HackerTube
Categories › AI, Machine Learning & Data

Computer vision, speech & NLP Videos Recommended on Hacker News (59)

Computer vision, speech & NLP is one of the 150 topics Hacker News readers organize their video recommendations around. These 59 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.

7 mo on HN

Bay Area Vision Meeting: Unsupervised Feature Learning and Deep Learning

Google TechTalks
Recommended 9× on HN · 2011–2013
6 mo on HN

"Voice Driven Development: Who needs a keyboard anyway?" by Emily Shea

Strange Loop Conference
Recommended 5× on HN · 2020–2023
6 mo on HN

Andrej Karpathy - AI for Full-Self Driving at Tesla

Matroid
Recommended 4× on HN · 2020–2022
5 mo on HN

Tensorflow and deep learning - without a PhD by Martin Görner

Devoxx
Recommended 6× on HN · 2017–2020
6 mo on HN

JPEG DCT, Discrete Cosine Transform (JPEG Pt2)- Computerphile

Computerphile
Recommended 6× on HN · 2015–2026
5 mo on HN

Fourier Optics used for Optical Pattern Recognition

Huygens Optics
Recommended 5× on HN · 2021–2025
5 mo on HN

Let's build the GPT Tokenizer

Andrej Karpathy
Recommended 5× on HN · 2024–2025
4 mo on HN

Massive-scale online collaboration | Luis von Ahn

TED
Recommended 4× on HN · 2012–2022
4 mo on HN

Breaking The Creepy AI in Police Cameras

Benn Jordan
Recommended 6× on HN · 2025–2026
4 mo on HN

!!Con 2017: HDR Photography in Microsoft Excel?! by Kevin Chen

Confreaks
Recommended 4× on HN · 2017–2025
4 mo on HN

Dasher: information-efficient text entry

Google TechTalks
Recommended 2× on HN · 2016–2025
4 mo on HN

LSTM is dead. Long Live Transformers!

Seattle Applied Deep Learning
Recommended 4× on HN · 2020–2023
4 mo on HN

Dual Photography

mm648230
Recommended 4× on HN · 2013–2026
3 mo on HN

Lecture 1 | Natural Language Processing with Deep Learning

Stanford University School of Engineering
Recommended 3× on HN · 2017–2018
3 mo on HN

Stealing Baseball Signs with a Phone (Machine Learning)

Mark Rober
Recommended 3× on HN · 2019–2023
3 mo on HN

[CVPR'21 WAD] Keynote - Andrej Karpathy, Tesla

WAD at CVPR
Recommended 4× on HN · 2021–2023
3 mo on HN

Google Developers Day US - Theorizing from Data

GoogleDeveloperDay
Recommended 3× on HN · 2007–2009
3 mo on HN

Peter Norvig - The Unreasonable Effectiveness of Data

UBC Computer Science
Recommended 3× on HN · 2012–2026
3 mo on HN

3D Gaussian Splatting! - Computerphile

Computerphile
Recommended 3× on HN · 2024–2026
3 mo on HN

How the US Postal Service reads terrible handwriting

Tom Scott
Recommended 4× on HN · 2022–2026
3 mo on HN

Speaking Piano - Now with (somewhat decent) captions!

TheMcphearson
Recommended 3× on HN · 2010–2023
3 mo on HN

AI Language Models & Transformers - Computerphile

Computerphile
Recommended 3× on HN · 2022–2025
2 mo on HN

This AI actually WORKS!!! - NVIDIA RTX Voice

ShortCircuit
Recommended 2× on HN · 2021–2024
2 mo on HN

BFS-Auto: High Speed Book Scanner at over 250 pages/min

Ishikawa Group Laboratory
Recommended 2× on HN · 2018–2024
2 mo on HN

George Hotz | Programming | Livecoding SLAM | twitchslam | Part1

george hotz archive
Recommended 2× on HN · 2018–2022
2 mo on HN

Practical Deep Learning for Coders: Lesson 1

Jeremy Howard
Recommended 2× on HN · 2022–2023
2 mo on HN

[60 fps] The Flying Train, Germany, 1902

Denis Shiryaev
Recommended 2× on HN · 2020–2023
2 mo on HN

Hound Internal Demo

Hound by SoundHound Inc.
Recommended 2× on HN · 2015–2019
2 mo on HN

3-Sweep: Extracting Editable Objects from a Single Photo, SIGGRAPH ASIA 2013

Daniel CohenOr
Recommended 2× on HN · 2013–2024
2 mo on HN

Militarizing Your Backyard with Python: Computer Vision and the Squirrel Hordes

Next Day Video
Recommended 3× on HN · 2014–2023
2 mo on HN

How Google's Self-Driving Car Works

IEEE Spectrum
Recommended 2× on HN · 2012–2016
2 mo on HN

Douglas Lenat: Cyc and the Quest to Solve Common Sense Reasoning in AI | Lex Fridman Podcast #221

Lex Fridman
Recommended 3× on HN · 2021–2023
2 mo on HN

#VoCo. Adobe Audio Manipulator Sneak Peak with Jordan Peele | Adobe Creative Cloud

Adobe Creative Cloud
Recommended 2× on HN · 2016–2024
2 mo on HN

"Cursorless: A spoken language for editing code" by Pokey Rule (Strange Loop 2023)

Strange Loop Conference
Recommended 2× on HN · 2023–2026
2 mo on HN

Glitch Tokens - Computerphile

Computerphile
Recommended 2× on HN · 2023–2023
2 mo on HN

Duolingo -- the next chapter in human computation | Luis von Ahn | TEDxCMU 2011

TEDx Talks
Recommended 2× on HN · 2011–2012

Also discussed on Hacker News (34)

Mentioned in HN threads about computer vision, speech & nlp, though never formally recommended:

Face2Face: Real-time Face Capture and Reenactment of RGB Videos (CVPR 2016 Oral) · Let's Enhance · Google Duplex: A.I. Assistant Calls Local Businesses To Make Appointments · Windows Vista Speech Recognition Tested - Perl Scripting · HP computers are racist · I Gave My Goldfish $50,000 to Trade Stocks · Dickmann's autonomous cars, 1980s · world's best ai vs geoguessr pro · Enemy of the state - Freeze,Rotate,Zoom,Focus,Enhance! · Janken (rock-paper-scissors) Robot with 100% winning rate · Scottish Elevator - Voice Recognition - ELEVEN ! · Eulerian Video Magnification · Burnistoun - Voice Recognition Lift · Can GPT-4 translate literature? · What do translators think about GPT? · Virtuo Vivo™ live scanning at IDS 2019 · Silicon Valley: Not Hotdog (Season 4 Episode 4 Clip) | HBO · Human brain mapping and brain decoding. | Jack Gallant | TEDxSanFrancisco · Let's Enhance HD · IIHS Pedestrian Autobrake Tests – Audi, Ford, Hyundai, Kia, Mercedes-Benz, Nissan, Subaru · Introducing Word Lens · A Style-Based Generator Architecture for Generative Adversarial Networks · Blade Runner Enhance Scene · Why I Don't Watch CSI · ATTOL: Autonomous Taxiing, Take-Off and Landing test flight · Fake Obama created using AI video tool - BBC News · Microsoft Vista Speech Recognition Tested - Perl Scripting · Adobe Photoshop CS5: Content-Aware Fill Sneak Peek · Say hello to Project Tango! · Siri Demo by Scott Forstall at Apple Special Event Oct. 4, 2011 · The Voder: 1939, the worlds first electronic voice synthesizer · The Eleventh HOPE (2016): Coding by Voice with Open Source Speech Recognition · ProFORMA: Probabilistic Feature-based On-line Rapid Model Acquisition · Adobe MAX 2011 - Photoshop Image Deblurring sneak