MounirB

c3d-keras

C3D for Keras + TensorFlow

Clustabs

Clustering algorithm of blocks of data

crowd-counting-scnn

This project is an implementation of the crowd counting model proposed in our CVPR 2017 paper - Switching Convolutional Neural Network(SCNN) for Crowd Counting. SCNN is an adaptation of the fully-convolutional neural network and uses an expert CNN that chooses the best crowd density CNN regressor for parts of the scene from a bag of regressors. This helps it tackle intra-scene crowd density variation and obtain SOTA results

Crowd-movements-classification

The classification of crowd movements

crowdcount-cascaded-mtl

Single Image Crowd Counting (CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting)

Crowded-scenes-Ensemble-classification

Ensemble classification of video-recorded crowd movements

Dense-Trajectory

updated for opencv 3

DenseNet

Densely Connected Convolutional Networks, In CVPR 2017 (Best Paper Award).

iDT

improved dense trajectories

keras-applications

Reference implementations of popular deep learning models.

MounirB/Crowd-movements-classification

The classification of crowd movements

MounirB/c3d-keras

C3D for Keras + TensorFlow

MounirB/Clustabs

Clustering algorithm of blocks of data

MounirB/crowd-counting-scnn

This project is an implementation of the crowd counting model proposed in our CVPR 2017 paper - Switching Convolutional Neural Network(SCNN) for Crowd Counting. SCNN is an adaptation of the fully-convolutional neural network and uses an expert CNN that chooses the best crowd density CNN regressor for parts of the scene from a bag of regressors. This helps it tackle intra-scene crowd density variation and obtain SOTA results

MounirB/crowdcount-cascaded-mtl

Single Image Crowd Counting (CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting)

MounirB/Crowded-scenes-Ensemble-classification

Ensemble classification of video-recorded crowd movements

MounirB/Dense-Trajectory

updated for opencv 3

MounirB/DenseNet

Densely Connected Convolutional Networks, In CVPR 2017 (Best Paper Award).

MounirB/iDT

improved dense trajectories

MounirB/keras-applications

Reference implementations of popular deep learning models.

MounirB/keras-frcnn

MounirB/keras-grad-cam

An implementation of Grad-CAM with keras

MounirB/keras-kinetics-i3d

keras implementation of inflated 3d from Quo Vardis paper + weights

MounirB/keras-resnet3d

Implementations of ResNets for volumetric data, including a vanilla resnet in 3D.

MounirB/keras-retinanet

Keras implementation of RetinaNet object detection.

MounirB/keras_frcnn

Keras Implementation of faster-rcnn

MounirB/Mask_RCNN

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

MounirB/MoonProject

MounirB/NuitDeLinfo2019

MounirB/OpenCV-3-x-with-Python-By-Example

published by Packt

MounirB/OpticalFlow-SpeedTest

This is a script which tests the speed of multiple optical flow extraction methods. support both single-thread and multi-thread

MounirB/py-denseflow

Extract TVL1 optical flows in python (multi-process && multi-server)

MounirB/R2Plus1D

R(2+1)D and Mixed-Convolutions for Action Recognition.

MounirB/Realtime_Multi-Person_Pose_Estimation

Code repo for realtime multi-person pose estimation in CVPR'17 (Oral)

MounirB/statis-matlab

Fonctions pour calculer le methode STATIS sur matlab|| Functions for calculate the method STATIS in MatLAB

MounirB/usthb

A sample project to demonstrate git and github

MounirB/vidaug

Effective Video Augmentation Techniques for Training Convolutional Neural Networks