Learn about Learning from Unlabeled Videos at #CVPR2019

https://sites.google.com/view/luv2019/home?authuser=0

✴️ @AI_Python_EN

Berkeley/FAIR AI revolution slogans:
- Jitendra Malik: "Supervision is the opium of the AI researcher"
- Alyosha Efros: "The AI revolution will not be supervised"
- Yann LeCun: "self-supervised learning is the cake,

https://www.facebook.com/722677142/posts/10156036317282143/

✴️ @AI_Python_EN

Despite their popularity in media and among amateurs, GANs have quite limited practical application. But this specific result has a huge cultural value.

A neural network was used to recreate the Doom Guy in high-res: https://lnkd.in/eERQ7MJ

✴️ @AI_Python_EN

Group For Who Have a Passion For:

1. Artificial Intelligence
2. Machine Learning
3. Deep Learning
4. Data Science
5. Computer vision
6. Image Processing

https://t.me/DeepLearningML

✴️ @AI_Python_EN

Great to see lots of interest in meta-learning at #CVPR2019 ! Had trouble getting in the room to give my talk. My talk was based on our icmlconf tutorial with Slides, video, references
here: http://sites.google.com/view/icml19metalearning

✴️ @AI_Python_EN

[about] https://medium.com/@jasonphang/deep-neural-networks-improve-radiologists-performance-in-breast-cancer-screening-565eb2bd3c9f

[code] https://github.com/nyukat/breast_cancer_classifier

[preprint] https://arxiv.org/pdf/1903.08297.pdf

[data specs] https://cs.nyu.edu/~kgeras/reports/datav1.0.pdf

[ICML '19] https://aiforsocialgood.github.io/icml2019/acceptedpapers.htm

#AI #radiology #breastcancer

✴️ @AI_Python_EN

A major benefit of self-supervision is we can truly scale and adapt on the fly. It could be 10% behind supervised ImageNet, it would still do better in real life. We show in http://online-objects.github.io that the longer our model looks at objects, the better it understands them.

✴️ @AI_Python_EN

#ACL2019 paper "Self-attentional Models for Lattice Inputs" proposes a method to apply Transformers to graphs encoding ambiguity from an upstream system such as speech recognition. Nice results, and much faster on speech translation benchmarks!
https://arxiv.org/abs/1906.01617

✴️ @AI_Python_EN

Oldies but Goldies: D. Lee et S. Seung, Learning the parts of objects by non-negative matrix factorization, Nature (1999). Lee and Seung proposed the most popular matrix factorization algorithm, which operates by multiplicative updates.
https://en.wikipedia.org/wiki/Non-negative_matrix_factorization

✴️ @AI_Python_EN

A video is now online of our ICML Tutorial on Recent Advances in Population-Based Search for Deep Neural Networks: Quality Diversity, Indirect Encodings, and Open-Ended Algorithms. We hope you find it valuable!

https://www.youtube.com/watch?v=g6HiuEnbwJE&feature=youtu.be
✴️ @AI_Python_EN

AlphaStar: Mastering the Game of StarCraft II

Talk by David Silver: https://slideslive.com/38916905/alphastar-mastering-the-game-of-starcraft-ii

#ArtificialIntelligence #DeepLearning #ReinforcementLearning

✴️ @AI_Python_EN

Best Papers Awards #ICML2019
The Thirty-sixth International Conference on Machine Learning, Long Beach, USA

(1)Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations https://arxiv.org/pdf/1811.12359.pdf
Congratulations to the GoogleAI team of Francesco Locatello, Stefan Bauer, Mario Lucic, Gunnar Rätsch, Sylvain Gelly,Bernhard Schölkopf, Olivier Bachem

(2)Rates of Convergence for Sparse Variational Gaussian Process Regression
https://arxiv.org/pdf/1903.03571.pdf
Kudos to David R. Burt, Carl E. Rasmussen, Mark van der Wilk of University of Cambridge

✴️ @AI_Python_EN

Learning the Depths of Moving People by Watching Frozen People” (http://goo.gle/2x4tEuQ ), recipient of a #CVPR2019 Best Paper Honorable Mention Award. Learn more about the paper at
http://goo.gle/2ZuZtJt

✴️ @AI_Python_EN

Rigorously testing Machine learning models using meta-learning. We show how a Neural Process-based meta-learning formulation allows us to efficiently search for hard examples.
inDeepMind, Interested in adversarial tests and reinforcement learning? We combine meta-learning in a general probabilistic paradigm to detect failures, helping us build robust algorithms. Includes results on recommender systems and control: http://arxiv.org/abs/1903.11907

✴️ @AI_Python_EN

Slides: "Three Challenging Research Avenues (in language and vision)" from my VQA workshop #cvpr2019 talk.
https://yoavartzi.com/slides/2019_06_17_vqa_workshop.pdf
Includes a quick summary of some of our recent vision+language work and resources

✴️ @AI_Python_EN

One-shot Voice Conversion by Separating Speaker and Content Representations with Instance Normalization is accepted to Interspeech 2019.
By combining VAE and adaIN, our model is able to do one-shot VC by a reference source utterance and a target utterance.

✴️ @AI_Python_EN

Text similarity
Are these two sentences similar ?!
1) President greets the press in Chicago
2) Obama speaks in Illinois


— Jaccard
— Cosine
— WMD

#naturallanguageprocessing


https://medium.com/@adriensieg/text-similarities-da019229c894

✴️ @AI_Python_EN

Learn Tensorflow 1: The Hello World of Machine Learning
https://codelabs.developers.google.com/codelabs/tensorflow-lab1-helloworld/#0

Privacy-Preserving Deep Visual Recognition: An Adversarial Learning Framework and A New Dataset

We have recently introduced PA-HMDB51 (https://github.com/htwang14/PA-HMDB51), the very first human action video dataset with potential privacy leak attributes annotated. This dataset is collected and maintained by the VITA group at the CSE department of Texas A&M University.

The dataset contains 592 videos selected from the HMDB51 dataset [2]. For each video, we provide with frame-level annotation of five privacy attributes: skin color, gender, face, nudity, and relationship. The annotations are all provided in JSON format. Visualized examples can be found in the attachment.

The dataset aims to support and promote research on protecting visual privacy information in smart camera-based applications. A manuscript [1] introduces the dataset and related algorithms that we have developed for this topic.

We hope you will find this dataset useful,

Haotao Wang,
Texas A&M University