Muhammad Haris Khan - Academia.edu (original) (raw)

Papers by Muhammad Haris Khan

IEEE Transactions on Pattern Analysis and Machine Intelligence

Accurate and robust visual object tracking is one of the most challenging and fundamental compute... more Accurate and robust visual object tracking is one of the most challenging and fundamental computer vision problems. It entails estimating the trajectory of the target in an image sequence, given only its initial location, and segmentation, or its rough approximation in the form of a bounding box. Discriminative Correlation Filters (DCFs) and deep Siamese Networks (SNs) have emerged as dominating tracking paradigms, which have led to significant progress. Following the rapid evolution of visual object tracking in the last decade, this survey presents a systematic and thorough review of more than 90 DCFs and Siamese trackers, based on results in nine tracking benchmarks. First, we present the background theory of both the DCF and Siamese tracking core formulations. Then, we distinguish and comprehensively review the shared as well as specific open research challenges in both these tracking paradigms. Furthermore, we thoroughly analyze the performance of DCF and Siamese trackers on nine benchmarks, covering different experimental aspects of visual tracking: datasets, evaluation metrics, performance, and speed comparisons. We finish the survey by presenting recommendations and suggestions for distinguished open challenges based on our analysis.

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Cornell University - arXiv, Mar 23, 2022

We study few-shot semantic segmentation that aims to segment a target object from a query image w... more We study few-shot semantic segmentation that aims to segment a target object from a query image when provided with a few annotated support images of the target class. Several recent methods resort to a feature masking (FM) technique to discard irrelevant feature activations which eventually facilitates the reliable prediction of segmentation mask. A fundamental limitation of FM is the inability to preserve the fine-grained spatial details that affect the accuracy of segmentation mask, especially for small target objects. In this paper, we develop a simple, effective, and efficient approach to enhance feature masking (FM). We dub the enhanced FM as hybrid masking (HM). Specifically, we compensate for the loss of fine-grained spatial details in FM technique by investigating and leveraging a complementary basic input masking method. Experiments have been conducted on three publicly available benchmarks with strong few-shot segmentation (FSS) baselines. We empirically show improved performance against the current state-of-the-art methods by visible margins across different benchmarks. Our code and trained models are available at: https://github.com/moonsh/HM-Hybrid-Masking

NUML International Journal of Business & Management

The study looks into the factors that influence electronic word of mouth, leading to goods and se... more The study looks into the factors that influence electronic word of mouth, leading to goods and services purchases. By reviewing the reviews of other reviewers on the internet, this study attempts to determine which factors impact an individual's purchasing decision because most internet users consult reviews before purchasing things; both the quality and quantity of reviews matter for that specific brand. In this study, four independent variables (information quality, website trustworthiness, social ties, and number of reviews) each impact electronic word of mouth, which leads to client purchasing decisions. For this study, two hundred and sixty-one university students were used as samples. A basic random sampling approach is used because the data is collected solely from university students. Out of the four variables studied, only two (website credibility and number of reviews) have a meaningful relationship with the purchasing decision. The findings imply that electronic word ...

Universities and institutes of higher education produce researchers and scholars who can find the... more Universities and institutes of higher education produce researchers and scholars who can find the solutions to the problems in their fields of studies. Researchers belonging to any academic discipline should have certain competencies and skills to conduct a valuable research. This study uses the Bibliometric method to investigate the literature published on researchers’ competencies, not limited to any specific subject. The query to search literature on research competencies was run on Web of Science and 5,716 results were analyzed. A comparison of pattern of publications and citations year wise was presented from 1905 to 2020. The study reveals that most of the publications were from USA. Similar results were found in the top ten highest research producing institutions which included five American and two Canadian universities. Keywords analysis shows the emergence of ‘research ethics’ and ‘academic writing’ as two major areas in research competencies

The digital divide refers to the gap between those people who have access to information and comm... more The digital divide refers to the gap between those people who have access to information and communication technologies (computer, cellphones, especially smart phones, digital hardware, software and internet) and those who don\u27t. Literature show that digital divide has been explored extensively in different perspectives. The main objective of the current study is to look at the bibliometric examination of research output on the Digital Divide literature published in the Web of Science from 1999 to 2021, using bibliometric and visualization techniques. Initially, minimum number of 14 keywords occurrences are selected in which 70 keywords out of 5127 finalized. For the Keywords analysis VOS-viewer were used. Five keywords “Digital Divide”, “Internet”, “ICT”, “Digital Inequalities” and “Digital Literacy” truly represent the nature of the current research. Finally, 2443 documents on Digital Divide indexed in the Web of Science database were analyzed, including Articles, Proceeding pa...

Energies

There is increasing growth in load demands and financial strain to upgrade the present power dist... more There is increasing growth in load demands and financial strain to upgrade the present power distribution system. It faces challenges such as power losses, voltage deviations, lack of reliability and voltage instability. There is also a sense of responsibility in the wake of environmental and energy crises to adopt distributed renewable resources for power generation. These challenges can be resolved by optimally allocating distributed generators (DGs) at different suitable locations in the radial power distribution system. Optimal allocation is a non-linear problem which is solved by powerful metaheuristic optimization algorithms. In this work, an objective function is introduced to optimally size four different types of DGs by utilizing honey badger algorithm (HBA), and comparison is drawn with grey wolf optimization (GWO) and whale optimization algorithm (WOA). The objective is to boost the voltage profile and minimize the power losses of the standard IEEE 33bus and 69-bus radial...

International Journal of Management Research and Emerging Sciences

Branding is an important factor in developing WOM communication, especially in the telecommunicat... more Branding is an important factor in developing WOM communication, especially in the telecommunication sector in Pakistan. Thus, this study aimed to evaluate the association between brand co-creation, brand love, and Word-of-Mouth communication, where the role of brand loyalty and brand association was studied in mediation. The researcher has implemented a quantitative design and used the five-Likert scale questionnaires as a research instrument. A total of 296 questionnaires have been included in the study, and the variable associations were evaluated based on mediation and path analysis. The results indicate a significant association between brand love, co-creation branding, and Word-of-Mouth communication by customers, showing that brand love is a stronger antecedent in the generation of word-of-mouth communication by the customers. The mediation results were also positive, showing that brand association and brand loyalty influence the relationship of brand love, co-creation brandi...

SSRN Electronic Journal

This study carried out the scientometric analysis of road traffic accident research in India from... more This study carried out the scientometric analysis of road traffic accident research in India from 1977 to 2020. It aimed to examine type of publications with their citations and usage, the year wise publication and citation growth, most preferred journals, authors' preference of keywords used, collaboration of Indian authors, authorship pattern and most prolific authors, and top contributing organizations. During 44 years of study, 1,132 research items were published and indexed in Web of Science (WoS) bibliographic database. Analysis discovered that number of publications increased from one (0.08%) in 1977 to 182 (16.07%) in 2018 and observed good progress in scholarly literature. Majority of scholarly publications were published in the form of article (740, 65.37%). From 2006 to 2018, number of publications increased rapidly from 11 (0.97%) to 182 (16.07%) publications, which was the most productive year for the researchers. On an average 25.73 documents were published per year and received 392.95 citations per year. Journal of Evaluation 2 of Medical and Dental Sciences published majority of the publications (108, 30.50%). The word "Trauma" was the most frequently used keyword. Majority of publications (83.38%) on road traffic accidents (RTA) were written by the Indian authors individually or with local collaboration. Majority of the publications (1,081, 95.49%) were written by multiple authors while 51 publications (4.51%) were from single author. Most prolific authors were Tiwari, G. and Mohan, D. with 18 publications each. The Indian Institute of Technology was highly contributing organization, which published 120 documents (10.60%).

Journal of Islamic and Religious Studies

Marketers are trying their best to find tactics and means of communication to gain the trust of c... more Marketers are trying their best to find tactics and means of communication to gain the trust of consumers by attracting them and keeping their needs and interests in view, like halal tourism in the domain of the hospitability industry. The main purpose of this study is to analyze and explain whether the trust is developed by Social Media influencers and Halal Tourism and hence impacts the travel decision of travelers or not, in the context of Pakistan. In this regard, the data is collected from university students of the University of Punjab Gujranwala Campus and GIFT University. After collection different tests of normality, correlation, regression, and mediations were run on the data for analysis by using statistical software SPSS 20. After analysis, it was found that all hypotheses are accepted and interpreted that Social Media Influencers and Halal Tourism significantly impact the decisions of travelers. The study also revealed that trust mediates the relationship between Social...

ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

We study the problem of learning association between face and voice, which is gaining interest in... more We study the problem of learning association between face and voice, which is gaining interest in the computer vision community lately. Prior works adopt pairwise or triplet loss formulations to learn an embedding space amenable for associated matching and verification tasks. Albeit showing some progress, such loss formulations are, however, restrictive due to dependency on distance-dependent margin parameter, poor run-time training complexity, and reliance on carefully crafted negative mining procedures. In this work, we hypothesize that enriched feature representation coupled with an effective yet efficient supervision is necessary in realizing a discriminative joint embedding space for improved face-voice association. To this end, we propose a lightweight , plug-and-play mechanism that exploits the complementary cues in both modalities to form enriched fused embeddings and clusters them based on their identity labels via orthogonality constraints. We coin our proposed mechanism as fusion and orthogonal projection (FOP) and instantiate in a two-stream pipeline. The overall resulting framework is evaluated on a large-scale VoxCeleb dataset with a multitude of tasks, including cross-modal verification and matching. Results show that our method performs favourably against the current state-of-the-art methods and our proposed supervision formulation is more effective and efficient than the ones employed by the contemporary methods.

Advances in Mathematical Physics

Growth series is an important invariant associated with group or monoid which classifies all the ... more Growth series is an important invariant associated with group or monoid which classifies all the words of group or monoid. Therefore, the growth series of braid monoids and Hecke algebras in Artin’s generators is presented in many scholarly published articles. The growth series of braid monoids M B 3 and M B 4 in band generators is known. In this work, we compute the complete presentation of braid monoid M B 5 in band generators by solving all the ambiguities of M B 5 . The words on the left-hand of each relation are reducible words, and the words on the right-hand side are canonical words. We partially find the growth series Q ∗ 5 of reducible words. Then, we construct a linear system for canonical words of M B 5 in band presentation and compute the corresponding growth series. We also find the growth rate of growth series of M B 5 in band generators.

Animals, 2021

Background: Fascioliasis is a zoonotic neglected tropical disease caused by Fasciola hepatica and... more Background: Fascioliasis is a zoonotic neglected tropical disease caused by Fasciola hepatica and F. gigantica. In endemic regions, fascioliasis represents a huge problem in livestock production and significantly threatens public health. The present study was performed to assess the key bibliometric indicators, plot the global research outcome, and strive to find the research frontiers and trends in fascioliasis. Methods: A descriptive bibliometric and visualized study was conducted. The data were extracted from the Web of Science Core Collection (WoSCC) database. The WoSCC was searched using key terms covering a wide range of synonyms related to the causative agent (Fasciola) and the disease (fascioliasis). The database search was performed for the period from the inception of WoSCC until 3 October 2021. The downloaded data were exported into VOSviewer software version 1.6.17 for Windows to construct co-authorship countries, keywords co-occurrence, bibliographic coupling sources, a...

International Journal of Pharmacy and Pharmaceutical Sciences, 2016

Objective: The objective of this research was to evaluate the, total phenolic contents (TPC), tot... more Objective: The objective of this research was to evaluate the, total phenolic contents (TPC), total flavonoid contents (TFC), antioxidant activity, cytotoxicity and functional group of epiphytes ferns grows on the Malaysian palm oil trunk (MPOTEF): that includes Nephrolepis biserrata (NBF), Davallia denticulata (DDF), Asplenium longissimum (ALF), Gonioplebium percussum (GPF), Stenochlaena palustris (SPF), Vittaria elongata (VLF) and Vittaria ensiformis (VSF). Methods : For extraction, microwave oven assisted method was used. TPC was determined by following the Folin-Ciocalteu colorimetric method and TFC was determined using aluminium chloride colorimetric assay. Antioxidant activity was determined by DPPH-scavenging assay methods. Results: All the ferns exhibited good results of TPC, TFC and antioxidant activity. SPF showed highest TPC and TFC in aqueous extracts; 639.4 mg/g and 172.71 mg/g respectively, and the same result showed in ethanol extracts; 271.61 mg/g and 174.54 mg/g, re...

Applied Sciences, 2020

The quality of red chili is characterized based on its color and pungency. Several factors like h... more The quality of red chili is characterized based on its color and pungency. Several factors like humidity, temperature, light, and storage conditions affect the characteristic qualities of red chili, thus preservation required several measures. Instead of ensuring these measures, traders are using oil and Sudan dye in red chili to increase the value of an inferior product. Thus, this work presents the feasibility of utilizing a hyperspectral camera for the detection of oil and Sudan dye in red chili. This study describes the important wavelengths (500–700 nm) where different adulteration affects the response of the reflected spectrum. These wavelengths are then utilized for training an Support Vector Machine (SVM) algorithm to detect pure, oil-adulterated, and Sudan dye-adulterated red chili. The classification performance achieves 97% with the reduced dimensionality and 100% with complete validation data. The trained algorithm is further tested on separate data with different adulte...

Biological Control, 2018

Intraguild predation (IGP) is a common phenomenon among the predacious coccinellids which involve... more Intraguild predation (IGP) is a common phenomenon among the predacious coccinellids which involves a combination of predation and competition. The aphidophagous predators, Coccinella septempunctata L. and Hippodamia variegata (G.) comprise major part of coccinellid predator species in the agroecosystem of Turkey. We investigated the IG interactions between these aphidophagous predators under laboratory conditions. Our results revealed that predation of the eggs of H. variegata by the adult male, female and 4 th instar larvae of C. septempunctata was maximum at 0 prey abundance, however, substantial number of eggs were also consumed at aphid densities of 30 and 80. Consumption of 1 st and 2 nd instar larvae was also higher in the absence of aphids, intermediate at 80 aphid density and greatly reduced or almost negligible at 350 prey abundance. The same sequence was also true for the predation of the different juvenile stages of C. septempunctata by H. variegata adult male, female and 4 th instar larvae. The adult female and 4 th instar larvae of both C. septempunctata and H. variegata proved to be more voracious towards different heterospecific juvenile stages compared to adult male. Results on the preference of C. septempunctata and H. variegata towards conspecific or heterospecific eggs revealed that both the aphidophagous coccinellids showed higher degree of preference for egg cannibalism (conspecific egg consumption) over IGP (heterospecific egg consumption).

Mobile Networks and Applications, 2018

Sensors (Basel, Switzerland), Jan 21, 2018

Movement analysis of infants' body parts is momentous for the early detection of various move... more Movement analysis of infants' body parts is momentous for the early detection of various movement disorders such as cerebral palsy. Most existing techniques are either marker-based or use wearable sensors to analyze the movement disorders. Such techniques work well for adults, however they are not effective for infants as wearing such sensors or markers may cause discomfort to them, affecting their natural movements. This paper presents a method to help the clinicians for the early detection of movement disorders in infants. The proposed method is marker-less and does not use any wearable sensors which makes it ideal for the analysis of body parts movement in infants. The algorithm is based on the deformable part-based model to detect the body parts and track them in the subsequent frames of the video to encode the motion information. The proposed algorithm learns a model using a set of part filters and spatial relations between the body parts. In particular, it forms a mixture ...

Sustainability, 2016

The severe hot temperature and high traffic loadings in the Kingdom of Saudi Arabia (KSA) are cau... more The severe hot temperature and high traffic loadings in the Kingdom of Saudi Arabia (KSA) are causing distress in flexible pavements within a few years of service. Secondly, the conventional bitumen extracted from Saudi oil refineries have a performance grade of 64-10 (PG 64-10), which does not meet the SuperPave performance grade requirement for most of the KSA's regions. In order to improve the performance grade of bitumen, different percentages of municipal wastes (plastic and crumb rubber) were used as bitumen additives. The performance of bitumen at low, intermediate, and high temperatures was evaluated. This is important as the waste production is rising significantly due to the fast urbanization and high population growth in the KSA. Particularly, when there are very few ways of recycling these wastes (municipal, as well as industrial), which in fact have great impact on the environment. High-density polyethylene (HDP), low-density polyethylene (LDP), and crumb rubber (CR) with 5%, 10%, and 15% by weight of bitumen, were mixed with the base bitumen (PG 64-10). Rotational viscometer (RV), dynamic shear rheometer (DSR), and bending beam rheometer (BBR) were used to evaluate the viscosity, rutting, fatigue, and low-temperature behavior of base and modified binders. The test results indicated that the rutting (permanent deformation) and fatigue resistance were significantly improved in modified binders due to the improvement in the visco-elastic properties.

Journal of Armed Forces Medical College, Bangladesh, 2014

Arrhythmias are not uncommon after Coronary Artery Bypass Graft (CABG) surgery. There is increasi... more Arrhythmias are not uncommon after Coronary Artery Bypass Graft (CABG) surgery. There is increasing evidence that Magnesium, the important intracellular cation plays a crucial role in preventing and terminating cardiac arrhythmias. Objectives: The aim of this study was to establish the role of peroperative use of intravenous Magnesium in reducing the incidence of per and postoperative arrhythmias in CABG surgery. Materials and methods: A total sixty (Group-I 30 and Group-II 30) patients of both sexes and different ages undergoing conventional CABG surgery under general anesthesia in CMH Dhaka from January 2009 to December 2011 were selected randomly. After induction, Group-I received 2 gm of Magnesium in 100 ml normal saline intravenously over a period of 30 minutes and Group-II received no Magnesium. Parameters recorded per and postoperatively were-aortic cross clamp time, Cardio Pulmonary Bypass (CPB) time, total surgery time, Heart Rate (HR), Systolic Blood Pressure (SBP), Diastolic Blood Pressure (DBP)