💣🔥#Unity acquires Ziva Dynamics 💣🔥

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Real-time digital humans
✅A mix of #ML & biomechanics
✅Complex anatomical simulation
✅30 terabytes of 4D data
✅72,000 trained shapes

More: https://www.linkedin.com/posts/visionarynet_unity-metaverse-ml-activity-6891413170834030592-Rr9p

🧁🧁The definitive (recently updated) collection of neural pedestrian detectors🧁🧁

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Cascade Mask-R-CNN
✅Faster R-CNN
✅RetinaNet(Guided Anchoring)
✅Hybrid Task Cascade, MGAN, CSP
✅MMDetection/SwinTransformer
✅Code under Apache License 2.0

More: https://bit.ly/3KArsA1

🧃🧃Training ImageNet in minutes with FFCV🧃🧃

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Work with any existing code
✅Pre-fetching, caching, transfer
✅Fused-and-compiled data proc.
✅Multiple models per GPU
✅Tools for image handling

More: https://bit.ly/3IAZHW9

🎨RePaint: new SOTA in inpainting🎨

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅RePaint via DDPM
✅Suitable with severe corruption
✅Pretrained DDPM as prior
✅SOTA vs Autoregressive/GAN

More: https://bit.ly/3AAk8jm

🐠🐠Re-inventing the animation🐠🐠

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅S2PR: engineers + artists
✅Style2Paint: a coloring software
✅Style2Paints -> “SePa”
✅Source code under Apache

More: https://bit.ly/3rPZPu4

💽 ManyDepth: adaptive 3D-depth 💽

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅SSL-training, monocular only
✅No depths or poses needed
✅Adaptive cost volume
✅Handling moving objects
✅Patent Pending😓

More: https://bit.ly/3fZpIlD

🔥The power of Transformers🔥

👉100+ official implementations, papers, github repo and colab of:

01 GPT-Neo 2021
02 Transformer 2017
03 BERT 2018
04 GPT 2018
05 Univ.Transformer 2018
06 T-D 2018
07 GPT-2 2019
08 T5 2019
09 BART 2019
10 XLNet 2019
11...

👉The full list: https://github.com/ashishpatel26/Treasure-of-Transformers

⚕️Transformers in Medical ⚕️

👉100+ papers, implementations and code of Transformers in medical imaging.

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Medical Image Segmentation
✅Medical Image Classification
✅Medical Image Reconstruction
✅Medical Image Registration
✅Medical Image Synthesis
✅Medical Image Detection
✅Clinical Report Generation
✅Survey and more..


The full list: https://bit.ly/3ILzswl

🪑#3D with Transformers🪑

👉ShapeFormer, transformer network for incomplete input

✅VQDIF representation for 3D
✅Transformer-based model
✅Partial input -> completed shape
✅ConvONet/Taming-transf/DCTransf.
✅SOTA for #3D shape completion

More: https://bit.ly/3s0D2f1

📱YOLO5 real-time logo detector📱

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Based on YOLOv5 family
✅Google Colab + Azure
✅90k pics, training: 2 weeks
✅Pretrained models/code
✅GNU License v3.0

More: https://bit.ly/3r8Qoa7

🦒RelTR: #AI scene-graphs🦒

👉One-stage method for object relationship via visual appearance only.

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅RelTR ,end-to-end framework
✅Classifying dense relationships
✅Scene graphs on appearance only
✅No combining entities & labeling
✅Superior performance, faster

More: https://bit.ly/3r8k86Y

🥶SOTA in crowd analysis is INSANE🥶

👉Tencent unveils P2PNet to predict heads in images

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Pure point counting/detecting
✅Normalized Average Precision
✅VGG16-like architecture
✅Simultaneous point/confidence
✅License: only academic

More: https://bit.ly/33UjoK0

❄️OLSO: Transformers Optimization❄️

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Automagical with Hugging Face
✅GPU-based optimizations
✅Easily installation with pip
✅Apache License 2.0

More: https://bit.ly/3r8wY58