peratham Goto Github PK

vatic.js

vatic.js A pure Javascript video annotation tool

vector-entailment

A suite of representation learning models for sentence embedding, and some tasks to evaluate them on.

verse

Visual Verb Sense Disambiguation

video-caffe

Video-friendly caffe -- comes with a recent version of Caffe (Dec 2016), a video reader, 3D(ND) pooling layer, and an example training script for C3D network and UCF-101 data

video-in-sentences-out

Code for 'Video In Sentences Out', UAI2012

video2text.pytorch

PyTorch implementation of video captioning

video_to_sequence

Implementation of "Sequence to Sequence – Video to Text"

videogan

Generating Videos with Scene Dynamics. NIPS 2016.

videologlabeling

A tool for labeling event logs synchronized with videos.

videovector

Code for video frame embeddings: Learning Temporal Embeddings for Complex Video Analysis, ICCV 2015

visual-concepts

Code for detecting visual concepts in images.

visual-semantic-embedding

Implementation of the image-sentence embedding method described in "Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models"

visual7w-qa-models

Visual7W visual question answering models

visual7w-toolkit

Toolkit for Visual7W visual question answering dataset

visual_genome_python_driver

A python wrapper for the Visual Genome API

visual_turing_test-tutorial

Tutorial for Visual Turing Test (visual question answering, image question answering).

vlfeat

An open library of computer vision algorithms

vpyp

Pitman-Yor processes in python

vqa-mcb

vqa.pytorch

Visual Question Answering in Pytorch

wide-residual-networks

95.8% and 80% on CIFAR-10 and CIFAR-100

wmd

Word Mover's Distance from Matthew J Kusner's paper "From Word Embeddings to Document Distances"

wolfe

Wolfe Language and Engine

word2gauss

Gaussian word embeddings

word2vec

My own comments and modifications to word2vec by Mikolov et al.

word2vec-api

Simple web service providing a word embedding model

word2vec-pride-vis

A hack to replace Pride & Prejudice text with closest word2vec model word, and visualize results.

worker_tracker

Tracks crowd worker's performance over time.

wsd_dbn

wsl

Weakly Supervised Object Localization with Progressive Domain Adaptation (CVPR 2016)