Skeleton-based action/gesture recognition has already witnessed excellent progress on processing large-scale, laboratory-based datasets with pre-defined skeleton joint topology. However, it's still an unsolved tas...
详细信息
ISBN:
(数字)9781665490627
ISBN:
(纸本)9781665490627
Skeleton-based action/gesture recognition has already witnessed excellent progress on processing large-scale, laboratory-based datasets with pre-defined skeleton joint topology. However, it's still an unsolved task when it comes to real-world scenarios with practical limitations such as small-scaled dataset sizes, few-labeled samples, and various skeleton topologies. In this paper, we work on the recognition of micro-gestures, which are subtle body gestures collected in real-world scenarios. Specifically, we utilize contrastive learning to heritage the knowledge from known large-scale datasets for enhancing the learning on fewer samples of micro-gestures. To overcome the gap caused by various domain distributions and structure topologies between the datasets, we compute skeleton representations from augmented sequences via momentum-based efficient and scalable encoders as additional inductive priors. Importantly, we propose an effective dense-graphbased unsupervised architecture that resorts to a queue-based dictionary to store positive and negative keys for better contrast with queries to learn substantially efficient and discriminant patterns in the feature space. Together with cross-dataset experimental results show that our model significantly improves the accuracies on two micro-gesture datasets, SMG by 7.4% and iMiGUE by 18.41% advocating its superiority.
this book constitutes the refereed proceedings of the 13th IAPR-TC-15 internationalworkshop on graph-basedrepresentations in patternrecognition, GbRPR 2023, which took place in Vietri sul Mare, Italy...
详细信息
ISBN:
(数字)9783031427954
ISBN:
(纸本)9783031427947
this book constitutes the refereed proceedings of the 13th IAPR-TC-15 internationalworkshop on graph-basedrepresentations in patternrecognition, GbRPR 2023, which took place in Vietri sul Mare, Italy, in September 2023.;the 16 full papers included in this book were carefully reviewed and selected from 18 submissions. they were organized in topical sections on graph kernels and graph algorithms; graph neural networks; and graph-basedrepresentations and applications.
In the field of structural patternrecognitiongraphs constitute a very common and powerful way of representing objects. the main drawback of graphrepresentations is that the computation of various graph similarity m...
详细信息
ISBN:
(纸本)9783642208447
In the field of structural patternrecognitiongraphs constitute a very common and powerful way of representing objects. the main drawback of graphrepresentations is that the computation of various graph similarity measures is exponential in the number of involved nodes. Hence, such computations are feasible for rather small graphs only. One of the most flexible graph similarity measures is graph edit distance. In this paper we propose a novel approach for the efficient computation of graph edit distance based on bipartite graph matching by means of the Volgenant-Jonker assignment algorithm. Our proposed algorithm provides only suboptimal edit distances, but runs in polynomial time. the reason for its sub-optimality is that edge information is taken into account only in a limited fashion during the process of finding the optimal node assignment between two graphs. In experiments on diverse graphrepresentations we demonstrate a high speed up of our proposed method over a traditional algorithm for graph edit distance computation and over two other sub-optimal approaches that use the Hungarian and Munkres algorithm. Also, we show that classification accuracy remains nearly unaffected by the suboptimal nature of the algorithm.
In this paper we explore how a spectral technique suggested by quantum walks can be used to distinguish non-isomorphic cospectral graphs. Reviewing ideas from the field of quantum computing we recall the definition of...
详细信息
this paper shows how strings can be used in a natural images classification task. We propose to build an attributed string from a set of regions of interest detected thanks to an interest point detector. these salient...
详细信息
We introduce a method for computing homology groups and their generators of a 2D image, using a hierarchical structure, i.e. irregular graph pyramid. Starting from an image, a hierarchy of the image is built by two op...
详细信息
We introduce a method for computing homology groups and their generators of a 2D image, using a hierarchical structure, i.e. irregular graph pyramid. Starting from an image, a hierarchy of the image is built by two operations that preserve homology of each region. Instead of computing homology generators in the base where the number of entities (cells) is large, we first reduce the number of cells by a graph pyramid. then homology generators are computed efficiently on the top level of the pyramid, since the number of cells is small. A top down process is then used to deduce homology generators in any level of the pyramid, including the base level, i.e. the initial image. the produced generators fit on the object boundaries. A unique set of generators called the minimal set, is defined and its computation is discussed. We show that the new method produces valid homology generators and present some experimental results. (C) 2008 Elsevier B.V. All rights reserved.
We present a novel Smartwatch-based approach, to enable Mobile Assisted Living (MAL) for users with special needs. A major focus group for this approach are elderly people. We developed a tool for caregivers applicabl...
详细信息
ISBN:
(纸本)9781450364874
We present a novel Smartwatch-based approach, to enable Mobile Assisted Living (MAL) for users with special needs. A major focus group for this approach are elderly people. We developed a tool for caregivers applicable in home environments, nursing care, and hospitals, to assess the vitality of their patients. Hereby, we particularly focus on the prediction of falls, because falls are a major reason for serious injuries and premature death among elderly. therefore, we propose a multi parametric score based on standardized fall risk assessment tests, as well as on sleep quality, medication, patient history, motor skills, and environmental factors. the resulting total fall risk score reflects individual changes in behavior and vitality, which consequently enables for fall preventing interventions. Our system has been deployed and evaluated in a pilot study among 30 elderly patients over a period of four weeks.
Recognizing human-object interactions is challenging due to their spatio-temporal changes. We propose the Spatio-Temporal Interaction Transformer-based (STIT) network to reason such changes. Specifically, spatial tran...
详细信息
ISBN:
(数字)9781665490627
ISBN:
(纸本)9781665490627
Recognizing human-object interactions is challenging due to their spatio-temporal changes. We propose the Spatio-Temporal Interaction Transformer-based (STIT) network to reason such changes. Specifically, spatial transformers learn humans and objects context at specific frame time. Temporal transformer then learns the relations at a higher level between spatial context representations at different time steps, capturing long-term dependencies across frames. We further investigate multiple hierarchy designs in learning human interactions. We achieved superior performance on Charades, Something-Something v1 and CAD-120 datasets, comparing to baseline models without learning human-object relations, or with prior graph-based networks. We also achieved state-of-the-art accuracy of 95.93% on CAD-120 dataset [1] by employing RGB data only.
We present a new algorithm based on Dual graph Contraction (DGC) to transform the Run graph into its Minimum Line Property Preserving (MLPP) form which, when implemented in parallel, requires O(log(longestcurve)) step...
详细信息
A robust method for registering inter-band and inter-sensor remote sensing images has been designed and implemented. the proposed method introduces noise-resilient and contrast invariant control point detection and co...
详细信息
ISBN:
(纸本)9781424426539
A robust method for registering inter-band and inter-sensor remote sensing images has been designed and implemented. the proposed method introduces noise-resilient and contrast invariant control point detection and control point matching schemes based on robust complex wavelet feature representations. Furthermore, an iterative refinement scheme is introduced for achieving improved control point pair localization and mapping function estimation between the images being registered. the registration accuracy of the proposed method was demonstrated on the registration of multi-spectral optical and synthetic aperture radar (SAR) images. the proposed method achieves better registration accuracy when compared withthe state-of-the-art MSSD and ARRSI registration algorithms.
暂无评论