KOKO's starred repositories
flops-counter.pytorch
Flops counter for convolutional networks in pytorch framework
ChatGPT-Academic-Prompt
Use ChatGPT for academic writing
CBAM-keras
CBAM implementation on Keras
SimVP-Simpler-yet-Better-Video-Prediction
The official implementation of the CVPR'2022 paper SimVP: Simpler Yet Better Video Prediction.
TensorFlow-Advanced-Segmentation-Models
A Python Library for High-Level Semantic Segmentation Models based on TensorFlow and Keras with pretrained backbones.
KernelWarehouse
The official project website of "KernelWarehouse: Rethinking the Design of Dynamic Convolution" (KW for short, accepted to ICML 2024)
DANet-keras
keras-Dual Attention Network for Scene Segmentation
Convolution_Variants
Reimplementing SOTA convolution variants with Tensorflow 2.0.
Pytorch-Learning
Pytorch Framework learning for deeplearning
TransfomerDownscaling
This includes the code and data used in the paper "Investigating transformer-based models for downscaling near-surface temperature and wind speed".
Spiking-Neural-Network-Image-Restoration
Image restoration using spiking neural networks.
Remote-sensing-principle-and-application
科普总结遥感成像原理,数据处理以及实际应用!
Temporal-Pooling-in-Inflated-3DCNN-for-Weakly-supervised-Video-Anomaly-Detection
Anomaly detection in surveillance videos requires significant attention in feature engineering to discriminate anomaly activity patterns from normal patterns. Keeping this in mind, this paper aims to extract superior quality spatio temporal features from Inflated 3DCNN followed by a temporal pooling strategy to intensify relevant spatio temporal feature in untrimmed anomalous videos. A superior temporal pooling strategy leads to better understanding of temporal dependency through LSTM model, which has become a necessary step for anomaly detection in surveillance videos. Thus, we propose a method consisting of an ideal temporal pooling strategy in inflated 3DCNN feature map along with LSTM model for temporal dependency encoding for weakly-supervised anomaly detection task. Our method is validated on a large scale video anomaly detection dataset, namely UCF-crime, resulting competitive performance in anomaly detection task with recent state-of-the-art methodologies.
3DCNN-LSTM
Driving code for 3DCNN-LSTM for radar