Sort by: Year Popularity Relevance
Alexandre Xavier Falcão, João Paulo Papa, Gustavo Henrique de Rosa - 2020
Machine learning techniques have been paramount throughout the last years, being applied in a wide range of tasks, such as classification, object recognition, person identification, image segmentation, among others. Nevertheless, conventional classification algorithms, e.g., Logistic Regression, Decision Trees, Bayesian classifiers, might lack co...
Ling Shao, David Crandall, Jianbing Shen, Xiankai Lu, Wenguan Wang - 2020
This work proposes a novel attentive graph neural network (AGNN) for zero-shot video object segmentation (ZVOS). The suggested AGNN recasts this task as a process of iterative information fusion over video graphs. Specifically, AGNN builds a fully connected graph to efficiently represent frames as nodes, and relations between arbitrary frame pair...
Jie Zhou, Cheng Niu, Yang Feng, Jinchao Zhang, Zongjia Li, Zekang Li - 2020
Audio-Visual Scene-Aware Dialog (AVSD) is a task to generate responses when chatting about a given video, which is organized as a track of the 8th Dialog System Technology Challenge (DSTC8). To solve the task, we propose a universal multimodal transformer and introduce the multi-task learning method to learn joint representations among different ...
Mohanasankar Sivaprakasam, Keerthi Ram, Balamurali Murugesan, Sriprabha Ramanarayanan - 2020
Several variants of Convolutional Neural Networks (CNN) have been developed for Magnetic Resonance (MR) image reconstruction. Among them, U-Net has shown to be the baseline architecture for MR image reconstruction. However, sub-sampling is performed by its pooling layers, causing information loss which in turn leads to blur and missing fine detai...
Liang Lin, Si Liu, Guanbin Li, Jie Wu - 2020
Temporally language grounding in untrimmed videos is a newly-raised task in video understanding. Most of the existing methods suffer from inferior efficiency, lacking interpretability, and deviating from the human perception mechanism. Inspired by human's coarse-to-fine decision-making paradigm, we formulate a novel Tree-Structured Policy based P...
Mihai Datcu, Bin Lei, Zongxu Pan, Corneliu Octavian Dumitru, Zhongling Huang - 2020
The classification of large-scale high-resolution SAR land cover images acquired by satellites is a challenging task, facing several difficulties such as semantic annotation with expertise, changing data characteristics due to varying imaging parameters or regional target area differences, and complex scattering mechanisms being different from op...
Irwin King, Michael R. Lyu, David Lo, Xin Xia, Jichuan Zeng, Cuiyun Gao - 2020
Previous studies showed that replying to a user review usually has a positive effect on the rating that is given by the user to the app. For example, Hassan et al. found that responding to a review increases the chances of a user updating their given rating by up to six times compared to not responding. To alleviate the labor burden in replying t...
Agoston E. Eiben, Ewelina Weglarz-Tomczak, Jakub M. Tomczak - 2020
Differential evolution (DE) is a well-known type of evolutionary algorithms (EA). Similarly to other EA variants it can suffer from small populations and loose diversity too quickly. This paper presents a new approach to mitigate this issue: We propose to generate new candidate solutions by utilizing reversible linear transformation applied to a ...
Pheng Ann Heng, Lequan Yu, Qi Dou, Quande Liu - 2020
Automated prostate segmentation in MRI is highly demanded for computer-assisted diagnosis. Recently, a variety of deep learning methods have achieved remarkable progress in this task, usually relying on large amounts of training data. Due to the nature of scarcity for medical images, it is important to effectively aggregate data from multiple sit...
Minlie Huang, Xiaoyan Zhu, Zhihao Zhao, Fei Huang, Jian Guan - 2020
Story generation, namely generating a reasonable story from a leading context, is an important but challenging task. In spite of the success in modeling fluency and local coherence, existing neural language generation models (e.g., GPT-2) still suffer from repetition, logic conflicts, and lack of long-range coherence in generated stories. We conj...