vtt-project Goto Github PK

2nd-year

Video location recognition for Video Turing Test(VTT)

3rd-year

dowhy

DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphical models and potential outcomes frameworks.

drcaptioning

knowledge-graph-builder

A Python based knowledge grpah builder.

knowledge-graph-dataset

This repository contains knowledge-graphs built from various dataset provided by research groups in VTT project.

knowledge-graph-input

Definition of Video Label object format and validator scripts.

knowledge-graph-input-repo-collector

This application collects the input data for knowledge graph from the given Git repositories

knowledge-graph-visualizer

This application visualizes the knowledge graph on the web page.

neuraloperator

Learning in infinite dimension with neural operators.

tome

A method to increase the speed and lower the memory footprint of existing vision transformers.

video-knowledge-builder

An application that builds context-dependent knowledge base with video label dataset.

video-knowledge-collector

A web platform that helps a team of researchers to collect label data for video files.

video_place_recognition

VTT 3rd year

viz-graph

Video Knowledge Builder and Graph Visualizer

vtt-action-recognition

Action Recognition for Visual Turing Test

vtt-char-identify

vtt-example-video-label-data

An example for a repository that contains label data for video files.

vtt-sound-event-detection

vtt-swrc-2020-knowledge

카이스트 시맨틱웹첨단연구센터(SWRC)의 VTT 프로젝트 세계지식(인물간 관계) 데이터입니다.

vtt-triple-data-jsonl

vtt_3year_friends_esf_annotation

vtt_tracking

VTT_TRACKING

vtt_vid_emotion

Video Emotion Recognition (2019)