Zoom Link

https://voxel51.com/computer-vision-events/august-24-meetup-apac/

Removing Backgrounds Automatically or with the User's Native Language

Image matting, also known as removing background, refers to extracting the accurate foregrounds in the image, which benefits many downstream applications such as film production and augmented reality. To solve this ill-posed problem, previous methods require extra user inputs with large amounts of manual effort such as trimap or scribbles. In this session, we will introduce our research, which allows user to automatically remove the background or even flexibly choose the specific foreground by a user's native language. We'll also show some fancy demos and illustrate some downstream applications.

Jizhizi Li has just finished her Ph.D. study in Artificial Intelligence at the University of Sydney. With several papers published in top-tier conferences and journals including CVPR, IJCV, IJCAI and Multimedia, her research interests include computer vision, image matting, multi-modal learning, and AIGC.

Self-Supervised Representative Learning for Action Recognition in Videos

Video data is exploding and drawing intelligence from it is increasing in importance. Self-supervised learning has grown in popularity because it enables the use of large data sets without having large labeled data. Action recognition in videos has always been a challenging task that is well-suited to leverage self supervised learning. This talk will cover representative learning pretext task with approaches such as contrastive learning and masked auto-encoders for videos.

Vidhya Vinay is a co-founder of Streamingo.ai, an AI startup that works on human activity detection in videos. As part of her work at Streamingo, Vidhya has worked on deep learning for speech recognition, NLP and computer vision.

AI at the Edge: Optimizing Deep Learning Models for Real-World Applications

As AI technology continues to advance, there is a growing demand for deep learning models to tackle more complex tasks, particularly on edge devices. However, real-time performance and hardware constraints can present significant challenges in deploying these models on such devices. At SightX, we have been exploring ways to optimize deep learning models for top performance on edge devices while minimizing degradation. In this lecture, we will share our insights and techniques for deploying AI on edge devices, specifically focusing on hardware-aware optimization of deep learning models. We’ll review practical ways to effectively deploy deep learning models in real-time scenarios.

Raz Petel, SightX’s Head of AI, has been tackling Computer Vision challenges with Deep Learning since 2015, aiming to enhance their efficiency, speed, compactness, and resilience