detail preservation.
In this paper, we propose an ensemble of convolutional neural networks (without a pooling layer) based on probability fusion for automated pavement crack detection and measurement.
To efficiently extract spatiotemporal features of video for action recognition, most state-of-the-art methods integrate 1D temporal convolution into a conventional 2D CNN backbone.
However, the binarization of weights and activations leads to feature maps of lower quality and lower capacity and thus a drop in accuracy compared to traditional networks.
In this paper, we integrate spiking convolutional neural network (SCNN) with temporal coding into the YOLOv2 architecture for real-time object detection.
We derive an explicit solution for deterministic market impact parameters in the Graewe and Horst (2017) portfolio liquidation model.
To solve this problem, the mixed gradient error, which is composed by MSE and a weighted mean gradient error, is proposed in this work and applied to a modified U-net network as the loss function.
This paper presents the sys- tem of our participation in the sentence-level subtask of the propaganda detection shared task.
Spiking neural network (SNN) is interesting both theoretically and practically because of its strong bio-inspiration nature and potentially outstanding energy efficiency.
The analysis uncovers the local mobility culture, embedded norms and values associated with acceptance of active travel modes in different communities.
In this paper, a multi-scale framework with local region based active contour and boundary shape similarity constraint is proposed for the segmentation of levator hiatus in ultrasound images.
Finally, we gather up the decoder layers with equivalent scales (sizes) to develop a feature pyramid for object detection, in which every feature map consists of the layers (features) from multiple levels.
Ranked #116 on Object Detection on COCO test-dev
We present a neural network-based joint approach for emotion classification and emotion cause detection, which attempts to capture mutual benefits across the two sub-tasks of emotion analysis.
Human generates responses relying on semantic and functional dependencies, including coreference relation, among dialogue elements and their context.
Ranked #6 on Conversational Response Selection on RRS