COSMO: Contextualized scene modeling with Boltzmann Machines

Bozcan, İlker; Kalkan, Sinan

doi:10.1016/j.robot.2018.12.009

Cited by 14 publications

(12 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Contextual information in the field of object detection can help to understand and explore object vicinity (i.e., scene-level context) as applied in [4,45], and also provides object-object relationships (i.e., object-level context) as in [9,40]. Moreover, Contextual information has been also studied in different areas, such as object localization [12], image segmentation [22], out-of-context detection [11], image annotation [34], scene modeling [6], image understanding [14] and cognitive robotics [48].…”

Section: B Contextual Informationmentioning

confidence: 99%

See 1 more Smart Citation

Improving Object Detection Performance Using Scene Contextual Constraints

Alamri

Pugeault

2022

IEEE Trans. Cogn. Dev. Syst.

View full text Add to dashboard Cite

Contextual information, such as the co-occurrence of objects and the spatial and relative size among objects, provides rich and complex information about digital scenes. It also plays an important role in improving object detection and determining out-of-context objects. In this work, we present contextual models that leverage contextual information (16 contextual relationships are applied in this paper) to enhance the performance of two of the state-of-the-art object detectors (i.e., Faster RCNN and YOLO), which are applied as a post-processing process for most of the existing detectors, especially for refining the confidences and associated categorical labels, without refining bounding boxes. We experimentally demonstrate that our models lead to enhancement in detection performance using the most common dataset used in this field (MSCOCO), where in some experiments PASCAL2012 is also used. We also show that iterating the process of applying our contextual models also enhances the detection performance further.

show abstract

Section: B Contextual Informationmentioning

confidence: 99%

“…In terms of object recognition, it could be defined as cues captured from a scene that presents knowledge about objects locations, size and objectto-object relationships. Due to the importance of contextual information, it has been widely studied [6,12,18,32,37,48].…”

Section: Introductionmentioning

confidence: 99%

Improving Object Detection Performance Using Scene Contextual Constraints

Alamri

Pugeault

2022

IEEE Trans. Cogn. Dev. Syst.

View full text Add to dashboard Cite

show abstract

“…Mutlu et al [47] presented a comprehensive review on graph feature learning and feature extraction techniques for link prediction. Bozcan and Kalkan [3] introduced COSMO: Contextualized scene modeling with Boltzmann machines.…”

Section: Application Of Srlmentioning

confidence: 99%

Statistical Relational Learning: A State-of-the-Art Review

Kastrati¹,

Biba²

2019

Journal of Engineering Technology and Applied Sciences

View full text Add to dashboard Cite

The objective of this paper is to review the state-of-the-art of statistical relational learning (SRL) models developed to deal with machine learning and data mining in relational domains in presence of missing, partially observed, and/or noisy data. It starts by giving a general overview of conventional graphical models, first-order logic and inductive logic programming approaches as needed for background. The historical development of each SRL key model is critically reviewed. The study also focuses on the practical application of SRL techniques to a broad variety of areas and their limitations.

show abstract

“…In recent years, with the rapid development of technologies such as virtual reality and 3D printing, the application of 3D models has become more and more widespread [6][7][8][9]. Traditional three-dimensional scene modeling methods mainly include modeling techniques based on geometric modeling and modeling techniques that use instrumentation to obtain scene depth information [10][11]. The instrument-based modeling technology obtains the depth information of the scene by using laser, infrared and other ranging technologies to realize the three-dimensional modeling of the target object [12].…”

Section: Introductionmentioning

confidence: 99%

Value of Virtual Reality Technology in Image Inspection and 3D Geometric Modeling

2020

IEEE Access

View full text Add to dashboard Cite

Aiming at the poor expressive ability of image statistical information during the reconstruction process of traditional 3D image reconstruction method based on virtual reality technology, resulting in low accuracy of 3D image after reconstruction, a new image detection and 3D image reconstruction based on virtual reality technology are studied method. This paper first proposed a new twolevel cascade convolutional neural network structure. The first level of the network predicts target positioning based on the image-level labels of the training image, generates a bounding box of the target in the original image, and generates a cropped image. The cropped image is input to the second-level network. The cropped image may contain areas where the target is stuck in the original image. Level 2 networks only use the adhesion area as training data.Secondly, the visualization software development platform and virtual reality 3D image processing software are selected as the platform for 3D image reconstruction. After the original image is imported into the computer through data input and file analysis steps, the original image is detected. The detected image is in the virtual in the real software, the bounding box method is first used to construct the three-dimensional data field of image reconstruction, and the three-dimensional direct volume of the image is drawn according to the three-dimensional data field of image reconstruction. Preferably, the three-dimensional image reconstruction output formula is obtained through the threedimensional image direct volume to realize the three-dimensional image reconstruction based on the virtual reality technology. The simulation results show that the method proposed in this paper can effectively detect images. The average traversal coverage of 3D image reconstruction is up to 0.979, and the reconstruction accuracy is higher than 0.97. INDEX TERMS image classification; distributed network representation learning; deep learning; neighbor reconstruction.

show abstract

COSMO: Contextualized scene modeling with Boltzmann Machines

Cited by 14 publications

References 67 publications

Improving Object Detection Performance Using Scene Contextual Constraints

Improving Object Detection Performance Using Scene Contextual Constraints

Statistical Relational Learning: A State-of-the-Art Review

Value of Virtual Reality Technology in Image Inspection and 3D Geometric Modeling

Contact Info

Product

Resources

About