Computer vision, speech & NLP Videos Recommended on Hacker News (93)
Computer vision, speech & NLP is one of the 150 topics Hacker News readers organize their video recommendations around. These 93 videos each earned real recommendations in real HN threads between 2007 and 2026 — 152 recommendations in total — and they're ranked by how many separate months the community kept coming back to them, not by view count.
Perception and language AI: image recognition, object detection, OCR, speech recognition, text-to-speech, machine translation, natural language processing, face recognition, classical AI and expert systems.
Why HN keeps sending people here — on Bay Area Vision Meeting: Unsupervised Feature Learning and Deep Learning: “he explains very simply how all this works for images and some examples about the audio case.” — an HN commenter, 2012.
Features
Evergreen only
6 mo on HN"Voice Driven Development: Who needs a keyboard anyway?" by Emily Shea
6 mo on HNJPEG DCT, Discrete Cosine Transform (JPEG Pt2)- Computerphile
5 mo on HNFourier Optics used for Optical Pattern Recognition
5 mo on HNLet's build the GPT Tokenizer
4 mo on HNMassive-scale online collaboration | Luis von Ahn
4 mo on HN!!Con 2017: HDR Photography in Microsoft Excel?! by Kevin Chen
4 mo on HNDasher: information-efficient text entry
4 mo on HNLSTM is dead. Long Live Transformers!
4 mo on HNDual Photography
3 mo on HNStealing Baseball Signs with a Phone (Machine Learning)
3 mo on HNGoogle Developers Day US - Theorizing from Data
3 mo on HNPeter Norvig - The Unreasonable Effectiveness of Data
3 mo on HNHow the US Postal Service reads terrible handwriting
3 mo on HNSpeaking Piano - Now with (somewhat decent) captions!
3 mo on HNAI Language Models & Transformers - Computerphile
2 mo on HNBFS-Auto: High Speed Book Scanner at over 250 pages/min
2 mo on HNGeorge Hotz | Programming | Livecoding SLAM | twitchslam | Part1
2 mo on HN[60 fps] The Flying Train, Germany, 1902
2 mo on HNMilitarizing Your Backyard with Python: Computer Vision and the Squirrel Hordes
2 mo on HNDouglas Lenat: Cyc and the Quest to Solve Common Sense Reasoning in AI | Lex Fridman Podcast #221
2 mo on HN"Cursorless: A spoken language for editing code" by Pokey Rule (Strange Loop 2023)
1 mo on HNBurnistoun - Voice Recognition Elevator in Scotland
1 mo on HNHuman Computation
1 mo on HNHigh-Speed Robot Hand
1 mo on HNDeep Visualization Toolbox
1 mo on HNThe Visual Microphone: Passive Recovery of Sound from Video
1 mo on HNImaging at a trillion frames per second | Ramesh Raskar
1 mo on HN[60 fps] A Trip Through Paris, France in late 1890s / Un voyage à travers Paris, 1890
1 mo on HNReveal Invisible Motion With This Clever Video Trick
0 mo on HNEnemy of the state - Freeze,Rotate,Zoom,Focus,Enhance!
0 mo on HNJanken (rock-paper-scissors) Robot with 100% winning rate
0 mo on HNWhy I Don't Watch CSI
0 mo on HNSilicon Valley: Not Hotdog (Season 4 Episode 4 Clip) | HBO
0 mo on HNMicrosoft Vista Speech Recognition Tested - Perl Scripting
0 mo on HNLet's Enhance HD
0 mo on HN