Search

Your search keyword '"Awan, Muhammad"' showing total 820 results
Start Over Author "Awan, Muhammad" Publication Year Range Last 3 years
820 results on '"Awan, Muhammad"'

3. Attend-Fusion: Efficient Audio-Visual Fusion for Video Classification

Author

Awan, Mahrukh, Nadeem, Asmar, Awan, Muhammad Junaid, Mustafa, Armin, and Husain, Syed Sameed

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence
Abstract

Exploiting both audio and visual modalities for video classification is a challenging task, as the existing methods require large model architectures, leading to high computational complexity and resource requirements. Smaller architectures, on the other hand, struggle to achieve optimal performance. In this paper, we propose Attend-Fusion, an audio-visual (AV) fusion approach that introduces a compact model architecture specifically designed to capture intricate audio-visual relationships in video data. Through extensive experiments on the challenging YouTube-8M dataset, we demonstrate that Attend-Fusion achieves an F1 score of 75.64\% with only 72M parameters, which is comparable to the performance of larger baseline models such as Fully-Connected Late Fusion (75.96\% F1 score, 341M parameters). Attend-Fusion achieves similar performance to the larger baseline model while reducing the model size by nearly 80\%, highlighting its efficiency in terms of model complexity. Our work demonstrates that the Attend-Fusion model effectively combines audio and visual information for video classification, achieving competitive performance with significantly reduced model size. This approach opens new possibilities for deploying high-performance video understanding systems in resource-constrained environments across various applications.

Published
2024

4. A multi-component intervention to reduce bias during family planning visits: qualitative insights on implementation from Burkina Faso, Pakistan and Tanzania.

Author

Moucheraud, Corrina, Wollum, Alexandra, Awan, Muhammad, Dow, William, Friedman, Willa, Koulidiati, Jean-Louis, Sabasaba, Amon, Shah, Manisha, and Wagner, Zachary

Subjects
Burkina Faso, Contraception, Implementation science, Intervention, Pakistan, Qualitative research, Tanzania
Abstract

Beyond Bias was an intervention introduced in Burkina Faso, Pakistan and Tanzania, with the aim of reducing health worker bias toward young, unmarried and nulliparous women seeking family planning services. This study used qualitative methods - based on interviews with health workers who participated in the intervention, managers at health facilities that participated in the intervention, and policy and program stakeholders at the national level - to understand implementation experiences with the intervention. The results offer insights for organizations or countries seeking to implement Beyond Bias or similar programs, and point to some other key implementation challenges for multi-component interventions in lower-resource settings. The intervention, developed using a human-centered design approach, was seen as key for successful implementation but there were logistical challenges. The digital intervention was disruptive and distracting to many. In addition, the non-financial rewards intervention was perceived as complex, and some participants expressed feeling discouraged when they did not receive a reward. Beyond Bias did not sufficiently attend to the outer setting, and this was perceived as a major implementation barrier as it limited individuals capacity to fully achieve the desired behavior change; for example, space constraints meant that some health facilities could not ensure private services for all clients. There were scalability concerns related to cost, and there is uncertainty whether diversity of contexts (within and across countries) might constrain implementation of Beyond Bias at scale.

Published
2024

10. Development and Evaluation of Network Utilities Using Python for Efficient Management

Author

Sharma, Richa, Salekzamankhani, Shahram, Virdee, Bal, Awan, Muhammad Umair, Kacprzyk, Janusz, Series Editor, Gomide, Fernando, Advisory Editor, Kaynak, Okyay, Advisory Editor, Liu, Derong, Advisory Editor, Pedrycz, Witold, Advisory Editor, Polycarpou, Marios M., Advisory Editor, Rudas, Imre J., Advisory Editor, Wang, Jun, Advisory Editor, Hassanien, Aboul Ella, editor, Anand, Sameer, editor, Jaiswal, Ajay, editor, and Kumar, Prabhat, editor

Published
2024
Full Text
View/download PDF

24. Genome Editing: Mechanism and Utilization in Plant Breeding

Author

Awan, Muhammad Jawad Akbar, Anjum, Naveed, Pervaiz, Komal, Ijaz, Muhammad Usman, Khan, Muhammad Zuhaib, Amin, Imran, Mansoor, Shahid, Raina, Aamir, editor, Wani, Mohammad Rafiq, editor, Laskar, Rafiul Amin, editor, Tomlekova, Nasya, editor, and Khan, Samiullah, editor

Published
2023
Full Text
View/download PDF

25. A New Filled Function for Global Optimization

Author

Şahiner Ahmet, Ermiş Temel, and Awan Muhammad Wasim

Subjects
global optimization, filled function method, auxiliary function, bezier curve, primary 90c26, 65k05, secondary 90c30, 65k10, 65d10, Mathematics, QA1-939
Abstract

The filled function method has recently become very popular in optimization theory, as it is an e cient and e ective method for finding the global minimizer of multimodal functions. However, the fact that the existing filled functions in the literature generally have exponential or logarithmic terms and/or parameter sensitivity reduces the e ectiveness of this method. In this study, we propose a new non parameter and without exponential/logarithmic terms filled function, which is numerically stable, and is successfully used to solve global optimization problems. Furthermore, we have demonstrated how successful this new filled function method in terms of e ciency with numerical experiments and comparisons.

Published
2023
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results