Extracting Variable-Depth Logical Document Hierarchy from Long Documents: Method, Evaluation, and ApplicationSpringer Science and Business Media LLC - Tập 37 - Trang 699-718 - 2022
Rong-Yu Cao, Yi-Xuan Cao, Gan-Bin Zhou, Ping Luo
In this paper, we study the problem of extracting variable-depth “logical document hierarchy” from long documents, namely organizing the recognized “physical document objects” into hierarchical structures. The discovery of logical document hierarchy is the vital step to support many downstream applications (e.g., passage-based retrieval and high-quality information extraction). However, long docum...... hiện toàn bộ
Reconnectable network with limited resourcesSpringer Science and Business Media LLC - Tập 6 - Trang 243-249 - 1991
Shi Weigeng
The reachability of a strongly connected network may be destroyed after link damage. Since many networks are directed or equivalent directed, connected by directed links with the potential for reversal. Therefore the reachability can be restored by reversing the direction of links. [1] has studied this matter under unlimited resources (transmitter and receiver) condition. In this paper the reconne...... hiện toàn bộ
Minimizing ADMs on WDM directed fiber treesSpringer Science and Business Media LLC - Tập 18 - Trang 725-731 - 2003
FengFeng Zhou, GuoLiang Chen, YinLong Xu, Jun Gu
This paper proposes a polynomial-time algorithm for Minimum WDM/SONET Add/Drop Multiplexer Problem (MADM) on WDM directed fiber trees whether or not wavelength converters are used. It runs in timeO(m2n), wheren andm are the number of nodes of the tree and the number of the requests respectively. Incorporating T. Erlebachet al.’s work into the proposed algorithm, it also reaches the lower bound of ...... hiện toàn bộ
Temporally Consistent Depth Map Prediction Using Deep Convolutional Neural Network and Spatial-Temporal Conditional Random FieldSpringer Science and Business Media LLC - Tập 32 - Trang 443-456 - 2017
Xu-Ran Zhao, Xun Wang, Qi-Chao Chen
Deep convolutional neural networks (DCNNs) based methods recently keep setting new records on the tasks of predicting depth maps from monocular images. When dealing with video-based applications such as 2D (2-dimensional) to 3D (3-dimensional) video conversion, however, these approaches tend to produce temporally inconsistent depth maps, since their CNN models are optimized over single frames. In ...... hiện toàn bộ
Single Image Super-Resolution via Dynamic Lightweight Database with Local-Feature Based InterpolationSpringer Science and Business Media LLC - Tập 34 - Trang 537-549 - 2019
Na Ding, Ye-Peng Liu, Lin-Wei Fan, Cai-Ming Zhang
Single image super-resolution is devoted to generating a high-resolution image from a low-resolution one, which has been a research hotspot for its significant applications. A novel method that is totally based on the single input image itself is proposed in this paper. Firstly, a local-feature based interpolation method where both edge pixel property and location information are taken into consid...... hiện toàn bộ
Effective and Efficient Multi-Facet Web Image AnnotationSpringer Science and Business Media LLC - Tập 27 - Trang 541-553 - 2012
Jia Chen, Yi-He Zhu, Hao-Fen Wang, Wei Jin, Yong Yu
The vast amount of images available on the Web request for an effective and efficient search service to help users find relevant images. The prevalent way is to provide a keyword interface for users to submit queries. However, the amount of images without any tags or annotations are beyond the reach of manual efforts. To overcome this, automatic image annotation techniques emerge, which are genera...... hiện toàn bộ
An Intra-Server Interconnect Fabric for Heterogeneous ComputingSpringer Science and Business Media LLC - Tập 29 - Trang 976-988 - 2014
Zheng Cao, Xiao-Li Liu, Qiang Li, Xiao-Bing Liu, Zhan Wang, Xue-Jun An
With the increasing diversity of application needs and computing units, the server with heterogeneous processors is more and more widespread. However, conventional SMP/ccNUMA server architecture introduces communication bottleneck between heterogeneous processors and only uses heterogeneous processors as coprocessors, which limits the efficiency and flexibility of using heterogeneous processors. T...... hiện toàn bộ
Improvement of Machine Translation Evaluation by Simple Linguistically Motivated FeaturesSpringer Science and Business Media LLC - Tập 26 - Trang 57-67 - 2011
Mu-Yun Yang, Shu-Qi Sun, Jun-Guo Zhu, Sheng Li, Tie-Jun Zhao, Xiao-Ning Zhu
Adopting the regression SVM framework, this paper proposes a linguistically motivated feature engineering strategy to develop an MT evaluation metric with a better correlation with human assessments. In contrast to current practices of “greedy” combination of all available features, six features are suggested according to the human intuition for translation quality. Then the contribution of lingui...... hiện toàn bộ