Computer Science and Programming – Telegram
Computer Science and Programming
152K subscribers
690 photos
29 videos
37 files
977 links
Channel specialized for advanced topics of:
* Artificial intelligence,
* Machine Learning,
* Deep Learning,
* Computer Vision,
* Data Science
* Python

Admin: @otchebuch

Memes: @memes_programming

Ads: @Source_Ads,
https://telega.io/c/computer_science
Download Telegram
Dark scene object detection API for detecting 12 common objects in the dark/night images and videos
👍10
Great resource of AI, Machine learning, Deep learning, Computer vision, NLP Projects and Courses with code
👍24
This media is not supported in your browser
VIEW IN TELEGRAM
Synthesizing Light Field From a Single Image with Variable MPI and Two Network Fusion
👍6
DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification
👍10
PVTv2: Improved Baselines with Pyramid Vision Transformer

Classification
Detection
Segmentation
👍11
It's CVPR 2021 time!
👍6
👍6
This media is not supported in your browser
VIEW IN TELEGRAM
From Google and Waymo researchers: The self-/unsupervised revolution is near! Unsupervised optical flow model SMURF improves SOTA by 40% and beats many supervised methods such as PWC-Net and FlowNet2

👉 @computer_science_and_programming
👍91
YOLOX: Exceeding YOLO Series in 2021

Anchor-free version of YOLO series

Won the 1st Place on Streaming
Perception Challenge (Workshop on Autonomous Driving
at CVPR 2021)
👍10
A simpler design but better performance! It aims to bridge the gap between research and industrial communities.

Paper:
https://arxiv.org/pdf/2107.08430v1.pdf

Github:
https://github.com/Megvii-BaseDetection/YOLOX

👉@computer_science_and_programming
👍13
Practical image restoration

Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data

👉@computer_science_and_programming
👍12👨‍💻1
Swin transformer for :
✔️ Object detection
✔️ Image Classification
✔️ Semantic Segmentation
✔️ Video Recognition
👍131
This media is not supported in your browser
VIEW IN TELEGRAM
Now removing, duplicating or enhancing objects in video is more realistic with the assist of AI

"We need to talk about the car in the room."
This paper: what car? 🙈
👍25