PREDATOR - Tracker that learns and improves
Zdenek Kalal1 HN recommender · recommended in 1 month, 2011-2023
893K views · 15 years ago · demo · dated
A demo of PREDATOR (TLD), a real-time object tracker that learns the appearance of its target and improves while it tracks. The technology was later developed commercially.
HN found it a nifty demo and cites it as a primitive but effective learning tracker that predates modern deep-learning trackers.
20:41Training an unbeatable AI in Trackmania
Yosh
17.7M views • 3 years ago
35:49Breaking The Creepy AI in Police Cameras
Benn Jordan
3.8M views • 1 year ago
![[CVPR'21 WAD] Keynote - Andrej Karpathy, Tesla](https://i.ytimg.com/vi/g6bOwQdCJrc/hq2.jpg)
31:32[CVPR'21 WAD] Keynote - Andrej Karpathy, Tesla
WAD at CVPR
51K views • 5 years ago
1:11:41Lecture 1 | Natural Language Processing with Deep Learning
Stanford University School of Engineering
820K views • 9 years ago
20:39AI Language Models & Transformers - Computerphile
Computerphile
354K views • 7 years ago
5:21Flexible Muscle-Based Locomotion for Bipedal Creatures
Goatstream
1.9M views • 12 years ago
4:09Evolved Virtual Creatures (1994)
karlsims
43K views • 6 years ago
3:57Facebook's Prototype VR Face Tracking Got Even Better
UploadVR
70K views • 7 years ago
3:32Teaching Robots New Behaviors
Toyota Research Institute
88K views • 3 years ago
48:10Bay Area Vision Meeting: Unsupervised Feature Learning and Deep Learning
Google TechTalks
123K views • 15 years ago
57:57Lecture 1 | Introduction to Convolutional Neural Networks for Visual Recognition
Stanford University School of Engineering
2.9M views • 9 years ago
1:19:08CS231n Winter 2016: Lecture1: Introduction and Historical Context
Andrej Karpathy
462K views • 10 years ago
4:17AI Learns Noise Filtering For Photorealistic Videos | Two Minute Papers #215
Two Minute Papers
65K views • 8 years ago
3:31CVPR 2018: Learning to See in the Dark
Chen Chen
190K views • 8 years ago
5:36Automatic Bullseye, MOVING Dartboard
Mark Rober
24.3M views • 9 years ago
1:03:32John Schulman - Reinforcement Learning from Human Feedback: Progress and Challenges
UC Berkeley EECS
88K views • 3 years ago
26:24Militarizing Your Backyard with Python: Computer Vision and the Squirrel Hordes
Next Day Video
261K views • 14 years ago
1:01Janken (rock-paper-scissors) Robot with 100% winning rate
Ishikawa Group Laboratory
4.3M views • 14 years ago
2:25:52The spelled-out intro to neural networks and backpropagation: building micrograd
Andrej Karpathy
4.4M views • 4 years ago
30:09Andrej Karpathy - AI for Full-Self Driving at Tesla
Matroid
374K views • 6 years ago
3 comments from Hacker News
OK, 11 years ago then. This time with some very primitive ML: OpenTLD ▶ this video Was good enough for commercialization link . I think their tech is powering this link
Incorrect. Recognition applications have been able to track objects across disparate frames of video even when obscures from camera view, for at least a decade now [1]. 1. ▶ this video
My friend forwarded me the video demo link for this: ▶ this video Very nifty. I'm looking forward to reading the machine learning code involved in this.