Pranoy

cnn-lstm. CNN LSTM architecture implemented in Pytorch for Video Classification

head-detection-using-yolo. Detection of head using YOLO

End-to-End-Trainable-Multi-Instance-Pose-Estimation-with-Transformers. pose-detection-transformer

text-to-video. Experimental text-to-video generation

scene-graph-vit. Implementation of the Paper Scene-Graph ViT

large-scale-visual-relationship-understanding. Visual Relationship Understanding

lstm-object-detection. Object Detection using LSTM-SSD

ml-from-scratch. Python

attention-models. Simplified Implementation of SOTA Deep Learning Papers in Pytorch

dynamic-Pix2Pix. Dynamic-Pix2Pix: Noise Injected cGAN for Modeling Input and Target Domain Joint Distributions with Limited Training Data

pix2seq. Python

TexTok. Python

D2iT. Python

token-shuffle. Python

open-sim. A Tool to convert human videos doing actions (eg : cooking) to realistic robotic videos + actions for training/fine tuning Foundation VLM/VAM models