BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:DAYLIGHT
DTSTART:20250309T030000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:PDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20251102T010000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:PST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250416T221611Z
UID:989E430D-5F0A-4CFF-B2BA-07C8C8E58D2D
DTSTART;TZID=America/Los_Angeles:20250415T173000
DTEND;TZID=America/Los_Angeles:20250415T183000
DESCRIPTION:In this talk\, Dr Subarna Tripathi\, will share exciting advanc
 ements from her research group\, Visual Algorithm Research\, at Intel Labs
 . In her own words... "in the first part of my talk\, I will cover several
  video representations methods such as sparse graphs and sparse transforme
 rs that are equipped with long-form reasoning capability. In the second pa
 rt\, I will focus on our research addressing egocentric use cases and seve
 ral associated algorithmic advancements. I will conclude with our recent w
 ork around video large language models".\n\nCo-sponsored by: Media Partner
 : Open Research Institute (ORI)\n\nSpeaker(s): Dr. Subarna Tripathi\n\nAge
 nda: \n- Invited talk from Dr. Subarna Tripathi\, research scientist at [I
 ntel Labs](https://intelailabpage.github.io/)\, working in computer vision
  and machine learning.\n- Q/A Session\n\nVirtual: https://events.vtools.ie
 ee.org/m/478569
LOCATION:Virtual: https://events.vtools.ieee.org/m/478569
ORGANIZER:upalmahbub@yahoo.com
SEQUENCE:91
SUMMARY:Towards Long-Form Video Representation Learning : Sparse Representa
 tions\, Leveraging Domain knowledge and Video-Large Language Models
URL;VALUE=URI:https://events.vtools.ieee.org/m/478569
X-ALT-DESC:Description: <br /><div id="list_meeting_header">\n<p>In this ta
 lk\, Dr Subarna Tripathi\, will share exciting advancements from her resea
 rch group\, Visual Algorithm Research\, at Intel Labs. In her own words...
  "in the first part of my talk\, I will cover several video representation
 s methods such as sparse graphs and sparse transformers that are equipped 
 with long-form reasoning capability. In the second part\, I will focus on 
 our research addressing egocentric use cases and several associated algori
 thmic advancements. I will conclude with our recent work around video larg
 e language models".</p>\n</div><br /><br />Agenda: <br /><ul>\n<li>Invited
  talk from Dr. Subarna Tripathi\, research scientist at&nbsp\;<a href="htt
 ps://intelailabpage.github.io/">Intel Labs</a>\, working in computer visio
 n and machine learning.</li>\n<li>Q/A Session</li>\n</ul>
END:VEVENT
END:VCALENDAR