⚡️ The best #AI of the week: #deeplearning, #computervision & #NLP free resources from across the internet in one place, every week. ⚡️

💡 Google | Face and Hand tracking in the browser with MediaPipe and TensorFlow: https://lnkd.in/dQRSB7U

💡 Berkeley | Speeding Up Transformer Training and Inference By Increasing Model Size: https://lnkd.in/dV5qZ4S

💡 CVPR-2020 | Zero-shot video classification by end-to-end training of 3D convolutional neural networks: https://lnkd.in/djs98Ew

💡 Google | Connecting Vision and Language with Localized Narratives: https://lnkd.in/dD6hjUq

More: https://www.linkedin.com/feed/update/urn:li:activity:6643790787312140288

⚡️ The best #AI of the week: #deeplearning, #computervision & #NLP free resources from across the internet in one place, every week. ⚡️

💡 MIT | How to make a pizza - Learning a compositional layer-based GAN model: https://lnkd.in/gFaVgnR

More: https://www.linkedin.com/feed/update/urn:li:activity:6645227487855022080

🔥🧨 Microsoft releases an #AI made by Convolutions + Transformers 🔥🧨


Code, paper and more: https://www.linkedin.com/posts/visionarynet_ai-artificialintelligence-machinelearning-activity-6783020475627945984-F8rv

⭐⭐This #AI uses *MIRRORS* to largely improve the 3D human pose reconstruction⭐⭐


Code and paper: https://www.linkedin.com/posts/visionarynet_ai-artificialintelligence-machinelearning-ugcPost-6783719931075723264-PE0z

🌎🌍🌏 An end-to-end #AI framework able to de-render the world's revolutionary artefacts 🌎🌍🌏

More: https://www.linkedin.com/posts/visionarynet_ai-artificialintelligence-machinelearning-activity-6786307882448146432-uKsm

🏆🧢 Make VGG-style ConvNets Great Again 🧢🏆

Pretrained models, code for building the model, training, and the conversion from training-time model to inference-time: https://www.linkedin.com/posts/visionarynet_ai-artificialintelligence-machinelearning-activity-6786931467214745601-hTc6

🙈 Removing tattoos with this #AI project 🙈

More: https://www.linkedin.com/posts/visionarynet_ai-fastai-pytorch-activity-6787791059402469376--bNq/

⚡Adapting a GAN to very few images⚡

Project, paper and code: https://www.linkedin.com/posts/visionarynet_ai-artificialintelligence-machinelearning-activity-6788378892366340096-LPhR

💃 This #AI could be a game-changer in #fashion e-commerce 💃



Paper, project and code: https://linkedin.com/posts/visionarynet_ai-artificialintelligence-machinelearning-activity-6788756245546369024-ASHw

💊This #AI from Facebook AI predicts effective drug combinations for complex diseases faster 💊

More: https://www.linkedin.com/posts/visionarynet_ai-artificialintelligence-machinelearning-activity-6788813800876380160-kJS9

🏃⚡PP-YOLOv2: the novel object detector faster than YOLOv5🏃⚡

Download the model: https://www.linkedin.com/posts/visionarynet_ai-artificialintelligence-machinelearning-activity-6790895297053757440-PK67

🎁From Alibaba Group a high-quality efficient pretraining on ImageNet-21K available for everyone🎁

Find the model: https://www.linkedin.com/posts/visionarynet_ai-artificialintelligence-machinelearning-activity-6791621355054911488-bSpt

🚄From Facebook AI a novel method to create photorealistic human avatars for telepresence🚄



More: https://www.linkedin.com/posts/visionarynet_ai-artificialintelligence-machinelearning-activity-6791995478276931584-raBn

🏃⚡Microsoft releases "LightTrack" a neural architecture search (NAS) to design hyper-efficient object trackers🏃⚡

More: https://www.linkedin.com/posts/visionarynet_ai-artificialintelligence-machinelearning-activity-6793795862993649664-CZvq

🏃⚡Google just released a novel system able to produce realistic composite images for any scene🏃⚡


More: https://www.linkedin.com/posts/visionarynet_deeplearning-ai-artificialintelligence-activity-6794294922867474432-pcW2