resolutions-2019A list of data mining and machine learning papers that I implemented in 2019.
Stars: ✭ 19 (-92.34%)
Transformer-in-TransformerAn Implementation of Transformer in Transformer in TensorFlow for image classification, attention inside local patches
Stars: ✭ 40 (-83.87%)
Two-Stream-CNNTwo Stream CNN implemented in Keras using in skeleton-based action recognition with dataset NTU RGB+D
Stars: ✭ 75 (-69.76%)
Perceiver PytorchImplementation of Perceiver, General Perception with Iterative Attention, in Pytorch
Stars: ✭ 130 (-47.58%)
Pose2vecA Repository for maintaining various human skeleton preprocessing steps in numpy and tensorflow along with tensorflow model to learn pose embeddings.
Stars: ✭ 25 (-89.92%)
Linformer PytorchMy take on a practical implementation of Linformer for Pytorch.
Stars: ✭ 239 (-3.63%)
pose2actionexperiments on classifying actions using poses
Stars: ✭ 24 (-90.32%)
Fed AttAttentive Federated Learning for Private NLM
Stars: ✭ 34 (-86.29%)
pred-rnnPredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs
Stars: ✭ 115 (-53.63%)
MmactionAn open-source toolbox for action understanding based on PyTorch
Stars: ✭ 1,711 (+589.92%)
CrabNetPredict materials properties using only the composition information!
Stars: ✭ 57 (-77.02%)
Isab PytorchAn implementation of (Induced) Set Attention Block, from the Set Transformers paper
Stars: ✭ 21 (-91.53%)
SelfAttentiveImplementation of A Structured Self-attentive Sentence Embedding
Stars: ✭ 107 (-56.85%)
AmassData preparation and loader for AMASS
Stars: ✭ 180 (-27.42%)
Brain-Tumor-SegmentationAttention-Guided Version of 2D UNet for Automatic Brain Tumor Segmentation
Stars: ✭ 125 (-49.6%)
I3d finetuneTensorFlow code for finetuning I3D model on UCF101.
Stars: ✭ 128 (-48.39%)
tfvaegan[ECCV 2020] Official Pytorch implementation for "Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification". SOTA results for ZSL and GZSL
Stars: ✭ 107 (-56.85%)
Text classificationall kinds of text classification models and more with deep learning
Stars: ✭ 7,179 (+2794.76%)
Generative inpaintingDeepFill v1/v2 with Contextual Attention and Gated Convolution, CVPR 2018, and ICCV 2019 Oral
Stars: ✭ 2,659 (+972.18%)
Pytorch GatMy implementation of the original GAT paper (Veličković et al.). I've additionally included the playground.py file for visualizing the Cora dataset, GAT embeddings, an attention mechanism, and entropy histograms. I've supported both Cora (transductive) and PPI (inductive) examples!
Stars: ✭ 908 (+266.13%)
Squeeze-and-Recursion-Temporal-GatesCode for : [Pattern Recognit. Lett. 2021] "Learn to cycle: Time-consistent feature discovery for action recognition" and [IJCNN 2021] "Multi-Temporal Convolutions for Human Action Recognition in Videos".
Stars: ✭ 62 (-75%)
DCAN[AAAI 2020] Code release for "Domain Conditioned Adaptation Network" https://arxiv.org/abs/2005.06717
Stars: ✭ 27 (-89.11%)
Tsn PytorchTemporal Segment Networks (TSN) in PyTorch
Stars: ✭ 895 (+260.89%)
SiGATsource code for signed graph attention networks (ICANN2019) & SDGNN (AAAI2021)
Stars: ✭ 37 (-85.08%)
VipVideo Platform for Action Recognition and Object Detection in Pytorch
Stars: ✭ 175 (-29.44%)
RETRO-pytorchImplementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch
Stars: ✭ 473 (+90.73%)
axial-attentionImplementation of Axial attention - attending to multi-dimensional data efficiently
Stars: ✭ 245 (-1.21%)
rnn-text-classification-tfTensorflow implementation of Attention-based Bidirectional RNN text classification.
Stars: ✭ 26 (-89.52%)
Two Stream Action RecognitionUsing two stream architecture to implement a classic action recognition method on UCF101 dataset
Stars: ✭ 705 (+184.27%)
Ican[BMVC 2018] iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection
Stars: ✭ 225 (-9.27%)
torch-lrcnAn implementation of the LRCN in Torch
Stars: ✭ 85 (-65.73%)
Keras AttentionVisualizing RNNs using the attention mechanism
Stars: ✭ 697 (+181.05%)
En-transformerImplementation of E(n)-Transformer, which extends the ideas of Welling's E(n)-Equivariant Graph Neural Network to attention
Stars: ✭ 131 (-47.18%)
DrlnDensely Residual Laplacian Super-resolution, IEEE Pattern Analysis and Machine Intelligence (TPAMI), 2020
Stars: ✭ 120 (-51.61%)
dgcnnClean & Documented TF2 implementation of "An end-to-end deep learning architecture for graph classification" (M. Zhang et al., 2018).
Stars: ✭ 21 (-91.53%)
conv3d-video-action-recognitionMy experimentation around action recognition in videos. Contains Keras implementation for C3D network based on original paper "Learning Spatiotemporal Features with 3D Convolutional Networks", Tran et al. and it includes video processing pipelines coded using mPyPl package. Model is being benchmarked on popular UCF101 dataset and achieves result…
Stars: ✭ 50 (-79.84%)
Generative Inpainting PytorchA PyTorch reimplementation for paper Generative Image Inpainting with Contextual Attention (https://arxiv.org/abs/1801.07892)
Stars: ✭ 242 (-2.42%)
AoanetCode for paper "Attention on Attention for Image Captioning". ICCV 2019
Stars: ✭ 242 (-2.42%)
Ms G3d[CVPR 2020 Oral] PyTorch implementation of "Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition"
Stars: ✭ 225 (-9.27%)
LightnetplusplusLightNet++: Boosted Light-weighted Networks for Real-time Semantic Segmentation
Stars: ✭ 218 (-12.1%)
StepSTEP: Spatio-Temporal Progressive Learning for Video Action Detection. CVPR'19 (Oral)
Stars: ✭ 196 (-20.97%)
HartHierarchical Attentive Recurrent Tracking
Stars: ✭ 149 (-39.92%)
DeepaffinityProtein-compound affinity prediction through unified RNN-CNN
Stars: ✭ 75 (-69.76%)
Image-CaptionUsing LSTM or Transformer to solve Image Captioning in Pytorch
Stars: ✭ 36 (-85.48%)