hjxh Goto Github PK

-

adv-inf

Adversarial Inference for Multi-Sentence Video Descriptions (CVPR 2019)

bmt

Source code for "Bi-modal Transformer for Dense Video Captioning" (BMVC 2020)

bootcamp

c3d-keras

C3D for Keras + TensorFlow

chinese-bert-wwm

Pre-Training with Whole Word Masking for Chinese BERT（中文BERT-wwm系列模型）

community

牛客网 牛客Java高级工程师 - 高薪求职项目课vol.4

community-1

仿照牛客网实现的讨论区。

deeplearning

dense-video-captioning-pytorch

Second-place solution to dense video captioning task in ActivityNet Challenge 2020

extruct-video-feature

Extract video feature from C3D pretrained on Sports-1M and Kinetics

face-alignment

Implementation of paper titled "Facial Landmark Detection by Deep Multi-task Learning" in keras

go-study-index

Go 语言学习资料索引

hifanclass

i3d-feature-extractor

I3D feature extractor

java-interview

Java 面试必会 直通BAT

java-interview-1

「Java面试小抄」一份通向理想互联网公司的面试汇总，包括 Java基础、Java并发、JVM、MySQL、Redis、Spring、MyBatis、Kafka、计算机操作系统、计算机网络、系统设计、分布式、Java 项目实战等

labuladong-fucking-algorithm

learn_neuraltalk

This is a place to learn the details about neutralTalk, comes from Deep Visual-Semantic Alignments for Generating Image Descriptions which is a paper written by Andrej Karpathy.

mmt

Multi-Modal Transformer for Video Retrieval

moviesynopsisassociation

Code for "A Graph-Based Framework to Bridge Movies and Synopses", ICCV2019

msr-vtt-captioning

This repository contains the MSR-VTT video captioning dataset in Hindi.

pytorch-doc-zh

Pytorch 中文文档

video-captioning-transformer

这是一个使用Pytorch实现的视频描述生成深度学习模型。视频描述生成任务就是：输入一个视频，可以输出一句描述整个视频内容的文字。本项目主要目的是帮助视力障碍者欣赏网络视频、感知周围环境，促进“无障碍视频”的发展。

video_features

Extract video features from raw videos using multiple GPUs. We support RAFT and PWC flow frames as well as I3D, R(2+1)D, VGGish, ResNet features.

videosearch

Large-scale video retrieval using image queries.

vmz

VMZ: Model Zoo for Video Modeling