li-xirong Goto Github PK

avs

Ad-hoc Video Search

cmrf

Cross-Media Reference Fusion

coco-cn

Enriching MS-COCO with Chinese sentences and tags for cross-lingual multimedia tasks

cross-lingual-cap

Cross-lingual image captioning

dong03.github.io

features

a python lib for image feature extraction

flickr8kcn

A bilingual dataset for image captioning

fundus10k

A color fundus image dataset for laser scar detection and other tasks related to fundus image analysis

hierse

Zero-shot image tagging by hierarchical semantic embedding

image2label

SVM based image concept recognition

jingwei

A framework for evaluating image tag assignment, tag refinement and tag-based image retrieval

lectures

demo code for lectures

li-xirong.github.io

mmc-amd

Multi-modal categorization of Age-related Macular Degeneration (4 classes: normal, dry AMD, pcv, wet AMD)

mvss-net

code for Image Manipulation Detection by Multi-View Multi-Scale Supervision

ouzor.github.com

Ouzor homepage

retinal-disease-recognition

sea

SEA: Sentence Encoder Assembly for Video Retrieval by Textual Queries

simpleknn

Find k nearest neighbors by an exhaustive search, used for content-based image retrieval

tagrel

tag relevance learning for social image tagging and retrieval

test

ude

Unsupervised domain expansion for visual categorization

video-retrieval

Deep Learning for Video Retrieval by Natural Language

vtt-basic

video-to-text matching as course project

w2vvpp

W2VV++: A fully deep learning solution for ad-hoc video search

wordmodel

train linear classifier per word using the Jingwei framework