Zobrazeno 1 - 10
of 129
pro vyhledávání: '"Afzal, Muhammad Zeshan"'
Autor:
Sarode, Shalini, Khan, Muhammad Saif Ullah, Shehzadi, Tahira, Stricker, Didier, Afzal, Muhammad Zeshan
We propose ClassroomKD, a novel multi-mentor knowledge distillation framework inspired by classroom environments to enhance knowledge transfer between student and multiple mentors. Unlike traditional methods that rely on fixed mentor-student relation
Externí odkaz:
http://arxiv.org/abs/2409.20237
Autor:
Khan, Muhammad Saif Ullah, Khan, Muhammad Ahmed Ullah, Afzal, Muhammad Zeshan, Stricker, Didier
This paper reformulates cross-dataset human pose estimation as a continual learning task, aiming to integrate new keypoints and pose variations into existing models without losing accuracy on previously learned datasets. We benchmark this formulation
Externí odkaz:
http://arxiv.org/abs/2409.20469
Autor:
Khan, Mohammad Sadil, Sinha, Sankalp, Sheikh, Talha Uddin, Stricker, Didier, Ali, Sk Aziz, Afzal, Muhammad Zeshan
Prototyping complex computer-aided design (CAD) models in modern softwares can be very time-consuming. This is due to the lack of intelligent systems that can quickly generate simpler intermediate parts. We propose Text2CAD, the first AI framework fo
Externí odkaz:
http://arxiv.org/abs/2409.17106
The impressive advancements in semi-supervised learning have driven researchers to explore its potential in object detection tasks within the field of computer vision. Semi-Supervised Object Detection (SSOD) leverages a combination of a small labeled
Externí odkaz:
http://arxiv.org/abs/2407.08460
Autor:
Khan, Muhammad Saif Ullah, Sinha, Sankalp, Stricker, Didier, Liwicki, Marcus, Afzal, Muhammad Zeshan
Reconstructing texture-less surfaces poses unique challenges in computer vision, primarily due to the lack of specialized datasets that cater to the nuanced needs of depth and normals estimation in the absence of textural information. We introduce "S
Externí odkaz:
http://arxiv.org/abs/2406.15831
Autor:
Khan, Muhammad Saif Ullah, Shehzadi, Tahira, Noor, Rabeya, Stricker, Didier, Afzal, Muhammad Zeshan
Automated signature verification on bank checks is critical for fraud prevention and ensuring transaction authenticity. This task is challenging due to the coexistence of signatures with other textual and graphical elements on real-world documents. V
Externí odkaz:
http://arxiv.org/abs/2406.14370
The Situational Instructions Database (SID) addresses the need for enhanced situational awareness in artificial intelligence (AI) systems operating in dynamic environments. By integrating detailed scene graphs with dynamically generated, task-specifi
Externí odkaz:
http://arxiv.org/abs/2406.13302
Autor:
Sheikh, Talha Uddin, Shehzadi, Tahira, Hashmi, Khurram Azeem, Stricker, Didier, Afzal, Muhammad Zeshan
Document layout analysis is a key area in document research, involving techniques like text mining and visual analysis. Despite various methods developed to tackle layout analysis, a critical but frequently overlooked problem is the scarcity of label
Externí odkaz:
http://arxiv.org/abs/2406.06236
Human pose estimation is a key task in computer vision with various applications such as activity recognition and interactive systems. However, the lack of consistency in the annotated skeletons across different datasets poses challenges in developin
Externí odkaz:
http://arxiv.org/abs/2405.20084
Table detection, a pivotal task in document analysis, aims to precisely recognize and locate tables within document images. Although deep learning has shown remarkable progress in this realm, it typically requires an extensive dataset of labeled data
Externí odkaz:
http://arxiv.org/abs/2405.04971