{"id":507,"date":"2018-06-13T10:38:12","date_gmt":"2018-06-13T10:38:12","guid":{"rendered":"http:\/\/madima.org\/?page_id=507"},"modified":"2026-07-08T10:49:53","modified_gmt":"2026-07-08T10:49:53","slug":"invited-speaker","status":"publish","type":"page","link":"https:\/\/madima.org\/madima2023\/invited-speaker\/","title":{"rendered":"Invited Speakers"},"content":{"rendered":"
\n
\n \n
\n
\n
\n
\n
\n \n <\/div>\n
\n
\n
Yuki M. Asano is an assistant professor for computer vision and machine learning at the VIS Lab at the University of Amsterdam. Prior to this, he finished his PhD at the Visual Geometry Group at the University of Oxford working with Andrea Vedaldi. He is the main organiser for the ECCV workshop series on 'Self-supervised Learning - What is next?', and ICCV's 'Big Model Adaptation in Computer Vision' workshop. During his PhD he has won the Qualcomm PhD Fellowship and interned at Meta AI.<\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div> \n <\/div> \n <\/div>\n <\/div>\n\t\t\t\n\n\n\n

Dr. Yuki M. Asano<\/strong><\/p>\n\n\n

<\/span>Towards Pixel-level Self-supervised Learning<\/div>
\nIn this talk I will talk about self-supervised learning and its current development of moving from image-level to pixel-level representations. We will first dive into how clustering can be combined with representation learning using optimal transport, a paradigm still relevant in current SoTA models like SwAV\/DINO\/MSN\/DINOv2. Next, I will show how self-supervised clustering can be used for unsupervised segmentation in images and how videos can be leveraged to obtain even better image encoders.
\n<\/div><\/div>\n\n\n
\n
\n \n
\n
\n
\n
\n
\n \n <\/div>\n
\n
\n
Aulo Gelli works as a senior research fellow in the Nutrition, Diets, and Health Unit of the International Food Policy Research Institute (IFPRI). His main interests and experience intersect food policy and nutrition, with a particular focus on evaluating the impact of child health and nutrition interventions. Aulo trained as a physicist at Imperial College London, then gained a MSc degree in information processing and neural networks at Kings College London working on semantic memory models, and then studied human perception and cognition at the Laboratory of Neurobiology at University College London. He transitioned his career towards food policy, gaining a MA in development economics and food security at the University of Rome, and a DPhil from the Department of Infectious Disease Epidemiology at Imperial College. Prior to working at IFPRI, Aulo worked as a research fellow at Imperial College (2009-2013), as policy analyst at the UK Collaborative on Development Sciences (2007-2009), and as a statistician at the World Food Programme (2004-2007).<\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div> \n <\/div> \n <\/div>\n <\/div>\n\t\t\t\n\n\n\n

Dr. Aulo Gelli<\/strong><\/p>\n\n\n

<\/span>An innovative passive dietary monitoring system<\/div>
\nObjectives:<\/strong> To validate FRANI (Food Recognition Assistance and Nudging Insights), a mobile phone application with computer vision assisted dietary assessment, and multi-pass 24-hour recalls (24HR), against weighed records (WR) in female youth aged 18-24y in Ghana.
\nMethods:<\/strong> Dietary intake was assessed on two non-consecutive days using FRANI, WRs and 24HRs. Equivalence of nutrient intake was tested using mixed effect models adjusted for repeated measures, by comparing ratios (FRANI\/WR and 24HR\/WR) with equivalence margins at 10%, 15% and 20% error bounds. Agreement between methods was assessed using the concordance correlation coefficient (CCC).
\nResults:<\/strong> Equivalence for FRANI and WR was determined at the 10% bound for fibre and folate, at 15% bound for energy, protein, fat, iron, riboflavin, thiamine, and vitamin B6 and zinc, while intake of calcium was equivalent at the 20% bound. Comparisons between 24HR and WR found protein and riboflavin intake estimates falling within a 10% bound. Iron, niacin, thiamine, and zinc intakes were equivalent at the 15% bound; and folate and vitamin B6 were equivalent at the 20% bound. The CCCs between FRANI and WR ranged between 0.44 and 0.72 (mean=0.57), and between 0.45 and 0.76 (mean=0.62) for 24HR and WR.
\nConclusions:<\/strong> FRANI-assisted dietary assessment and 24HRs were found to accurately estimate nutrient intake in female youth in urban Ghana.
\nFunding Sources: <\/strong>CGIAR.
\n<\/div><\/div>\n","protected":false},"excerpt":{"rendered":"

Dr. Yuki M. Asano Dr. Aulo Gelli<\/p>\n","protected":false},"author":3,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"nf_dc_page":"","footnotes":""},"class_list":["post-507","page","type-page","status-publish","hentry"],"aioseo_notices":[],"aioseo_head":"\n\t\t\n\t\n\t\n\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t