scholarly journals Exploring, browsing and interacting with multi-level and multi-scale dynamics of knowledge

2021 ◽  
pp. 147387162110448
Author(s):  
Quentin Lobbé ◽  
Alexandre Delanoë ◽  
David Chavalarias
Keyword(s):  
Complex Systems ◽  
State Of The Art ◽  
Free Software ◽  
Discovery Process ◽  
Multi Scale ◽  
Computational Sciences ◽  
Knowledge Dynamics ◽  
Multi Level ◽  
Scale Properties ◽  
Ict Revolution

The ICT revolution has given birth to a world of digital traces. A wide number of knowledge-driven domains like science are daily fueled by unlimited flows of textual contents. In order to navigate across these growing constellations of words, interdisciplinary innovations are emerging at the crossroad between social and computational sciences. In particular, complex systems approaches make it now possible to reconstruct multi-level and multi-scale dynamics of knowledge by means of inheritance networks of elements of knowledge called phylomemies. In this article, we will introduce an endogenous way to visualize the multi-level and multi-scale properties of phylomemies. The resulting system will enrich a state-of-the-art tree like representation with the possibility to browse through the evolution of a corpus of documents at different level of observation, to interact with various scales of description, to reconstruct a hierarchical clustering of elements of knowledge and to navigate across complex semantic lineages. We will then formalize a generic macro-to-micro methodology of exploration and implement our system as a free software called the Memiescape. Our system will be illustrated by three use cases that will respectively reconstruct the scientific landscape of the top cited publications of the French CNRS, the evolution of the state of the art of knowledge dynamics visualization and the ongoing discovery process of Covid-19 vaccines.

scholarly journals App Download Forecasting: An Evolutionary Hierarchical Competition Approach

2017 ◽  
Author(s):  
Yingzi Wang ◽  
Nicholas Jing Yuan ◽  
Yu Sun ◽  
Chuan Qin ◽  
Xing Xie
Keyword(s):  
Time Series ◽  
Future Development ◽  
Real World ◽  
State Of The Art ◽  
Time Series Forecasting ◽  
Comprehensive Understanding ◽  
Competition Analysis ◽  
Multi Scale ◽  
Multi Level ◽  
Product Sales

Product sales forecasting enables comprehensive understanding of products' future development, making it of particular interest for companies to improve their business, for investors to measure the values of firms, and for users to capture the trends of a market. Recent studies show that the complex competition interactions among products directly influence products' future development. However, most existing approaches fail to model the evolutionary competition among products and lack the capability to organically reflect multi-level competition analysis in sales forecasting. To address these problems, we propose the Evolutionary Hierarchical Competition Model (EHCM), which effectively considers the time-evolving multi-level competition among products. The EHCM model systematically integrates hierarchical competition analysis with multi-scale time series forecasting. Extensive experiments using a real-world app download dataset show that EHCM outperforms state-of-the-art methods in various forecasting granularities.

scholarly journals Rethinking the Bottom-Up Framework for Query-Based Video Localization

2020 ◽  
Vol 34 (07) ◽  
pp. 10551-10558 ◽  
Author(s):  
Long Chen ◽  
Chujie Lu ◽  
Siliang Tang ◽  
Jun Xiao ◽  
Dong Zhang ◽  
...  
Keyword(s):  
State Of The Art ◽  
Ground Truth ◽  
Video Frame ◽  
Top Down ◽  
Bottom Up ◽  
Multi Scale ◽  
Feature Pyramid ◽  
Multi Level ◽  
Classification And Regression ◽  
Model Graph

In this paper, we focus on the task query-based video localization, i.e., localizing a query in a long and untrimmed video. The prevailing solutions for this problem can be grouped into two categories: i) Top-down approach: It pre-cuts the video into a set of moment candidates, then it does classification and regression for each candidate; ii) Bottom-up approach: It injects the whole query content into each video frame, then it predicts the probabilities of each frame as a ground truth segment boundary (i.e., start or end). Both two frameworks have respective shortcomings: the top-down models suffer from heavy computations and they are sensitive to the heuristic rules, while the performance of bottom-up models is behind the performance of top-down counterpart thus far. However, we argue that the performance of bottom-up framework is severely underestimated by current unreasonable designs, including both the backbone and head network. To this end, we design a novel bottom-up model: Graph-FPN with Dense Predictions (GDP). For the backbone, GDP firstly generates a frame feature pyramid to capture multi-level semantics, then it utilizes graph convolution to encode the plentiful scene relationships, which incidentally mitigates the semantic gaps in the multi-scale feature pyramid. For the head network, GDP regards all frames falling in the ground truth segment as the foreground, and each foreground frame regresses the unique distances from its location to bi-directional boundaries. Extensive experiments on two challenging query-based video localization tasks (natural language video localization and video relocalization), involving four challenging benchmarks (TACoS, Charades-STA, ActivityNet Captions, and Activity-VRL), have shown that GDP surpasses the state-of-the-art top-down models.

scholarly journals Adaptive Feature Pyramid Network to Predict Crisp Boundaries via NMS Layer and ODS F-Measure Loss Function

Information ◽  
2022 ◽  
Vol 13 (1) ◽  
pp. 32
Author(s):  
Gang Sun ◽  
Hancheng Yu ◽  
Xiangtao Jiang ◽  
Mingkui Feng
Keyword(s):  
Edge Detection ◽  
Loss Function ◽  
State Of The Art ◽  
Cross Entropy ◽  
Post Processing ◽  
Multi Scale ◽  
Feature Pyramid ◽  
Multi Level ◽  
Different Levels ◽  
F Measure

Edge detection is one of the fundamental computer vision tasks. Recent methods for edge detection based on a convolutional neural network (CNN) typically employ the weighted cross-entropy loss. Their predicted results being thick and needing post-processing before calculating the optimal dataset scale (ODS) F-measure for evaluation. To achieve end-to-end training, we propose a non-maximum suppression layer (NMS) to obtain sharp boundaries without the need for post-processing. The ODS F-measure can be calculated based on these sharp boundaries. So, the ODS F-measure loss function is proposed to train the network. Besides, we propose an adaptive multi-level feature pyramid network (AFPN) to better fuse different levels of features. Furthermore, to enrich multi-scale features learned by AFPN, we introduce a pyramid context module (PCM) that includes dilated convolution to extract multi-scale features. Experimental results indicate that the proposed AFPN achieves state-of-the-art performance on the BSDS500 dataset (ODS F-score of 0.837) and the NYUDv2 dataset (ODS F-score of 0.780).

scholarly journals M2Det: A Single-Shot Object Detector Based on Multi-Level Feature Pyramid Network

2019 ◽  
Vol 33 ◽  
pp. 9259-9266 ◽  
Author(s):  
Qijie Zhao ◽  
Tao Sheng ◽  
Yongtao Wang ◽  
Zhi Tang ◽  
Ying Chen ◽  
...  
Keyword(s):  
Feature Fusion ◽  
State Of The Art ◽  
Single Shot ◽  
Multi Scale ◽  
One Stage ◽  
Single Scale ◽  
Feature Pyramid ◽  
Multi Level ◽  
Multiple Levels ◽  
Inference Strategy

Feature pyramids are widely exploited by both the state-of-the-art one-stage object detectors (e.g., DSSD, RetinaNet, RefineDet) and the two-stage object detectors (e.g., Mask RCNN, DetNet) to alleviate the problem arising from scale variation across object instances. Although these object detectors with feature pyramids achieve encouraging results, they have some limitations due to that they only simply construct the feature pyramid according to the inherent multiscale, pyramidal architecture of the backbones which are originally designed for object classification task. Newly, in this work, we present Multi-Level Feature Pyramid Network (MLFPN) to construct more effective feature pyramids for detecting objects of different scales. First, we fuse multi-level features (i.e. multiple layers) extracted by backbone as the base feature. Second, we feed the base feature into a block of alternating joint Thinned U-shape Modules and Feature Fusion Modules and exploit the decoder layers of each Ushape module as the features for detecting objects. Finally, we gather up the decoder layers with equivalent scales (sizes) to construct a feature pyramid for object detection, in which every feature map consists of the layers (features) from multiple levels. To evaluate the effectiveness of the proposed MLFPN, we design and train a powerful end-to-end one-stage object detector we call M2Det by integrating it into the architecture of SSD, and achieve better detection performance than state-of-the-art one-stage detectors. Specifically, on MSCOCO benchmark, M2Det achieves AP of 41.0 at speed of 11.8 FPS with single-scale inference strategy and AP of 44.2 with multi-scale inference strategy, which are the new stateof-the-art results among one-stage detectors. The code will be made available on https://github.com/qijiezhao/M2Det.

scholarly journals Multi-scale methods for reconstructing collective shapes of digital diasporas

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Quentin Lobbé
Keyword(s):  
Daily Activities ◽  
Historical Events ◽  
Multi Scale ◽  
Reconstruction Methods ◽  
Digital Contents ◽  
History Of ◽  
Computational Sciences ◽  
Natural Result ◽  
Ict Revolution ◽  
The Way

AbstractThe ICT revolution has impacted the way diasporic groups and individuals communicate and interact with one another. Diasporas are now fueled by unlimited flows of digital contents generated by daily activities or sudden historical events. As a natural result, the science of migration has evolved just as much as its own subject of research. Thus, dedicated branches of research like digital diasporas emerge at the crossroad between fields of social and computational sciences. Thereupon, new types of multi-scale reconstruction methods are developed to investigate the collective shapes of digital diasporas. They allow the researchers to focus on individual interactions before visualizing their global structures and dynamics. In this paper, we present three different multi-scale reconstruction methods applied to reveal the scientific landscape of digital diasporas and to explore the history of an extinct online collective of Moroccan migrants.

Multi-Scale Compromise and Multi-Level Correlation in Complex Systems

2005 ◽  
Vol 83 (6) ◽  
pp. 574-582 ◽  
Author(s):  
J. Li ◽  
W. Ge ◽  
J. Zhang ◽  
M. Kwauk
Keyword(s):  
Complex Systems ◽  
Multi Scale ◽  
Multi Level

scholarly journals Context-aware Cross-level Fusion Network for Camouflaged Object Detection

2021 ◽  
Author(s):  
Yujia Sun ◽  
Geng Chen ◽  
Tao Zhou ◽  
Yi Zhang ◽  
Nian Liu
Keyword(s):  
Object Detection ◽  
State Of The Art ◽  
Context Aware ◽  
Global Context ◽  
Feature Representations ◽  
Multi Scale ◽  
Benchmark Datasets ◽  
Multi Level ◽  
High Level ◽  
Level Fusion

Camouflaged object detection (COD) is a challenging task due to the low boundary contrast between the object and its surroundings. In addition, the appearance of camouflaged objects varies significantly, e.g., object size and shape, aggravating the difficulties of accurate COD. In this paper, we propose a novel Context-aware Cross-level Fusion Network (C2F-Net) to address the challenging COD task. Specifically, we propose an Attention-induced Cross-level Fusion Module (ACFM) to integrate the multi-level features with informative attention coefficients. The fused features are then fed to the proposed Dual-branch Global Context Module (DGCM), which yields multi-scale feature representations for exploiting rich global context information. In C2F-Net, the two modules are conducted on high-level features using a cascaded manner. Extensive experiments on three widely used benchmark datasets demonstrate that our C2F-Net is an effective COD model and outperforms state-of-the-art models remarkably. Our code is publicly available at: https://github.com/thograce/C2FNet.

scholarly journals MSDRN: Pansharpening of Multispectral Images via Multi-Scale Deep Residual Network

2021 ◽  
Vol 13 (6) ◽  
pp. 1200
Author(s):  
Wenqing Wang ◽  
Zhiqiang Zhou ◽  
Han Liu ◽  
Guo Xie
Keyword(s):  
High Frequency ◽  
State Of The Art ◽  
Multispectral Images ◽  
Residual Network ◽  
Visual Evaluation ◽  
Multi Scale ◽  
Residual Learning ◽  
Fused Image ◽  
Series Of Experiments ◽  
Multi Level

In order to acquire a high resolution multispectral (HRMS) image with the same spectral resolution as multispectral (MS) image and the same spatial resolution as panchromatic (PAN) image, pansharpening, a typical and hot image fusion topic, has been well researched. Various pansharpening methods that are based on convolutional neural networks (CNN) with different architectures have been introduced by prior works. However, different scale information of the source images is not considered by these methods, which may lead to the loss of high-frequency details in the fused image. This paper proposes a pansharpening method of MS images via multi-scale deep residual network (MSDRN). The proposed method constructs a multi-level network to make better use of the scale information of the source images. Moreover, residual learning is introduced into the network to further improve the ability of feature extraction and simplify the learning process. A series of experiments are conducted on the QuickBird and GeoEye-1 datasets. Experimental results demonstrate that the MSDRN achieves a superior or competitive fusion performance to the state-of-the-art methods in both visual evaluation and quantitative evaluation.

Sign in / Sign up

Export Citation Format

Share Document