scholarly journals Multi-Level Graph Encoding with Structural-Collaborative Relation Learning for Skeleton-Based Person Re-Identification

2021 ◽  
Author(s):  
Haocong Rao ◽  
Shihao Xu ◽  
Xiping Hu ◽  
Jun Cheng ◽  
Bin Hu
Keyword(s):  
Superior Performance ◽  
Skeleton Graph ◽  
Graph Dynamics ◽  
Connected Body ◽  
Body Component ◽  
Multi Level ◽  
Highly Correlated ◽  
High Level ◽  
Body Joints ◽  
Relation Learning

Skeleton-based person re-identification (Re-ID) is an emerging open topic providing great value for safety-critical applications. Existing methods typically extract hand-crafted features or model skeleton dynamics from the trajectory of body joints, while they rarely explore valuable relation information contained in body structure or motion. To fully explore body relations, we construct graphs to model human skeletons from different levels, and for the first time propose a Multi-level Graph encoding approach with Structural-Collaborative Relation learning (MG-SCR) to encode discriminative graph features for person Re-ID. Specifically, considering that structurally-connected body components are highly correlated in a skeleton, we first propose a multi-head structural relation layer to learn different relations of neighbor body-component nodes in graphs, which helps aggregate key correlative features for effective node representations. Second, inspired by the fact that body-component collaboration in walking usually carries recognizable patterns, we propose a cross-level collaborative relation layer to infer collaboration between different level components, so as to capture more discriminative skeleton graph features. Finally, to enhance graph dynamics encoding, we propose a novel self-supervised sparse sequential prediction task for model pre-training, which facilitates encoding high-level graph semantics for person Re-ID. MG-SCR outperforms state-of-the-art skeleton-based methods, and it achieves superior performance to many multi-modal methods that utilize extra RGB or depth features. Our codes are available at https://github.com/Kali-Hac/MG-SCR.

scholarly journals MCCRNet: A Multi-Level Change Contextual Refinement Network for Remote Sensing Image Change Detection

2021 ◽  
Vol 10 (9) ◽  
pp. 591
Author(s):  
Qingtian Ke ◽  
Peng Zhang
Keyword(s):  
Remote Sensing ◽  
Change Detection ◽  
Superior Performance ◽  
Detection Methods ◽  
Sample Number ◽  
Level Change ◽  
Class Context ◽  
Discrimination Information ◽  
Multi Level ◽  
High Level

Change detection based on bi-temporal remote sensing images has made significant progress in recent years, aiming to identify the changed and unchanged pixels between a registered pair of images. However, most learning-based change detection methods only utilize fused high-level features from the feature encoder and thus miss the detailed representations that low-level feature pairs contain. Here we propose a multi-level change contextual refinement network (MCCRNet) to strengthen the multi-level change representations of feature pairs. To effectively capture the dependencies of feature pairs while avoiding fusing them, our atrous spatial pyramid cross attention (ASPCA) module introduces a crossed spatial attention module and a crossed channel attention module to emphasize the position importance and channel importance of each feature while simultaneously keeping the scale of input and output the same. This module can be plugged into any feature extraction layer of a Siamese change detection network. Furthermore, we propose a change contextual representations (CCR) module from the perspective of the relationship between the change pixels and the contextual representation, named change region contextual representations. The CCR module aims to correct changed pixels mistakenly predicted as unchanged by a class attention mechanism. Finally, we introduce an effective sample number adaptively weighted loss to solve the class-imbalanced problem of change detection datasets. On the whole, compared with other attention modules that only use fused features from the highest feature pairs, our method can capture the multi-level spatial, channel, and class context of change discrimination information. The experiments are performed with four public change detection datasets of various image resolutions. Compared to state-of-the-art methods, our MCCRNet achieved superior performance on all datasets (i.e., LEVIR, Season-Varying Change Detection Dataset, Google Data GZ, and DSIFN) with improvements of 0.47%, 0.11%, 2.62%, and 3.99%, respectively.

Methyl mercury in the dutch rhine delta

1994 ◽  
Vol 30 (10) ◽  
pp. 213-219 ◽  
Author(s):  
Hendrik Pieters ◽  
Victor Geuke
Keyword(s):  
Suspended Matter ◽  
Methyl Mercury ◽  
Mercury Contamination ◽  
Benthic Organisms ◽  
Considerable Decrease ◽  
Continuous Sedimentation ◽  
Highly Correlated ◽  
High Level ◽  
Almost All

Samples of yellow eel from various locations in the Dutch Rhine area have been analyzed for trend monitoring of mercury since 1977. In the western Rhine delta mercury levels in eels have hardly changed since the seventies, whereas in the eastern part of the Dutch Rhine area a considerable decrease of mercury concentrations in eel has occurred. Because of continuous sedimentation of contaminated suspended matter transported from upstream regions, accumulation rates and concentrations of mercury in eel in the western Rhine delta remained at a relatively high level. Analyses of methyl mercury in biota have been performed to elucidate the role of methyl mercury in the mercury contamination of the Dutch Rhine ecosystem. Low percentages of methyl mercury were observed in zooplankton (3 to 35%). In benthic organisms (mussels) percentages of methyl mercury ranged from 30 to 57%, while in fish species and liver of aquatic top predator birds almost all the mercury was present in the form of methyl mercury (> 80%). During the period 1970-1990 mercury concentrations of suspended matter in the eastern Rhine delta have drastically decreased. These concentrations seemed to be highly correlated with mercury concentrations of eel (R = 0.84). The consequences of this relation are discussed.

scholarly journals A Review of Algorithms and Hardware Implementations for Spiking Neural Networks

2021 ◽  
Vol 11 (2) ◽  
pp. 23
Author(s):  
Duy-Anh Nguyen ◽  
Xuan-Tu Tran ◽  
Francesca Iacopi
Keyword(s):  
Neural Networks ◽  
Computational Cost ◽  
Superior Performance ◽  
Training Algorithms ◽  
Current State ◽  
Hardware Implementations ◽  
Neuromorphic Hardware ◽  
High Level ◽  
Event Based ◽  
Hardware Platforms

Deep Learning (DL) has contributed to the success of many applications in recent years. The applications range from simple ones such as recognizing tiny images or simple speech patterns to ones with a high level of complexity such as playing the game of Go. However, this superior performance comes at a high computational cost, which made porting DL applications to conventional hardware platforms a challenging task. Many approaches have been investigated, and Spiking Neural Network (SNN) is one of the promising candidates. SNN is the third generation of Artificial Neural Networks (ANNs), where each neuron in the network uses discrete spikes to communicate in an event-based manner. SNNs have the potential advantage of achieving better energy efficiency than their ANN counterparts. While generally there will be a loss of accuracy on SNN models, new algorithms have helped to close the accuracy gap. For hardware implementations, SNNs have attracted much attention in the neuromorphic hardware research community. In this work, we review the basic background of SNNs, the current state and challenges of the training algorithms for SNNs and the current implementations of SNNs on various hardware platforms.

A Comparison of Urban with Rural Support Networks: Liverpool and North Wales

1995 ◽  
Vol 15 (1) ◽  
pp. 59-81 ◽  
Author(s):  
G. Clare Wenger
Keyword(s):  
Rural Communities ◽  
Support Networks ◽  
Support Network ◽  
Social Variables ◽  
North Wales ◽  
Care And Support ◽  
Wide Range ◽  
Highly Correlated ◽  
High Level ◽  
The City

AbstractThis paper compares findings on the distribution of support networks in the City of Liverpool and in rural communities in North Wales. It demonstrates that while support network type is highly correlated with a wide range of demographic and social variables in both urban and rural samples, the nature of the relationships are not always comparable. The paper shows how cultural, migration and socio-economic factors interact to affect the formation of different types of support networks. As a result of a more stable elderly population, more old people in Liverpool have network types able to provide a high level of informal care and support.

scholarly journals An Efficient Module for Instance Segmentation Based on Multi-Level Features and Attention Mechanisms

2021 ◽  
Vol 11 (3) ◽  
pp. 968
Author(s):  
Yingchun Sun ◽  
Wang Gao ◽  
Shuguo Pan ◽  
Tao Zhao ◽  
Yahui Peng
Keyword(s):  
Feature Extraction ◽  
Spatial Structure ◽  
Semantic Feature ◽  
Semantic Features ◽  
Segmentation Method ◽  
Spatial Dimensions ◽  
Feature Pyramid ◽  
Multi Level ◽  
High Level ◽  
Instance Segmentation

Recently, multi-level feature networks have been extensively used in instance segmentation. However, because not all features are beneficial to instance segmentation tasks, the performance of networks cannot be adequately improved by synthesizing multi-level convolutional features indiscriminately. In order to solve the problem, an attention-based feature pyramid module (AFPM) is proposed, which integrates the attention mechanism on the basis of a multi-level feature pyramid network to efficiently and pertinently extract the high-level semantic features and low-level spatial structure features; for instance, segmentation. Firstly, we adopt a convolutional block attention module (CBAM) into feature extraction, and sequentially generate attention maps which focus on instance-related features along the channel and spatial dimensions. Secondly, we build inter-dimensional dependencies through a convolutional triplet attention module (CTAM) in lateral attention connections, which is used to propagate a helpful semantic feature map and filter redundant informative features irrelevant to instance objects. Finally, we construct branches for feature enhancement to strengthen detailed information to boost the entire feature hierarchy of the network. The experimental results on the Cityscapes dataset manifest that the proposed module outperforms other excellent methods under different evaluation metrics and effectively upgrades the performance of the instance segmentation method.

The breeding success of common loons (Gavia immer) in relation to alkalinity and other lake characteristics in Ontario

1988 ◽  
Vol 66 (3) ◽  
pp. 746-752 ◽  
Author(s):  
Robert Alvo ◽  
David J. T. Hussell ◽  
Michael Berrill
Keyword(s):  
Breeding Success ◽  
Benthic Algae ◽  
Gavia Immer ◽  
Acidic Lake ◽  
Acidic Lakes ◽  
Common Loons ◽  
Breeding Attempt ◽  
High Alkalinity ◽  
Highly Correlated ◽  
High Level

We examined the breeding success of common loons (Gavia immer) and made observations of loons feeding their young on small lakes (5.3–75 ha) with different alkalinities (−73 to 1804 μequiv./L) near Sudbury, Ontario. Alkalinity, pH, and conductivity were highly correlated with each other. There was a significant positive relationship between successful breeding and alkalinity on 68 lakes surveyed in 1982. Discriminant analysis showed that alkalinity, area, and colour of the lake contributed significantly to discrimination among lakes with successful, unsuccessful, and no breeding attempts. Lack of a breeding attempt tended to be associated with small, brown, low-alkalinity lakes, and successful breeding with large, clear, high-alkalinity lakes. For lakes with breeding attempts in 1982–1984, alkalinity (all years), depth (1983), and area (1984) provided significant discrimination between unsuccessful lakes and those on which young were raised. Unsuccessful breeding resulted primarily from brood mortalities on acidic lakes. Adult loons were more successful at securing fish on high-alkalinity lakes than on low-alkalinity lakes, and this may reflect differences in fish densities. A pair of loons attempting to raise a chick on a fishless, acidic lake fed the chick benthic algae and possibly benthic invertebrates, but flew to other lakes to feed themselves. We suggest that the high level of brood mortalities on acidic lakes resulted from a shortage of suitable food for the young.

Performance on an Adaptive Automated Team Tracking Task with Human and Computer Teammates

1997 ◽  
Vol 41 (1) ◽  
pp. 551-555 ◽  
Author(s):  
Kristin Krahl ◽  
Mark W. Scerbo
Keyword(s):  
Adaptive Systems ◽  
High Performance ◽  
Vertical Axis ◽  
Tracking Task ◽  
Superior Performance ◽  
Performance Skills ◽  
Group Assignment ◽  
Pursuit Tracking ◽  
Human Participants ◽  
High Level

The present study examined team performance on an adaptive pursuit tracking task with human-human and human-computer teams. The participants were randomly assigned to one of three team conditions where their partner was either a computer novice, computer expert, or human. Participants began the experiment with control over either the horizontal or vertical axis, but had the option of taking control of their teammate's axis if they achieved superior performance on the previous trial. A control condition was also run where a single participant controlled both axes. Performance was assessed by RMSE scores over 100 trials. The results showed that performance along the horizontal axis improved over the session regardless of the experimental condition, but the degree of improvement was dependent upon group assignment. Individuals working alone or paired with an expert computer maintained a high level of performance throughout the experiment. Those paired with a computer-novice or another human performed poorly initially, but eventually reached the level of those in the other conditions. The results showed that team training can be as effective as individual training, but that the quality of training is moderated by the skill level of one's teammate. Moreover, these findings suggest that task partitioning of high performance skills between a human and a computer is not only possible but may be considered a viable option in the design of adaptive systems.

Custody of the Myelodysplastic Child: Implications for Selection for Early Treatment

PEDIATRICS ◽  
1974 ◽  
Vol 53 (2) ◽  
pp. 253-256
Author(s):  
Patricia W. Hayden ◽  
David B. Shurtleff ◽  
Arline B. Broy
Keyword(s):  
University Hospital ◽  
Contributory Factor ◽  
Foster Home ◽  
Term Care ◽  
Long Term Follow Up ◽  
Selection For ◽  
Foster Home Care ◽  
Highly Correlated ◽  
High Level

Of 173 patients with myelodysplasia followed in the Birth Defects Center at University Hospital between 1968 and 1972, 30 (17%) have been placed outside their natural families for temporary or long-term care. Only one has been adopted and five have been institutionalized; the remainder have been in foster home care. High level paralysis, mental retardation, and lower socioeconomic status correlate positively with placement. In this series, gender was not a contributory factor. An initial "hopeless" prognosis and/or selection for "no treatment" were decisions often made prior to referral to this center but were highly correlated to placement. Considering the multiple medical, emotional, and economic problems facing these families, relinquishment of custody should be anticipated in a significant percentage of cases. To date, placement outside the natural family has been viewed primarily as abandonment or as an emergency solution to a crisis. Long-term follow-up study of this group of children may indicate that transfer of custody can be a positive therapeutic alternative for the child and his family.

Sign in / Sign up

Export Citation Format

Share Document