v-user1098new Goto Github PK

action-recognition-visual-attention

Action recognition using soft attention based deep recurrent neural networks

action_recognition_using_visual_attention

TensorFlow Implementation of "Action Recognition using Visual Attention"

adl_vqa_tensorflow2

Project Submission for Applied Deep Learning - Spring 2019

ads2018

cyberagent team's implementation for Advertisement VQA challenge

adversarial-vqa

ampycure

Flask server for detection of Parkinson's disease, Autism and Depression from voice

artvqa

AQUA dataset and VIKING model for the task of Art Visual Question Answering

asd-diagnet

asd-ml-api

This project has 3 goals: To find out the best machine learning pipeline for predicting ASD cases using genetic algorithms, via the TPOT library. (Classification Problem) Compare the accuracy of the accuracy of the determined pipeline, with a standard Naive-Bayes classifier. Saving the classifier as an external file, and use this file in a Flask API to make predictions in the cloud.

attention-based-vqa-model

attention-on-attention-for-vqa

Visual Question Answering Project with state of the art single Model performance.

attention_knowledge_vqa

vqa drived by bottom-up and top-down attention and knowledge

autism-detection-in-children-using-facial-images

Our aim is to develop a binary classifier for discriminating the two classes of facial image . We have to train the classifier that can predict the class of participants into autistic (1) and non-autistic (0) using CNN classifier of machine learning .

autismdetection_transfer_learning

detect autism from facial image, using deep learning. Network used, CNN and MLP with RESNET50

automatic-image-captioning-using-cnn-lstm-deep-neural-networks-and-flask

Image caption generation has emerged as a challenging and important research area following ad-vances in statistical language modelling and image recognition. The generation of captions from images has various practical benefits, ranging from aiding the visually impaired, to enabling the automatic and cost-saving labelling of the millions of images uploaded to the Internet every day. The field also brings together state-of-the-art models in Natural Language Processing and Computer Vision, two of the major fields in Artificial Intelligence. In this model, we has used CNN and LSTM to generate captions for the images and deployed our model using Flask.

basic_vqa

Pytorch VQA : Visual Question Answering (https://arxiv.org/pdf/1505.00468.pdf)

bottom-up-attention

Bottom-up attention model for image captioning and VQA, based on Faster R-CNN and Visual Genome

bottom-up-attention-vqa

An efficient PyTorch implementation of the winning entry of the 2017 VQA Challenge.

cbvr

A repo for Content Based Video Retrieval (CBVR) system.

ci2v

compare an image to every frame of a video

cnn-lstm-caption-generator

A Tensorflow implementation of CNN-LSTM image caption generator architecture that achieves close to state-of-the-art results on the MSCOCO dataset.

coco-caption

content-based-video-retrieval

A tool to search inside videos

content-based-video-retrieval-code

Undergraduate Dissertation: Content-based video retrieval prototype for movies written in Python using OpenCV.

contentbasedvideoretrieval-matlab

ContentBasedVideoRetrieval-MATLAB

context-aware-image-captioning

Implementation of the the CVPR 2017 paper "Context-aware Captions from Context-agnostic Supervision"

cs594_project_vqa

cs7650-project-vqa

cse3018-content-based-image-and-video-retrieval-lab

Repository containing all the codes created for the lab sessions of CSE3018 Content Based Image and Video Retrieval at VIT University Chennai Campus

cvqa

Visual Query Answering & Editing