Zobrazeno 1 - 10
of 715
pro vyhledávání: '"Islam, Ashraful"'
Accurate camera-to-lidar calibration is a requirement for sensor data fusion in many 3D perception tasks. In this paper, we present SceneCalib, a novel method for simultaneous self-calibration of extrinsic and intrinsic parameters in a system contain
Externí odkaz:
http://arxiv.org/abs/2304.05530
Autor:
Islam, Ashraful, Lundell, Ben, Sawhney, Harpreet, Sinha, Sudipta, Morales, Peter, Radke, Richard J.
We present a self-supervised learning (SSL) method suitable for semi-global tasks such as object detection and semantic segmentation. We enforce local consistency between self-learned features, representing corresponding image locations of transforme
Externí odkaz:
http://arxiv.org/abs/2207.04398
Autor:
Raman, Chirag, Vargas-Quiros, Jose, Tan, Stephanie, Islam, Ashraful, Gedik, Ekin, Hung, Hayley
Recording the dynamics of unscripted human interactions in the wild is challenging due to the delicate trade-offs between several factors: participant privacy, ecological validity, data fidelity, and logistical overheads. To address these, following
Externí odkaz:
http://arxiv.org/abs/2205.05177
Autor:
Abdul Karim, Md., Reddy Chappidi, Vishnuvardhan, Emrul Kayesh, Md., Santosh Kumar Raavi, Sai, Islam, Ashraful
Publikováno v:
In Solar Energy August 2024 278
Autor:
Islam, Ashraful, Sultana, Sonia
Title: Role of e-commerce for the survival of food service industry during covid-19 Level: Thesis for Master‟s Degree in Business Administration Authors: Ashraful Islam and Sonia Sultana Supervisor: Professor Akmal Hyder Examiner: Dr. Olivia Kang F
Externí odkaz:
http://urn.kb.se/resolve?urn=urn:nbn:se:hig:diva-35223
Autor:
Hossen, Md Imran, Islam, Ashraful, Anowar, Farzana, Ahmed, Eshtiak, Rahman, Mohammad Masudur, Xiali, Hei
Due to the variety of cyber-attacks or threats, the cybersecurity community enhances the traditional security control mechanisms to an advanced level so that automated tools can encounter potential security threats. Very recently, Cyber Threat Intell
Externí odkaz:
http://arxiv.org/abs/2108.06862
Autor:
Islam, Ashraful, Chen, Chun-Fu, Panda, Rameswar, Karlinsky, Leonid, Feris, Rogerio, Radke, Richard J.
Most existing works in few-shot learning rely on meta-learning the network on a large base dataset which is typically from the same domain as the target dataset. We tackle the problem of cross-domain few-shot learning where there is a large shift bet
Externí odkaz:
http://arxiv.org/abs/2106.07807
Autor:
Islam, Ashraful, Chen, Chun-Fu, Panda, Rameswar, Karlinsky, Leonid, Radke, Richard, Feris, Rogerio
Tremendous progress has been made in visual representation learning, notably with the recent success of self-supervised contrastive learning methods. Supervised contrastive learning has also been shown to outperform its cross-entropy counterparts by
Externí odkaz:
http://arxiv.org/abs/2103.13517
Weakly supervised temporal action localization is a challenging vision task due to the absence of ground-truth temporal locations of actions in the training videos. With only video-level supervision during training, most existing methods rely on a Mu
Externí odkaz:
http://arxiv.org/abs/2101.00545
Autor:
Islam, Ashraful, Radke, Richard J.
Temporal action localization is an important step towards video understanding. Most current action localization methods depend on untrimmed videos with full temporal annotations of action instances. However, it is expensive and time-consuming to anno
Externí odkaz:
http://arxiv.org/abs/2001.07793