Spatio-temporal convolution kernels

Knauf, Konstantin; Memmert, Daniel; Brefeld, Ulf

doi:10.1007/s10994-015-5520-1

Cited by 39 publications

(35 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ese convolutional kernels reflect the organization information in the images extracted by the deep CNN, that is, the features of the object in the image. Generally speaking, the ordered convolutional kernels usually mean effective extraction of the organization information, while chaotic ones mean the "overfitting" of networks [49]. is is helpful for establishing the relationship between regularization intensity and network generalization ability and provides standards or principles to guide algorithm development or model structure improvement.…”

Section: Relationship Between Data Augmentation and Networkmentioning

confidence: 99%

A Full Stage Data Augmentation Method in Deep Convolutional Neural Network for Natural Image Classification

Zheng

Tian

Jiang

et al. 2020

Discrete Dynamics in Nature and Society

147

View full text Add to dashboard Cite

Nowadays, deep learning has achieved remarkable results in many computer vision related tasks, among which the support of big data is essential. In this paper, we propose a full stage data augmentation framework to improve the accuracy of deep convolutional neural networks, which can also play the role of implicit model ensemble without introducing additional model training costs. Simultaneous data augmentation during training and testing stages can ensure network optimization and enhance its generalization ability. Augmentation in two stages needs to be consistent to ensure the accurate transfer of specific domain information. Furthermore, this framework is universal for any network architecture and data augmentation strategy and therefore can be applied to a variety of deep learning based tasks. Finally, experimental results about image classification on the coarse-grained dataset CIFAR-10 (93.41%) and fine-grained dataset CIFAR-100 (70.22%) demonstrate the effectiveness of the framework by comparing with state-of-the-art results.

show abstract

Section: Relationship Between Data Augmentation and Networkmentioning

confidence: 99%

A Full Stage Data Augmentation Method in Deep Convolutional Neural Network for Natural Image Classification

Zheng

Tian

Jiang

et al. 2020

Discrete Dynamics in Nature and Society

147

View full text Add to dashboard Cite

show abstract

“…The amount of available data about various sports is constantly increasing, most importantly tracking data and event data [14]. Within soccer, the analysis of tracking data focuses on discovering individual or collective movement patterns, e.g., spectral clustering of trajectories [6], strategy analysis with occupancy maps [12], or formation analysis via minimum entropy partitioning [1]. Gyarmati et al use event data to discover motif patterns in pass sequences [4].…”

Section: Related Workmentioning

confidence: 99%

Automatically Discovering Offensive Patterns in Soccer Match Data

Haaren

Dzyuba

Hannosset

et al. 2015

Advances in Intelligent Data Analysis XIV

View full text Add to dashboard Cite

Abstract. In recent years, many professional sports clubs have adopted camera-based tracking technology that captures the location of both the players and the ball at a high frequency. Nevertheless, the valuable information that is hidden in these performance data is rarely used in their decision-making process. What is missing are the computational methods to analyze these data in great depth. This paper addresses the task of automatically discovering patterns in offensive strategies in professional soccer matches. To address this task, we propose an inductive logic programming approach that can easily deal with the relational structure of the data. An experimental study shows the utility of our approach.

show abstract

“…To infer the underlying spatio-temporal dynamical process, a variety of methods have been proposed. These include kernel-based methods [10], approaches using spatio-temporal Kriging [11] as well as Bayesian nonparametric approaches for multi-dimensional spatial evolution [12]. Some methods aim to tackle this problem assuming separability of the spatial and the temporal evolution which helps to simplify the inference problem.…”

Section: Introductionmentioning

confidence: 99%

Field dynamics inference via spectral density estimation

Frank¹,

Steininger²,

Enßlin³

2017

Phys. Rev. E

View full text Add to dashboard Cite

Stochastic differential equations (SDEs) are of utmost importance in various scientific and industrial areas. They are the natural description of dynamical processes whose precise equations of motion are either not known or too expensive to solve, e.g., when modeling Brownian motion. In some cases, the equations governing the dynamics of a physical system on macroscopic scales occur to be unknown since they typically cannot be deduced from general principles. In this work, we describe how the underlying laws of a stochastic process can be approximated by the spectral density of the corresponding process. Furthermore, we show how the density can be inferred from possibly very noisy and incomplete measurements of the dynamical field. Generally, inverse problems like these can be tackled with the help of Information Field Theory (IFT). For now, we restrict to linear and autonomous processes. Though, this is a non-conceptual limitation that may be omitted in future work. To demonstrate its applicability we employ our reconstruction algorithm on a time-series and spatio-temporal processes.

show abstract

Spatio-temporal convolution kernels

Cited by 39 publications

References 49 publications

A Full Stage Data Augmentation Method in Deep Convolutional Neural Network for Natural Image Classification

A Full Stage Data Augmentation Method in Deep Convolutional Neural Network for Natural Image Classification

Automatically Discovering Offensive Patterns in Soccer Match Data

Field dynamics inference via spectral density estimation

Contact Info

Product

Resources

About