kiradiso Goto Github PK

acar-net

Actor-Context-Actor Relation Network for Spatio-temporal Action Localization

actiongenome

A video database bridging human actions and human-object relationships

corrected-ucf101-annots

cpnet

Learning Video Representations from Correspondence Proposals (CVPR 2019 Oral)

eada

The code for EADA, the data can be downloaded in https://github.com/jindongwang/transferlearning/blob/master/doc/dataset.md

interview-notes

包含机器学习、深度学习、图像处理、c++等视觉算法岗面试必备基础知识

kiradiso.github.io

mega.pytorch

Memory Enhanced Global-Local Aggregation for Video Object Detection, CVPR2020

mmaction

mmdetection

OpenMMLab Detection Toolbox and Benchmark

mmtracking

My experiment on mmtracking

mssnet

KSSNet: Multi-Label Classification with Label Graph Superimposing

pi-rec

:fire: PI-REC: Progressive Image Reconstruction Network With Edge and Color Domain. :fire: 图像翻译，条件GAN，AI绘画

slowfast

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

something_else

Code repository for the paper: 'Something-Else: Compositional Action Recognition with Spatial-Temporal Interaction Networks'

timeception

Implementation of the paper: Timeception for Complex Action Recognition. Accepted as Oral Presentation at CVPR 2019

yowo

You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization