Convolutional recurrent network in pytorch

Unsupervised video summarization with deep reinforcement learning (AAAI'18)

a collection of visualization function

MVCNN on PyTorch

Using RGB Image as Visual Input for Mapless Robot Navigation

Learning to Learn how to Learn: Self-Adaptive Visual Navigation using Meta-Learning (https://arxiv.org/abs/1812.00971)

[CVPR'20] Implementation for the paper "ViewAL: Active Learning with Viewpoint Entropy for Semantic Segmentation"

Deepfake Video Detection Using Convolutional Vision Transformer

Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning implemented in PyTorch

PVRNet: Point-View Relation Neural Network for 3D Shape Recognition (AAAI 2019)

from ModelNet off file to multiview images

PC-NBV: A Point Cloud Based Deep Network for Efficient Next Best View Planning, IROS, 2020

Implementation of our CVPR 2018 Paper (FFNet: Video Fast-Forwarding via Reinforcement Learning)

This project is designed to classify human action recognition datasets with a CNN + LSTM model.

Unofficial implementation of "SSAN: Separable Self-Attention Network for Video Representation Learning (CVPR2021)", in Pytorch

关于python的一些学习和资源

multi-view cnn, Neural-EM, multi view alignment

Learning Representations from Skeletal Self-Similarities for Cross-View Action Recognition