DDSC X Veo
Join us for an exciting DDSC event with Veo! 🎤 Fine-grained Image Analysis (FGIA), Veo and Trackman 🍕 Food & Drinks Provided! 🤝 Mingle with fellow DDSC computer vision and AI/ML enthusiasts!
DDSC X Veo
Summary
Join us for an exciting DDSC event with Veo! 🎤 Fine-grained Image Analysis (FGIA), Veo and Trackman 🍕 Food & Drinks Provided! 🤝 Mingle with fellow DDSC computer vision and AI/ML enthusiasts!
Time and place
Veo
2100, København
Rovsingsgade 68
Date 20-02-2025
Time 16:30 - 20:00
Description
🎤 Featured Speaker:
Dive into the world of Fine-grained Image Analysis (FGIA)! This talk by Serge Belongie, Director of the AI Pioneer Centre, will explore the challenges and advancements in recognizing visual objects from subordinate categories, such as species of birds or models of cars. Read more below.
✨ Veo:
Learn about Veo's innovative AI-powered follow-cam technology that automatically follows the action of the game, providing a broadcast-like experience. Read more here: https://www.veo.co/
Don't miss this opportunity to expand your knowledge, network with peers, and enjoy some great food and drinks! 🍽️🥳
Program
16:30 Doors open
17:00 Welcome speech from DDSC
17:05 Welcome speech from Veo
17:15 1st speaker - Challenges in Fine-Grained Image Analysis by Serge Belongie
18:00 Break w. food, drinks and socializing
18:30 2nd speaker - Trackman: Redefining Sports Through Vision by Christian Ingwersen, Tech and Vision AI Lead at Trackman
19:15 Socializing - meet the community
20:00 Good Bye. See you next time!
Challenges in Fine-Grained Image Analysis
Fine-grained image analysis (FGIA) is a longstanding and fundamental problem in computer vision and pattern recognition, and underpins a diverse set of real-world applications. The task of FGIA is concerned with visual objects from subordinate categories, e.g., species of birds or models of cars. The small inter-class and large intra-class variation inherent to fine-grained image analysis makes it a challenging problem. Capitalizing on advances in deep learning, in recent years we have witnessed remarkable progress in deep learning powered FGIA. In this talk we review representative examples in the context of recognition, retrieval, and generation/synthesis. In addition, we also review other key issues of FGIA, such as publicly available benchmark datasets, related domain-specific applications, and connections with other modalities including text and audio. We conclude by highlighting several research directions and open problems.
RSVP Now!
We look forward to seeing you there! 🚀
Location pin: https://maps.app.goo.gl/sYtCJcZgBUbNSuzNA