Computer Science and Programming
Channel specialized for advanced topics of: * Artificial intelligence, * Machine Learning, * Deep Learning, * Computer Vision, * Data Science * Python For Ads: @otchebuch & @cobbl, https://telega.io/c/computer_science_and_programming
Ko'proq ko'rsatishNetwork:Computer Science and ProgrammingMamlakat belgilanmaganIngliz1 947Texnologiyalar & Aralashmalar347
160 930
Obunachilar
+9624 soatlar
+4047 kunlar
+2 14530 kunlar
Postlar arxiv
00:31
Video unavailableShow in Telegram
3D-aware Conditional Image Synthesis (pix2pix3D)
Pix2pix3D synthesizes 3D objects (neural fields) given a 2D label map, such as a segmentation or edge map
Github:
https://github.com/dunbar12138/pix2pix3D
Paper:
https://arxiv.org/abs/2302.08509
Project:
https://www.cs.cmu.edu/~pix2pix3D/
Datasets:
CelebAMask , AFHQ-Cat-Seg , Shapenet-Car-Edge
π@computer_science_and_programming
123.mp46.07 MB
π 184π 6
Photo unavailableShow in Telegram
YOWOv2: A Stronger yet Efficient Multi-level Detection Framework for Real-time Spatio-temporal Action Detection
SPATIO-temporal action detection (STAD) aims to detect action instances in the current frame, which it has been widely
applied, such as video surveillance and somatosensory game.
Paper:
https://arxiv.org/pdf/2302.06848.pdf
Github:
https://github.com/yjh0410/YOWOv2
Dataset:
https://drive.google.com/file/d/1Dwh90pRi7uGkH5qLRjQIFiEmMJrAog5J/view?usp=sharing
π@computer_science_and_programming
π 127π 4
01:19
Video unavailableShow in Telegram
Gen-1: The Next Step Forward for Generative AI
Use words and images to generate new videos out of existing
Introducing Gen-1: a new AI model that uses language and images to generate new videos out of existing ones.
https://research.runwayml.com/gen1
βοΈ Project:
https://research.runwayml.com/gen1
β
Paper:
https://arxiv.org/abs/2302.03011
πRequest form:
https://docs.google.com/forms/d/e/1FAIpQLSfU0O_i1dym30hEI33teAvCRQ1i8UrGgXd4BPrvBWaOnDgs9g/viewform
π@computer_science_and_programming
ssstwitter.com_1676283208092.mp48.47 MB
π 150π 6
Audio AI Timeline
Here we will keep track of the latest AI models for audio generation, starting in 2023!
βͺοΈSingSong: Generating musical accompaniments from singing
- Paper
βͺοΈAudioLDM: Text-to-Audio Generation with Latent Diffusion Models
- Paper
- Code
βͺοΈMoΓ»sai: Text-to-Music Generation with Long-Context Latent Diffusion
- Paper
- Code
βͺοΈMake-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models
- Paper
βͺοΈNoise2Music
βͺοΈRAVE2
- Paper
- Code
βͺοΈMusicLM: Generating Music From Text
- Paper
βͺοΈMsanii: High Fidelity Music Synthesis on a Shoestring Budget
- Paper
- Code
- HuggingFace
βͺοΈArchiSound: Audio Generation with Diffusion
- Paper
- Code
βͺοΈVALL-E: Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers
- Paper
π@computer_science_and_programming
auto-music-.jpg1.79 KB
π 164π 4
π Link:- https://apitester.org
A fully free mobile API client for interacting with APIs straight from your phone. Doesn't it sound fantastic?
API Tester allows you to connect to whatever type of API you're working with, including REST, gRPC, SOAP, and GraphQL. Constructing HTTP requests with parameters, auth details, and body data requires only a few steps with a simple and optimized UI. You can also create WebSocket connections, import collections, and use global variables.
API Tester was developed by a team of enthusiasts who feel that powerful apps simplifying work is the key to progress. The app is constantly updated to ensure that you have all of the top-tier features. Try it out for yourself, rate and review on the App Store and Google Play.
Cut and Learn for Unsupervised Object Detection and Instance Segmentation
Cut-and-LEaRn (CutLER) is a simple approach for training object detection and instance segmentation models without human annotations. It outperforms previous SOTA by 2.7 times for AP50 and 2.6 times for AR on 11 benchmarks.
Paper:
https://arxiv.org/pdf/2301.11320.pdf
Github:
https://github.com/facebookresearch/CutLER
Demo:
https://colab.research.google.com/drive/1NgEyFHvOfuA2MZZnfNPWg1w5gSr3HOBb?usp=sharing
π@computer_science_and_programming
image_2023-01-27_12-19-16.png10.12 KB
π 97π 1
00:09
Video unavailableShow in Telegram
GLIGEN: Open-Set Grounded Text-to-Image Generation
GLIGEN (Grounded-Language-to-Image Generation) a novel approach that builds upon and extends the functionality of existing pre-trained text-to-image diffusion models by enabling them to also be conditioned on grounding inputs.
Project page:
https://gligen.github.io/
Paper:
https://arxiv.org/abs/2301.07093
Github (coming soon):
https://github.com/gligen/GLIGEN
Demo:
https://huggingface.co/spaces/gligen/demo
π@computer_science_and_programming
same_box.gif.mp40.54 KB
π 106π 4
00:16
Video unavailableShow in Telegram
Box2Mask: Box-supervised Instance Segmentation via Level-set Evolution
BoxInstSeg is a toolbox that aims to provide state-of-the-art box-supervised instance segmentation algorithms. It supports instance segmentation with only box annotations.
Github:
https://github.com/LiWentomng/BoxInstSeg
Paper:
https://arxiv.org/pdf/2212.01579.pdf
boxInstSeg.mp49.33 MB
π 110π 6
01:01
Video unavailableShow in Telegram
YOLOv8 is the newest state-of-the-art YOLO model that can be used for object detection, image classification, and instance segmentation tasks. YOLOv8 includes numerous architectural and developer experience changes and improvements over YOLOv5.
Code:
https://github.com/ultralytics/ultralytics
What's New in YOLOv8 ?
https://blog.roboflow.com/whats-new-in-yolov8/
Yolov8 Instance Segmentation (ONNX):
https://github.com/ibaiGorordo/ONNX-YOLOv8-Instance-Segmentation
ssstwitter.com_1673507204305.mp410.58 MB
π 157π 5
Photo unavailableShow in Telegram
MIT Introduction to Deep Learning - 2023 Starting soon! MIT Intro to DL is one of the most concise AI courses on the web that cover basic deep learning techniques, architectures, and applications. 2023 lectures are starting in just one day, Jan 9th!
http://introtodeeplearning.com
MIT Introduction to Deep Learning The 2022 lectures can be found here:
https://m.youtube.com/playlist?list=PLtBw6njQRU-rwp5__7C0oIVt26ZgjG9NI
π 153π 12
PACO: Parts and Attributes of Common Objects
Sometimes object detection is not enough and you need more detail about object. Especially, when parts of objects is matters in your task. Then this dataset is for you from Facebook research team.
PACO is a detection dataset that goes beyond traditional object boxes and masks and provides richer annotations such as part masks and attributes. It spans 75 object categories, 456 object-part categories and 55 attributes across image (LVIS) and video (Ego4D) datasets.
Paper:
https://arxiv.org/pdf/2301.01795.pdf
Github:
https://github.com/facebookresearch/paco
Visualization:
https://github.com/facebookresearch/paco/tree/main/notebooks
teaser.png1.39 MB
π 95π 5
Happy New Year!
In the new 2023 year, we wish a rapid increase in subscribers, high posts reach, high-quality active audience and, of course, happiness and health.
A traditional present from us is a New Year card with your channel's this year results.
See you in 2023, from TGSTAT team
stats.jpg2.27 KB
π 169
Accurate and Efficient Stereo Matching via Attention Concatenation Volume
Stereo Depth Estimation
Paper:
https://arxiv.org/pdf/2209.12699.pdf
Github:
https://github.com/gangweiX/Fast-ACVNet
Demo:
https://www.youtube.com/watch?v=az4Z3dp72Zw
ONNX:
ONNX-FastACVNet-Stereo-Depth-Estimation
@computer_science_and_programming
fastacvnet_malaga_urban.gif12.24 MB
π 99π 4
00:14
Video unavailableShow in Telegram
DeepLSD: Line Segment Detection and Refinement with Deep Image Gradients
DeepLSD is a generic line detector that combines the robustness of deep learning with the accuracy of handcrafted detectors. It can be used to extract generic line segments from images in-the-wild, and is suitable for any task requiring high precision, such as homography estimation, visual localization, and 3D reconstruction. By predicting a line distance and angle fields, it can furthermore refine any existing line segments through an optimization
Paper:
https://arxiv.org/abs/2212.07766v1
Github:
https://github.com/cvg/deeplsd
Dataset:
https://paperswithcode.com/dataset/hpatches
ml.mp48.56 KB
β Message was hidden by channel owner
DiffusionInst: Diffusion Model for Instance Segmentation
* DiffusionInst is the first work of diffusion model for instance segmentation
Github:
https://github.com/chenhaoxing/DiffusionInst
Paper:
https://arxiv.org/abs/2212.02773v2
Getting started:
https://github.com/chenhaoxing/DiffusionInst/blob/main/GETTING_STARTED.md
Dataset:
https://paperswithcode.com/dataset/lvis
image_2022-12-13_18-55-00.png1.76 MB
Automatically find and fix errors in any ML datasets with cleanlab
This data-centric AI package facilitates machine learning with messy, real-world data by providing clean labels during training.
Github:
https://github.com/cleanlab/cleanlab
@computer_science_and_programming
Docs:
https://docs.cleanlab.ai/stable/index.html
Examples:
https://github.com/cleanlab/examples
Paper:
https://arxiv.org/abs/2211.13895v1
SSL4EO-S12: A Large-Scale Multi-Modal, Multi-Temporal Dataset for Self-Supervised Learning in Earth Observation
The dataset consists of unlabeled patch triplets from 251079 locations across the globe, each patch covering 2640mx2640m and including 4 seasonal time stamps.
Github:
https://github.com/zhu-xlab/ssl4eo-s12
Paper:
https://arxiv.org/abs/2211.07044v1
Dataset:
https://mediatum.ub.tum.de/1660427
@computer_science_and_programming
image_2022-11-16_12-40-42.png4.85 MB
You don't need to spend several $ππ¬π¬π¬π to learn Data Science.β
Stanford University, Harvard University & Massachusetts Institute of Technology is providing free courses.π₯
Here's 8 free Courses that'll teach you better than the paid ones.
1. CS50βs Introduction to Artificial Intelligence with Python (Harvard)
https://lnkd.in/d9CkkfGK
2. Data Science: Machine Learning (Harvard)
https://lnkd.in/dQ7zkCv9
3. Artificial Intelligence (MIT)
https://lnkd.in/dG5BCPen
4. Introduction to Computational Thinking and Data Science (MIT)
https://lnkd.in/ddm5Ckk9
5. Machine Learning (MIT)
https://lnkd.in/dJEjStCw
6. Matrix Methods in Data Analysis, Signal Processing, and Machine Learning (MIT)
https://lnkd.in/dkpyt6qr
7. Statistical Learning (Stanford)
https://lnkd.in/dymn4hbD
8. Mining Massive Data Sets (Stanford)
πhttps://lnkd.in/d2uf-FkB
00:11
Video unavailableShow in Telegram
Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild
Paper:
https://arxiv.org/pdf/2207.10660.pdf
Github:
https://github.com/facebookresearch/omni3d
Project page:
https://garrickbrazil.com/omni3d/
@computer_science_and_programming
generalization_demo.gif.mp42.11 KB
VToonify: Controllable High-Resolution Portrait Video Style Transfer
Github:
https://github.com/williamyang1991/vtoonify
Colab code example
https://colab.research.google.com/github/williamyang1991/VToonify/blob/master/notebooks/inference_playground.ipynb
Paper:
https://arxiv.org/pdf/2209.11224.pdf
Dataset:
https://paperswithcode.com/dataset/faceforensics-1
Video explanation:
https://www.youtube.com/watch?v=0_OmVhDgYuY
123.jpg3.55 KB
00:10
Video unavailableShow in Telegram
VToonify: Controllable High-Resolution Portrait Video Style Transfer
123.mp41.54 MB
Photo unavailableShow in Telegram
Resources for performing deep learning on satellite imagery:
- Techniques
- Datasets
- ML best Practice
- Courses
and more
Harvard CS109A #DataScience course materials β huge collection free & open!
1. Lecture notes
2. R code, #Python notebooks
3. Lab material
4. Advanced sections
and more ...
https://harvard-iacs.github.io/2019-CS109A/pages/materials.html
@computer_science_and_programming
00:26
Video unavailableShow in Telegram
UFO: segmentation 140+ FPS
πUnified Transformer Framework for Co-Segmentation, Co-Saliency & Salient Object Detection. All in one!
ππ’π π‘π₯π’π π‘ππ¬:
β
Unified framework for co-segmentation
β
Co-segmentation, co-saliency, saliency
β
Block for long-range dependencies
β
Able to reach for 140 FPS in inference
β
The new SOTA on multiple datasets
Paper:
https://arxiv.org/pdf/2203.04708v2.pdf
Code:
https://github.com/suyukun666/UFO
ezgif-4-fb03f1ac86.mp43.57 MB
Photo unavailableShow in Telegram
Weakly Supervised Object Localization via Transformer with Implicit Spatial Calibration
learnable parameter to dynamically adjust the semantic correlations and spatial context intensities for effective information propagation.
Github: https://github.com/164140757/scm
Paper: https://arxiv.org/abs/2207.10447v1
Dataset: https://paperswithcode.com/dataset/cub-200-2011
π Instance Shadow Detection with A Single-Stage Detector
Deep framework, and an evaluation metric to approach this new task.
Github: https://github.com/stevewongv/InstanceShadowDetection
Instance Shadow Detection: https://github.com/stevewongv/SSIS
Video: https://www.youtube.com/watch?v=p0b_2SsFypw
Colab: https://colab.research.google.com/drive/1y9UpS5uA1YuoMyvYVzcKL4ltA_FDu_x0?usp=sharing
Paper: https://arxiv.org/abs/2207.04614v1
Datasets: https://paperswithcode.com/dataset/soba
@computer_science_and_programming
Prosody Cloning in Zero-Shot Multispeaker Text-to-Speech
IMS Toucan is a toolkit for teaching, training and using state-of-the-art Speech Synthesis models.
Github: https://github.com/DigitalPhonetics/IMS-Toucan
https://github.com/rballester/tntorch
Pre-Generated Audios: https://multilingualtoucan.github.io/
Cloning prosody across speakers: https://toucanprosodycloningdemo.github.io/
Interactive Demo: https://huggingface.co/spaces/Flux9665/IMS-Toucan
Paper: https://arxiv.org/abs/2206.12229v1
@computer_science_and_programming
Photo unavailableShow in Telegram
CVPR 2022 open access
https://openaccess.thecvf.com/CVPR2022?day=2022-06-21
Photo unavailableShow in Telegram
MIT, Introduction to Deep Learning, 2022 Lecture series
Website:
http://introtodeeplearning.com/
Lecture:
https://www.youtube.com/watch?v=7sB052Pz0sQ&list=PLtBw6njQRU-rwp5__7C0oIVt26ZgjG9NI
Photo unavailableShow in Telegram
Squeezeformer: An Efficient Transformer for Automatic Speech Recognition
Github: https://github.com/kssteven418/squeezeformer
Paper: https://arxiv.org/abs/2206.00888v1
Dataset: https://paperswithcode.com/dataset/librispeech
00:08
Video unavailableShow in Telegram
AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition
Github: https://github.com/ShoufaChen/AdaptFormer
Paper: https://arxiv.org/abs/2205.13535v1
Dataset: https://paperswithcode.com/dataset/something-something-v2
3.90 KB
RefineMask: Towards High-Quality Instance Segmentation
with Fine-Grained Features (CVPR 2021)
Paper:
https://openaccess.thecvf.com/content/CVPR2021/papers/Zhang_RefineMask_Towards_High-Quality_Instance_Segmentation_With_Fine-Grained_Features_CVPR_2021_paper.pdf
Source:
https://github.com/zhanggang001/RefineMask
@computer_science_and_programming
Photo unavailableShow in Telegram
π§ Focal Sparse Convolutional Networks for 3D Object Detection (CVPR 2022, Oral)
Github: https://github.com/dvlab-research/focalsconv
Paper: https://arxiv.org/abs/2204.12463
Dataset: https://paperswithcode.com/dataset/nuscenes
00:07
Video unavailableShow in Telegram
NAFSSR: Stereo Image Super-Resolution Using NAFNet
Github: https://github.com/megvii-research/NAFNet
Paper: https://arxiv.org/abs/2204.08714v1
Demo: https://colab.research.google.com/drive/1dkO5AyktmBoWwxBwoKFUurIDn0m4qDXT?usp=sharing
Dataset: https://paperswithcode.com/dataset/kitti
deblur.gif.mp40.48 KB
Photo unavailableShow in Telegram
π¬ A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolution
Github: https://github.com/mjq11302010044/tatt
Paper: https://arxiv.org/abs/2203.09388v2
Dataset: https://deepchecks.com/blog/
Reading suggestions to keep you up-to-date with the latest and classic breakthroughs in AI and Data Science.
https://towardsdatascience.com/ai-papers-to-read-in-2022-c6edd4302247
Boshqa reja tanlang
Joriy rejangiz faqat 5 ta kanal uchun analitika imkoniyatini beradi. Ko'proq olish uchun, iltimos, boshqa reja tanlang.