scholarly journals Dynamic Graph Representation for Occlusion Handling in Biometrics

2020 ◽  
Vol 34 (07) ◽  
pp. 11940-11947
Author(s):  
Min Ren ◽  
Yunlong Wang ◽  
Zhenan Sun ◽  
Tieniu Tan
Keyword(s):  
Graphical Models ◽  
Graph Matching ◽  
Input Image ◽  
Graph Representation ◽  
Dynamic Graph ◽  
Unified Framework ◽  
Graph Representations ◽  
Novel Strategy ◽  
Biometrics Recognition ◽  
Reasonable Inference

The generalization ability of Convolutional neural networks (CNNs) for biometrics drops greatly due to the adverse effects of various occlusions. To this end, we propose a novel unified framework integrated the merits of both CNNs and graphical models to learn dynamic graph representations for occlusion problems in biometrics, called Dynamic Graph Representation (DGR). Convolutional features onto certain regions are re-crafted by a graph generator to establish the connections among the spatial parts of biometrics and build Feature Graphs based on these node representations. Each node of Feature Graphs corresponds to a specific part of the input image and the edges express the spatial relationships between parts. By analyzing the similarities between the nodes, the framework is able to adaptively remove the nodes representing the occluded parts. During dynamic graph matching, we propose a novel strategy to measure the distances of both nodes and adjacent matrixes. In this way, the proposed method is more convincing than CNNs-based methods because the dynamic graph method implies a more illustrative and reasonable inference of the biometrics decision. Experiments conducted on iris and face demonstrate the superiority of the proposed framework, which boosts the accuracy of occluded biometrics recognition by a large margin comparing with baseline methods.

scholarly journals LineageOT is a unified framework for lineage tracing and trajectory inference

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Aden Forrow ◽  
Geoffrey Schiebinger
Keyword(s):  
Graphical Models ◽  
Optimal Transport ◽  
Developmental Trajectories ◽  
Lineage Tracing ◽  
Developmental Pathways ◽  
State Transitions ◽  
Unified Framework ◽  
Measured Time ◽  
Mathematical Problems ◽  
Time Courses

AbstractUnderstanding the genetic and epigenetic programs that control differentiation during development is a fundamental challenge, with broad impacts across biology and medicine. Measurement technologies like single-cell RNA-sequencing and CRISPR-based lineage tracing have opened new windows on these processes, through computational trajectory inference and lineage reconstruction. While these two mathematical problems are deeply related, methods for trajectory inference are not typically designed to leverage information from lineage tracing and vice versa. Here, we present LineageOT, a unified framework for lineage tracing and trajectory inference. Specifically, we leverage mathematical tools from graphical models and optimal transport to reconstruct developmental trajectories from time courses with snapshots of both cell states and lineages. We find that lineage data helps disentangle complex state transitions with increased accuracy using fewer measured time points. Moreover, integrating lineage tracing with trajectory inference in this way could enable accurate reconstruction of developmental pathways that are impossible to recover with state-based methods alone.

A New Technique Based on Loops to Investigate Displacement Isomorphism in Planetary Gear Trains

2002 ◽  
Vol 124 (4) ◽  
pp. 662-675 ◽  
Author(s):  
V. V. N. R. Prasad Raju Pathapati ◽  
A. C. Rao
Keyword(s):  
Graph Isomorphism ◽  
Planetary Gear ◽  
Degree Of Freedom ◽  
Gear Train ◽  
Graph Representation ◽  
Kinematic Structure ◽  
Graph Representations ◽  
Planetary Gear Trains ◽  
Gear Trains ◽  
A New Technique

The most important step in the structural synthesis of planetary gear trains (PGTs) requires the identification of isomorphism (rotational as well as displacement) between the graphs which represent the kinematic structure of planetary gear train. Previously used methods for identifying graph isomorphism yielded incorrect results. Literature review in this area shows there is inconsistency in results from six link, one degree-of-freedom onwards. The purpose of this paper is to present an efficient methodology through the use of Loop concept and Hamming number concept to detect displacement and rotational isomorphism in PGTs in an unambiguous way. New invariants for rotational graphs and displacement graphs called geared chain hamming strings and geared chain loop hamming strings are developed respectively to identify rotational and displacement isomorphism. This paper also presents a procedure to redraw conventional graph representation that not only clarifies the kinematic structure of a PGT but also averts the problem of pseudo isomorphism. Finally a thorough analysis of existing methods is carried out using the proposed technique and the results in the category of six links one degree-of-freedom are established and an Atlas comprises of graph representations in conventional form as well as in new form is presented.

scholarly journals COLLEGE STUDENT’S ERROR ANALYSIS BASED ON THEIR MATHEMATICAL CONNECTIONS ON GRAPH REPRESENTATION

2019 ◽  
Vol 4 (1) ◽  
pp. 18
Author(s):  
I ketut Suastika ◽  
Vivi Suwanti
Keyword(s):  
Graph Theory ◽  
College Student ◽  
Real Life ◽  
Graph Representation ◽  
High Ability ◽  
Pilot Studies ◽  
Graph Representations ◽  
Mathematical Connections ◽  
Life Problems ◽  
Basic Concepts

This study is investigates the college student’s errors on their graph representations making based on the mathematical connections indicators. Pilot studies were conducted with 4 college students of middle to high ability in Graph Theory class. Data analyze revealed that top 3 subject’s errors are 1) Finding the relations of a representations to it’s concepts and procedures, 2) Applying mathematics in other sciences or real life problems, and 3) Finding relations among procedures of the equivalent representations. Their lack of graph concepts understanding and it’s connections plays the major role in their errors. They failed at recognizing and choosing the suitable properties of graph which able to detect the error of their graph representation. So, in order to decrease college student errors in graph representations, we need to strengthen their basic concepts and its connections.

A practical succinct dynamic graph representation

2021 ◽  
pp. 104862
Author(s):  
Miguel E. Coimbra ◽  
Joana Hrotkó ◽  
Alexandre P. Francisco ◽  
Luís M.S. Russo ◽  
Guillermo de Bernardo ◽  
...  
Keyword(s):  
Graph Representation ◽  
Dynamic Graph

Multi-modal transportation recommendation with unified route representation learning

2020 ◽  
Vol 14 (3) ◽  
pp. 342-350
Author(s):  
Hao Liu ◽  
Jindong Han ◽  
Yanjie Fu ◽  
Jingbo Zhou ◽  
Xinjiang Lu ◽  
...  
Keyword(s):  
Large Scale ◽  
Transportation Networks ◽  
Representation Learning ◽  
Transportation Systems ◽  
Graph Representation ◽  
Dynamic Graph ◽  
Arbitrary Length ◽  
Task Learning ◽  
Semantic Coherence ◽  
Spatio Temporal

Multi-modal transportation recommendation aims to provide the most appropriate travel route with various transportation modes according to certain criteria. After analyzing large-scale navigation data, we find that route representations exhibit two patterns: spatio-temporal autocorrelations within transportation networks and the semantic coherence of route sequences. However, there are few studies that consider both patterns when developing multi-modal transportation systems. To this end, in this paper, we study multi-modal transportation recommendation with unified route representation learning by exploiting both spatio-temporal dependencies in transportation networks and the semantic coherence of historical routes. Specifically, we propose to unify both dynamic graph representation learning and hierarchical multi-task learning for multi-modal transportation recommendations. Along this line, we first transform the multi-modal transportation network into time-dependent multi-view transportation graphs and propose a spatiotemporal graph neural network module to capture the spatial and temporal autocorrelation. Then, we introduce a coherent-aware attentive route representation learning module to project arbitrary-length routes into fixed-length representation vectors, with explicit modeling of route coherence from historical routes. Moreover, we develop a hierarchical multi-task learning module to differentiate route representations for different transport modes, and this is guided by the final recommendation feedback as well as multiple auxiliary tasks equipped in different network layers. Extensive experimental results on two large-scale real-world datasets demonstrate the performance of the proposed system outperforms eight baselines.

Recent Advances in Graph Matching

1997 ◽  
Vol 11 (01) ◽  
pp. 169-203 ◽  
Author(s):  
H. Bunke ◽  
B. T. Messmer
Keyword(s):  
Decision Tree ◽  
Graph Matching ◽  
Extreme Case ◽  
Input Image ◽  
Computational Effort ◽  
Compact Representation ◽  
Subgraph Isomorphism ◽  
Input Graph ◽  
Matching Problem ◽  
Tree Traversal

A powerful and universal data structure with applications invarious subfields of science and engineering is graphs. In computer vision and image analysis, graphs are often used for the representation of structured objects. For example, if the problem is to recognize instances of known objects in an image, then often models, or prototypes, of the known objects are represented by means of graphs and stored in a database. The unknown objects in the input image are extracted by means of suitable preprocessing and segmentation algorithms, and represented by graphs that are analogous to the model graphs. Thus, the problem of object recognition is transformed into a graph matching problem. In this paper, it is assumed that there is an input graph that is given on-line, and a number of model, or prototype, graphs that are known a priori. We present a new approach to subgraph isomorphism detection which is based on a compact representation of the model graphs that is computed off-line. Subgraphs that appear multiple times within the same or within different model graphs are represented only once, thus reducing the computational effort to detect them in an input graph. In the extreme case where all model graphs are highly similar, the run time of the new algorithm becomes independent of the number of model graphs. We also describe an extension of this method to error-correcting graph matching. Furthermore, an approach to subgraph isomorphism detection based on decision trees is proposed. A decision tree is generated from the models in an off-line phase. This decision tree can be used for subgraph isomorphism detection. The time needed for decision tree traversal is only polynomial in terms of the number of nodes of the input graph. Moreover, the time complexity of the decision tree traversal is completely independent on the number of model graphs, regardless of their similarity. However, the size of the decision tree is exponential in the number of nodes of the models. To cut down the space complexity of the decision tree, some pruning strategies are discussed.

scholarly journals Long-Term Loop Closure Detection through Visual-Spatial Information Preserving Multi-Order Graph Matching

2020 ◽  
Vol 34 (06) ◽  
pp. 10369-10376
Author(s):  
Peng Gao ◽  
Hao Zhang
Keyword(s):  
Spatial Information ◽  
Graph Matching ◽  
Fundamental Problem ◽  
Graph Representation ◽  
Spatial Relationships ◽  
Matching Problem ◽  
Loop Closure ◽  
Loop Closure Detection ◽  
Visual Spatial

Loop closure detection is a fundamental problem for simultaneous localization and mapping (SLAM) in robotics. Most of the previous methods only consider one type of information, based on either visual appearances or spatial relationships of landmarks. In this paper, we introduce a novel visual-spatial information preserving multi-order graph matching approach for long-term loop closure detection. Our approach constructs a graph representation of a place from an input image to integrate visual-spatial information, including visual appearances of the landmarks and the background environment, as well as the second and third-order spatial relationships between two and three landmarks, respectively. Furthermore, we introduce a new formulation that formulates loop closure detection as a multi-order graph matching problem to compute a similarity score directly from the graph representations of the query and template images, instead of performing conventional vector-based image matching. We evaluate the proposed multi-order graph matching approach based on two public long-term loop closure detection benchmark datasets, including the St. Lucia and CMU-VL datasets. Experimental results have shown that our approach is effective for long-term loop closure detection and it outperforms the previous state-of-the-art methods.

Applying Rigidity Theory Methods for Topological Decomposition and Synthesis of Gear Train Systems

2012 ◽  
Author(s):  
Maria Terushkin ◽  
Offer Shai
Keyword(s):  
Synthesis Method ◽  
Building Blocks ◽  
The Body ◽  
Computational Method ◽  
Gear Train ◽  
Graph Representation ◽  
Rigidity Theory ◽  
Graph Representations ◽  
Machine Theory ◽  
Gear Trains

This paper introduces a novel way to augment the knowledge and methods of rigidity theory to the topological decomposition and synthesis of gear train systems. A graph of gear trains, widely reported in the literature of machine theory, is treated as a graph representation from rigidity theory—the Body-Bar graph. Once we have this Body-Bar graph, methods and theorems from rigidity theory can be employed for analysis and synthesis. In this paper we employ the pebble-game algorithm, a computational method which allows determination of the topological mobility of mechanisms and the decomposition of gear trains into basic building blocks—Body-Bar Assur Graphs. Once we gain the ability to decompose any gear train into standalone components (Body-Bar Assur Graphs), this paper suggests inverting the process and applying the same method for synthesis. Relying on rigidity theory operations (Body-Bar extension, in this case), it is possible to construct all of the Body-Bar Assur Graphs, meaning the building blocks of gear trains. Once we have these building blocks at hand, it is possible to recombine them in various ways, providing us with a topological synthesis method for constructing gear trains. This paper also introduces a transformation between the Body-Bar graph and other graph representations used in mechanisms, thus leaving room for the application of the proposed synthesis and decomposition method directly to known graph representations already used in machine theory.

Sign in / Sign up

Export Citation Format

Share Document