A pytorch implementation of the CVPR2021 paper "VSPW: A Large-scale Dataset for Video Scene Parsing in the Wild"

Last update: Nov 29, 2022

Related tags

Deep Learning CVPR2021_VSPW_Implement

Overview

VSPW: A Large-scale Dataset for Video Scene Parsing in the Wild

A pytorch implementation of the CVPR2021 paper "VSPW: A Large-scale Dataset for Video Scene Parsing in the Wild"

Preparation

Download VSPW dataset

The VSPW dataset with extracted frames and masks is available here. Now you can directly download VSPW_480P dataset.

Dependencies

Python 3.7
Pytorch 1.3.1
Numpy

Download the ImageNet-pretrained models at this link. Put it in the root folder and decompress it.

Train and Test

Resize the frames and masks of the VSPW dataset to 480p.

python change2_480p.py

Edit the .sh files in scripts/ and change the $DATAROOT to your path to VSPW_480p.

Image-based methods

PSPNet

sh scripts/run_psp.sh

OCRNet

sh scripts/run_ocr.sh

Video-based methods

TCB-PSP

sh run_temporal_psp.sh

TCB-OCR

sh run_temporal_ocr.sh

Evaluation on TC and VC

Change dataroot and prediction root in TC_cal.py and VC_perclip.py.

python TC_cal.py

python VC_perclip.py

This implementation utilized this code and RAFT.

Citation

@inproceedings{miao2021vspw,

  title={VSPW: A Large-scale Dataset for Video Scene Parsing in the Wild},

  author={Miao, Jiaxu and Wei, Yunchao and  Wu, Yu and Liang, Chen and Li, Guangrui and Yang, Yi},

  booktitle={Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition},

  year={2021}

}

You might also like...

Code for our CVPR2021 paper coordinate attention

Coordinate Attention for Efficient Mobile Network Design (preprint) This repository is a PyTorch implementation of our coordinate attention (will appe

726 Jan 5, 2023

[CVPR2021] The source code for our paper 《Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Learning》.

TBE The source code for our paper "Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Le

150 Dec 28, 2022

Code for CVPR2021 paper "Robust Reflection Removal with Reflection-free Flash-only Cues"

Robust Reflection Removal with Reflection-free Flash-only Cues (RFC) Paper | To be released: Project Page | Video | Data Tensorflow implementation for

162 Jan 5, 2023

Repo for CVPR2021 paper "QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information"

QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information by Masato Tamura, Hiroki Ohashi, and Tomoaki Yosh

105 Dec 23, 2022

Comments

Potential Bug in SpatialTemporalGather Module

Hello

Thanks for your code and helpful comments. I think there might be a bug in line 104 in the spatial_ocr_block.py file. It seems you are taking softmax spatially, while it should be on the dimension for the classes right?

so it should be dim=1 instead of dim=2, can you please correct me on this cause I understood from the paper that they are re-weighting it with the class probabilities. I am not sure whats the point of this softmax?

Thanks

opened by MSiam 1
Code cannot run normally!

I don't know why the program warned no error but got stuck when I ran scripts/run_temporal_ocr.sh or other .sh files. CPU showed zero utilization, but GPU was into full of use.

opened by TAILEMI 1

A pytorch implementation of the CVPR2021 paper "VSPW: A Large-scale Dataset for Video Scene Parsing in the Wild"

Related tags

Overview

VSPW: A Large-scale Dataset for Video Scene Parsing in the Wild

Preparation

Download VSPW dataset

Dependencies

Train and Test

Image-based methods

Video-based methods

Evaluation on TC and VC

Citation

You might also like...

Code for our CVPR2021 paper coordinate attention

[CVPR2021] The source code for our paper 《Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Learning》.

Code for CVPR2021 paper "Robust Reflection Removal with Reflection-free Flash-only Cues"

Repo for CVPR2021 paper "QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information"

Code for the paper "Graph Attention Tracking". (CVPR2021)

The official repo of the CVPR2021 oral paper: Representative Batch Normalization with Feature Calibration

Code for CVPR2021 paper "Learning Salient Boundary Feature for Anchor-free Temporal Action Localization"

Code for C2-Matching (CVPR2021). Paper: Robust Reference-based Super-Resolution via C2-Matching.

Code for CVPR2021 paper 'Where and What? Examining Interpretable Disentangled Representations'.

Comments

Potential Bug in SpatialTemporalGather Module

Code cannot run normally!

Owner

[PyTorch] Official implementation of CVPR2021 paper "PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency". https://arxiv.org/abs/2103.05465

PyTorch implementation of our Adam-NSCL algorithm from our CVPR2021 (oral) paper "Training Networks in Null Space for Continual Learning"

Pytorch implementation of CVPR2021 paper "MUST-GAN: Multi-level Statistics Transfer for Self-driven Person Image Generation"

PyTorch code for the paper "Curriculum Graph Co-Teaching for Multi-target Domain Adaptation" (CVPR2021)

PyTorch code for our paper "Image Super-Resolution with Non-Local Sparse Attention" (CVPR2021).

The implementation of the CVPR2021 paper "Structure-Aware Face Clustering on a Large-Scale Graph with 10^7 Nodes"

The implementation of CVPR2021 paper Temporal Query Networks for Fine-grained Video Understanding, by Chuhan Zhang, Ankush Gupta and Andrew Zisserman.

The official implementation of the CVPR2021 paper: Decoupled Dynamic Filter Networks

A weakly-supervised scene graph generation codebase. The implementation of our CVPR2021 paper ``Linguistic Structures as Weak Supervision for Visual Scene Graph Generation''

HGCAE Pytorch implementation. CVPR2021 accepted.