Improving video ranking on social video platforms

Rupapara, Vaibhav; Thipparthy, Kaushika Reddy; Gunda, Naresh Kumar; Narra, Manideep; Gandhi, Swapnil

doi:10.1109/icsss49621.2020.9202153

Cited by 11 publications

(7 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The techniques based on object detection utilize a huge variety of image processing applications to mine the required portion. 6,7 It is generally utilized in applications, like retrieval of images, security, medical domain, and defense. 8,9 The majority of machine learning techniques are based on deep learning, which can produce and utilize artificial intelligence (AI)-features to discover and track different objects using real-time videos.…”

Section: Introductionmentioning

confidence: 99%

Object detection and multi‐object tracking based on optimized deep convolutional neural network and unscented Kalman filtering

Jaganathan¹,

Panneerselvam

Kumaraswamy³

2022

Concurrency and Computation

View full text Add to dashboard Cite

Summary The tracking of multiple objects has gained immense interest in several applications that ranges from video surveillance and robotics. The goal of tracking multiple objects is to discover correspondences and perform matching among various objects in frames. However, occlusion is a major issue in several classical techniques, which fail to track multiple moving objects. Here, the extraction of frames is done to obtain information about an action. Thereafter, the segmentation of objects is done using the entropy weighting K‐means (EWKM) algorithm to generate optimum segments from the frame. After that, the detection of the object is done using a deep convolutional neural network (DCNN) to obtain objects from segments. Proposed Jaya‐political optimizer (Jaya‐PO) is used to train DCNN, which is devised by collaborating political optimizer (PO) and Jaya optimization algorithm. After detecting the object, the tracking of multiple objects is done using the proposed Henry gas solubility optimized unscented Kalman filtering (HGSO‐based UKF), wherein the UKF is modified with HGSO. The proposed Jaya‐PO‐based DCNN and HGSO‐based UKF outperformed other methods with high accuracy of 92%, high multiple object tracking precision (MOTP) of 87.6%, high sensitivity of 91.7%, and high specificity of 92%.

show abstract

Section: Introductionmentioning

confidence: 99%

Object detection and multi‐object tracking based on optimized deep convolutional neural network and unscented Kalman filtering

Jaganathan¹,

Panneerselvam

Kumaraswamy³

2022

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…7,8 Its goal is to adopt a suitable HO initialization method. This method showed that it could enhance the utilization of resources 9,10 and quality of service (QoS) in heterogeneous networks. 11,12 The classical HO method integrates network loading with the RSS.…”

Section: Introductionmentioning

confidence: 99%

Fractional squirrel–dolphin echolocation with deep belief network for network‐controlled vertical handoff in disparate and heterogeneous wireless network

Patil

2021

Int J Communication

View full text Add to dashboard Cite

The innovative characteristics of different heterogeneous wireless networks provide better service. The disparate wireless access networks consist of wireless metropolitan access network (WMAN) and cellular networks. Various techniques are devised for dynamic network selection, but these techniques concentrated on attaining improved performance. To address this issue, a novel method is devised to improve the energy efficiency of disparate heterogeneous wireless networks. Here, the proposed fractional squirrel-dolphin echolocation (FrSqDE) algorithm is devised by integrating squirrel search optimization (SSA) and fractional dolphin echolocation (fractional DE) algorithm. In addition, the fitness function is considered with certain factors that include delay, bit error rate (BER), jitter, packet loss, energy consumption, probability of hot spot, average bit rate (ABR), and received signal strength (RSS). The proposed FrSqDE optimization algorithm is used for training deep belief networks (DBNs) to select optimal weights. Here, the network selection factors are given as input to the proposed FrSqDE-based DBN, wherein optimal decision is made to handle vertical handoff. The proposed FrSqDE-based DBN offered improved performance with a minimal call drop probability of 0.050, minimal delay of 0.013 s, minimal energy consumption of 0.393 J, and maximal throughput of 117.972 kbps.

show abstract

“…Thus, image enhancement approaches are introduced for improving the quality of the image. Nowadays, various frameworks or algorithms are developed for enhancing resolution, blurring effect, contrast, sensitivity, and limited noise levels in images and videos 5,8–10 . Moreover, for implementing effective image enhancement procedures, the methods fully rely on using pattern recognition effectively, which is the branch of artificial intelligence 11 …”

Section: Introductionmentioning

confidence: 99%

“…Nowadays, various frameworks or algorithms are developed for enhancing resolution, blurring effect, contrast, sensitivity, and limited noise levels in images and videos. 5,[8][9][10] Moreover, for implementing effective image enhancement procedures, the methods fully rely on using pattern recognition effectively, which is the branch of artificial intelligence. 11 Image enhancement aims to enhance the interesting region in the image that does not require image data transform and then match visual response and the image.…”

mentioning

confidence: 99%

Ant Cuckoo Search Optimization‐based deep learning classifier for image enhancement in spinal cord images

Saminathan¹,

Samuel²

2021

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Image enhancement has been paid great attention in several areas, and various image enhancement approaches are introduced by the researchers to enhance the images clearer from the degraded images. Accordingly, this paper presents the proposed ACSO-based IE-CGAN for image enhancement. Initially, an effective noisy pixel identification based on image enhancement is developed, which employs circular-based searching for improving the input image from several noises, like salt and pepper noise, speckle (impulse) noise, Gaussian noise, and random noise. Once the noisy pixels are identified, the pixel enhancement is done using the circular-based search. The noise removal is done using a statistical model, where the best threshold value is determining using the proposed Ant Cuckoo Search Optimization (ACSO) algorithm. The ACSO algorithm is newly designed by integrating Ant Lion Optimization (ALO) and the Cuckoo Search Optimization (CSO) algorithm. After that, the contrast enhancement is carried out using Image Enhancement Conditional Generative Adversarial Network (IE-CGAN), which is trained by the proposed ASCO algorithm. The experimentation is carried out using an osteoporotic vertebral fracture dataset, and the performance of image enhancement using ACSO-based IE-CGAN is evaluated based on Peak Signal to Noise ratio (PSNR), Structural Similarity Index (SSIM), and Second Derivative like Measure of Enhancement (SDME). The developed method achieves the maximal PSNR of 33.50 dB with salt and pepper noise, maximal SDME 41.38 dB with random noise, and maximal SSIM of 0.967 with salt and pepper noise.

show abstract

Improving video ranking on social video platforms

Cited by 11 publications

References 13 publications

Object detection and multi‐object tracking based on optimized deep convolutional neural network and unscented Kalman filtering

Object detection and multi‐object tracking based on optimized deep convolutional neural network and unscented Kalman filtering

Fractional squirrel–dolphin echolocation with deep belief network for network‐controlled vertical handoff in disparate and heterogeneous wireless network

Ant Cuckoo Search Optimization‐based deep learning classifier for image enhancement in spinal cord images

Contact Info

Product

Resources

About