lianglili Goto Github PK

-

基于多特征点的视频拼接

1-dualvgr-videoqa-0.39

Implementation for the journal paper "DualVGR: A Dual-Visual Graph Reasoning Unit for Video Question Answering" (Jianyu et al., IEEE Transactions on Multimedia (TMM. 2021)

1-video_features_extractor

Python implementation of extraction of several visual features representations from videos

2-video-feature-extraction

feature extraction for video captioning

2d-tan

AAAI‘20 - Learning 2D Temporal Localization Networks for Moment Localization with Natural Language

2s-agcn

Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition in CVPR19

3-just-ask-0.463

[TPAMI Special Issue on ICCV 2021 Best Papers, Oral] Just Ask: Learning to Answer Questions from Millions of Narrated Videos

3-video-feature-extraction

Scripts for feature extraction of video using opencv & pytorch

4-all-in-one-0.483

[Arxiv2022] All in One: Exploring Unified Video-Language Pre-training

4-video-feature-extraction-tool

video feature extraction tool

5-video-feature-extraction

This repo is based on pytorch-i3d.

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"

actionformer_release

Code release for ActionFormer (ECCV 2022)

activitynet

This repository is intended to host tools and demos for ActivityNet

agqa_baselines_code

alexnet

ImageNet Classification with Deep Convolutional Neural Networks

am-gcn

AM-GCN: Adaptive Multi-channel Graph Convolutional Networks

android-architecture

A collection of samples to discuss and showcase different architectural tools and patterns for Android apps.

androidarchitecturecollection

安卓架构文章合集（a collection of android Architecture）

anetqa-code

ant-learn-recsys

推荐系统从入门到实战

arctic-capgen-vid

automatic video description generation with GPU training

articulated-animation

Code for Motion Representations for Articulated Animation paper

asr_theory

语音识别理论，论文和PPT

asrt_speechrecognition

A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统，使用CNN和CTC实现

attention-augmented-conv2d

Implementing Attention Augmented Convolutional Networks using Pytorch

attention_is_all_you_need

Transformer of "Attention Is All You Need" (Vaswani et al. 2017) by Chainer.

audio_numbers_recognition

autosparql

Warning: Not working at the moment. Maintainer on parental leave. AutoSPARQL allows to create SPARQL queries over RDF knowledge bases from natural language with low effort.