![VIP Lab at the University of Waterloo](/img/default-banner.jpg)
- 12
- 1 943
VIP Lab at the University of Waterloo
Registrace 3. 11. 2023
Welcome to the CZcams channel of the Vision and Image Processing Lab at the University of Waterloo.
The Vision and Image Processing (VIP) Lab is a research group under the Systems Design Engineering Department at the University of Waterloo. The VIP Lab is dedicated to understanding visual processes and finding solutions for the outstanding problems in visual processing and perception, as well as artificial intelligence, machine learning, and intelligent systems for a wide variety of applications. The VIP Lab also focuses on pushing the boundaries of AI by tackling the key operational challenges surrounding widespread adoption of AI and enabling AI to become an empowering technology for anyone, anywhere, anytime. Towards this goal, two of the key areas of research interest for the VIP Lab are scalable AI and transparent and responsible AI, both of which are key to enabling widespread ethical use of AI for real-world societal impact.
The Vision and Image Processing (VIP) Lab is a research group under the Systems Design Engineering Department at the University of Waterloo. The VIP Lab is dedicated to understanding visual processes and finding solutions for the outstanding problems in visual processing and perception, as well as artificial intelligence, machine learning, and intelligent systems for a wide variety of applications. The VIP Lab also focuses on pushing the boundaries of AI by tackling the key operational challenges surrounding widespread adoption of AI and enabling AI to become an empowering technology for anyone, anywhere, anytime. Towards this goal, two of the key areas of research interest for the VIP Lab are scalable AI and transparent and responsible AI, both of which are key to enabling widespread ethical use of AI for real-world societal impact.
[MASc Thesis] Microarray Image Denoising
Thesis presentation by the MASc student Chris Czarnecki
zhlédnutí: 24
Video
[CVPRW 2024 MetaFood Workshop] How Much You Ate? Food Portion Estimation on Spoons
zhlédnutí 64Před měsícem
Presenter: Chris Czarnecki Presented at CVPR 2024 MetaFood Workshop as Oral Paper: arxiv.org/abs/2405.08717
Towards Real-Time Gaussian Splatting: Accelerating 3DGS through Photometric SLAM
zhlédnutí 1,3KPřed 2 měsíci
Authored by Yan Song Hu, Dayou Mao, Yuhao Chen, and John Zelek
[Best Paper Award @ CRV’24] Distribution and Depth-Aware Transformers for 3D Human Mesh Recovery
zhlédnutí 50Před 2 měsíci
Presentation by Jerrin Bright for the paper "Distribution and Depth-Aware Transformers for 3D Human Mesh Recovery” This work was presented at the 21st Conference on Robots and Vision (CRV'24) as an ORAL presentation. Paper: assets.pubpub.org/nzhl89hf/f9h-11715796570485.pdf
[NeurIPS2023] A Step Towards Worldwide Biodiversity Assessment: The BIOSCAN-1M Insect Dataset
zhlédnutí 19Před 6 měsíci
Presentation video for the paper "A Step Towards Worldwide Biodiversity Assessment: The BIOSCAN-1M Insect Dataset" presented by Dr. Zahra Gharaee Link to the paper: arxiv.org/abs/2307.10455 Link to the github: github.com/zahrag/BIOSCAN-1M
Covid Swab Tests Robot
zhlédnutí 283Před 7 měsíci
Peter Lee’s PhD work on building a control robot using visual serving for guiding covid swab tests.
[MMSports @ ACMMM 2023] Mitigating Motion Blur for Robust 3D Baseball Player Pose Modeling
zhlédnutí 29Před 10 měsíci
Presentation by Jerrin Bright for the paper "Mitigating Motion Blur for Robust 3D Baseball Player Pose Modeling for Pitch Analysis" This work was presented at the 6th International Workshop on Multimedia Content Analysis in Sports during the 2023 ACM Multimedia conference. Paper: dl.acm.org/doi/10.1145/3606038.3616163
[MMSports @ ACMMM 2023] Jersey Number Recognition from Low-Resolution Broadcast Videos
zhlédnutí 61Před 10 měsíci
Presentation by Bavesh Balaji for the paper "Jersey Number Recognition using Keyframe Identification from Low-Resolution Broadcast Videos" This work was presented at the 6th International ACM Workshop on Multimedia Content Analysis in Sports during the 2023 ACM Multimedia conference Paper: dl.acm.org/doi/10.1145/3606038.3616162
[MMSports Workshop @ ACMMM 2023] Rink-Agnostic Hockey Rink Registration
zhlédnutí 21Před 10 měsíci
Teaser video for our paper: Rink-Agnostic Hockey Rink Registration. This work was presented by Jason Shang at the 6th International ACM Workshop on Multimedia Content Analysis in Sports during the 2023 ACM Multimedia conference. Paper: dl.acm.org/doi/abs/10.1145/3606038.3616161
[All Things Attention Workshop @ NeurIPS 2022] "Faster Attention Is What You Need"
zhlédnutí 50Před 10 měsíci
Presentation by Saeejith Nair for the paper "Faster Attention Is What You Need: A Fast Self-Attention Neural Network Backbone Architecture for the Edge via Double-Condensing Attention Condensers" This work was presented at the NeurIPS 2022 Workshop on All Things Attention. Paper: arxiv.org/abs/2208.06980 Poster: neurips.cc/media/PosterPDFs/NeurIPS 2022/57622.png
[MADiMa@ACMMM 2023] NutritionVerse: Empirical Study of Various Dietary Intake Estimation Approaches
zhlédnutí 33Před 10 měsíci
Presentation prepared by Dr. Yuhao Chen for the paper "NutritionVerse: Empirical Study of Various Dietary Intake Estimation Approaches" This work was presented at the 8th International Workshop on Multimedia Assisted Dietary Management during the 2023 ACM Multimedia conference Paper: dl.acm.org/doi/10.1145/3607828.3617799 Dataset link: www.kaggle.com/nutritionverse/datasets
GENERATIVE AI FOR GOOD: FROM CONCEPT TO PRACTICE
zhlédnutí 64Před 10 měsíci
This is a recorded version of a talk presented by Dr. Yuhao Chen from the VIP Lab at the Big Data & AI Toronto conference on October 19th, 2023
Can't find your paper on arXiv. Can you attach the paper link please?
Im excited for a future where you can create a splat in real time with multiple cameras 😵💫 might even be cool for things like autonomous driving (or instead of security cameras, you mix them into a live splat and have security angels with vr headsets flying over crouds to detect anomalies)
Heck, military applications are also obvious here, but I don't like them :P might even be able to predict movement when out of line of sight? Like a deep 4D kalman filter @@ hoho. We are so fucked
For the final plots showing PSNR vs training time, have you considered plotting on a log scale? It appears the main benefit is the reduced time required to reach a given PSNR. These close asymptotic tails seem to obscure this result. Also, using hours rather than seconds might be clearer 😅. Great work and Cool paper!
Great work! Any plans to release the code for this?
I hope so, code please? :) I would love to attempt something with this as well, have an idea for an app/experience that will require me to better understand and be able to implement this tools. Thanks for the demonstration!
How much taxpayer money did they swindle to come up with his mouse trap
Looking: gets far enough 2 get in2 tha (mysterious) pituitary gland. "Yeaaaaayyyy..." sign mee up. I want 2 B an "early adaptor"
*Promosm* 🤩