BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:Asia/Dhaka BEGIN:DAYLIGHT DTSTART:20380119T091407 TZOFFSETFROM:+0600 TZOFFSETTO:+0600 RRULE:FREQ=YEARLY;BYDAY=3TU;BYMONTH=1 TZNAME:+06 END:DAYLIGHT BEGIN:STANDARD DTSTART:20091231T230000 TZOFFSETFROM:+0700 TZOFFSETTO:+0600 RRULE:FREQ=YEARLY;BYDAY=-1TH;BYMONTH=12 TZNAME:+06 END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20250821T164428Z UID:099C8C0E-50B9-43A5-9D30-282334087036 DTSTART;TZID=Asia/Dhaka:20250810T103000 DTEND;TZID=Asia/Dhaka:20250810T130000 DESCRIPTION:Following the welcome address\, our honorable Chairperson\, Pro fessor Dr. Md. Ahsan Habib\, SMIEEE\, delivered a brief speech emphasizing the significance of academic events and acknowledging IEEE’s contributi on in organizing the seminar. He highlighted the value of knowledge-sharin g platforms in fostering students’ academic and professional growth.\n\n The keynote speech was then delivered by the Vice-Chancellor of Green Univ ersity of Bangladesh\, Professor Dr. Mohammad Shorif Uddin\, SMIEEE\, who also served as the Chief Guest. He began by discussing Artificial Intellig ence as a pivotal force shaping the Fifth Industrial Revolution\, providin g insights into various image processing systems and their operational mec hanisms. He elaborated on different learning paradigms\, including Few-Sho t Learning (FSL)\, and outlined the seminar’s content.\n\nProfessor Uddi n explored computer vision\, explaining challenges such as viewpoint varia tion\, occlusion\, scaling\, deformation\, intra-class variation\, local a mbiguity\, and background complexity. He traced the historical evolution o f computer vision and emphasized how machine learning can enhance work eff iciency. Encouraging students to engage with academic literature\, he disc ussed supervised\, unsupervised\, semi-supervised\, and reinforcement lear ning\, supported by visual graphs and frameworks.\n\nThe discussion extend ed to deep learning\, conventional machine learning algorithms\, transfer learning\, Generative Adversarial Networks (GANs)\, and federated learning \, highlighting research opportunities in these areas. He stressed data ef ficiency and interpretability\, addressing limitations of current approach es and strategies like data augmentation and synthetic data generation thr ough GANs.\n\nProfessor Uddin provided a detailed explanation of Few-Shot Learning\, covering meta-learning\, metric-based learning\, optimization-b ased approaches\, and generative methods with illustrative diagrams. He th en introduced Explainable AI (XAI)\, highlighting tools such as SHAP and L IME for transparency and accountability in AI systems. He concluded by emp hasizing the synergy between FSL and XAI in developing AI that is both pow erful and interpretable.\n\nFollowing the keynote\, Professor Dr. Md. Ahsa n Habib delivered the closing speech\, reinforcing the importance of resea rch\, advising students to develop independence for securing internships\, and encouraging proactive career development. He also discussed improveme nts to the university’s multipurpose room facilities and thanked all par ticipants.The seminar concluded with an award ceremony and photo session\, recognizing students who completed IDP-1 and IDP-2 for their outstanding projects. The event officially ended at 1:00 p.m.\, leaving participants e nriched with insights into the evolving landscape of AI\, Few-Shot Learnin g\, and Explainable AI.\n\nSpeaker(s): Shorif Uddin\, \n\nBldg: Multi-Pur pose hall\, Green University of Bangladesh\, Purbachal American City\, Dha ka\, Bangladesh LOCATION:Bldg: Multi-Purpose hall\, Green University of Bangladesh\, Purbac hal American City\, Dhaka\, Bangladesh ORGANIZER:ieee_sb@green.edu.bd SEQUENCE:7 SUMMARY:Towards Data-Eficient and Interpretable Computer Vision: Advances i n Few-Shot Learning and Explainable AI. URL;VALUE=URI:https://events.vtools.ieee.org/m/497672 X-ALT-DESC:Description: <br /><p data-start="107" data-end="464"><strong id ="docs-internal-guid-85aac62a-7fff-6340-8559-0a487c28923b">&nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; & nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nb sp\; &nbsp\; <img src="https://lh7-rt.googleusercontent.com/docsz/AD_4nXca iDev64KsbbgJA6n7W2iH_rkKREAax5mgr26chTi1oqQ0fwzegwFsIxr_UUrg7amGk5-tvCRB0h 3t10latT2G0zcDfjHKK6KYeZAn-8Nlabfzb1kv0iY9p4gp3JvmGePFcefObw?key=o7Wb61ALf HrN-QtiPXKW4w" width="641" height="279"></strong></p>\n<p data-start="107" data-end="464">Following the welcome address\, our honorable Chairperson\ , Professor Dr. Md. Ahsan Habib\, SMIEEE\, delivered a brief speech emphas izing the significance of academic events and acknowledging IEEE&rsquo\;s contribution in organizing the seminar. He highlighted the value of knowle dge-sharing platforms in fostering students&rsquo\; academic and professio nal growth.</p>\n<p data-start="466" data-end="984">The keynote speech was then delivered by the Vice-Chancellor of Green University of Bangladesh\, Professor Dr. Mohammad Shorif Uddin\, SMIEEE\, who also served as the Chi ef Guest. He began by discussing Artificial Intelligence as a pivotal forc e shaping the Fifth Industrial Revolution\, providing insights into variou s image processing systems and their operational mechanisms. He elaborated on different learning paradigms\, including Few-Shot Learning (FSL)\, and outlined the seminar&rsquo\;s content.</p>\n<p data-start="986" data-end= "1495">Professor Uddin explored computer vision\, explaining challenges su ch as viewpoint variation\, occlusion\, scaling\, deformation\, intra-clas s variation\, local ambiguity\, and background complexity. He traced the h istorical evolution of computer vision and emphasized how machine learning can enhance work efficiency. Encouraging students to engage with academic literature\, he discussed supervised\, unsupervised\, semi-supervised\, a nd reinforcement learning\, supported by visual graphs and frameworks.</p> \n<p data-start="1497" data-end="1910">The discussion extended to deep lea rning\, conventional machine learning algorithms\, transfer learning\, Gen erative Adversarial Networks (GANs)\, and federated learning\, highlightin g research opportunities in these areas. He stressed data efficiency and i nterpretability\, addressing limitations of current approaches and strateg ies like data augmentation and synthetic data generation through GANs.</p> \n<p data-start="1912" data-end="2379">Professor Uddin provided a detailed explanation of Few-Shot Learning\, covering meta-learning\, metric-based learning\, optimization-based approaches\, and generative methods with ill ustrative diagrams. He then introduced Explainable AI (XAI)\, highlighting tools such as SHAP and LIME for transparency and accountability in AI sys tems. He concluded by emphasizing the synergy between FSL and XAI in devel oping AI that is both powerful and interpretable.</p>\n<p data-start="1912 " data-end="2379">Following the keynote\, Professor Dr. Md. Ahsan Habib de livered the closing speech\, reinforcing the importance of research\, advi sing students to develop independence for securing internships\, and encou raging proactive career development. He also discussed improvements to the university&rsquo\;s multipurpose room facilities and thanked all particip ants.The seminar concluded with an award ceremony and photo session\, reco gnizing students who completed IDP-1 and IDP-2 for their outstanding proje cts. The event officially ended at 1:00 p.m.\, leaving participants enrich ed with insights into the evolving landscape of AI\, Few-Shot Learning\, a nd Explainable AI.</p> END:VEVENT END:VCALENDAR