computer-vision-3

Video Semantic Segmentation

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in video-semantic-segmentation-3

Trend

Dataset

Best Model

Actions

Cityscapes val

CamVid

VSPW

Libraries

i

Use these libraries to find video-semantic-segmentation-3 models and implementations

yoxu515/aot-benchmark

4 papers 560

Datasets

Subtasks

Camera shot segmentation

Most implemented papers

Pyramid Scene Parsing Network

Xiaogang Wang, Jiaya Jia, Jianping Shi, Xiaojuan Qi, Hengshuang Zhao•Sat Dec 03 2016

This paper exploits the capability of global context information by different-region-based context aggregation through the pyramid pooling module together with the proposed pyramid scene parsing network (PSPNet) to produce good quality results on the scene parsing task.

13635

Content

LaRS

Multispectral Video Semantic Segmentation

PaddlePaddle/PaddleSeg

3 papers 8,228

visionml/pytracking

3 papers 3,082

hkchengrex/Mask-Propagation

3 papers 124

z-x-yang/AOT

3 papers 116

open-mmlab/mmsegmentation

2 papers 7,374

osmr/imgclsmob

2 papers 2,918

wjf5203/vnext

2 papers 592

JanMarcelKezmann/TensorFlow-Advance…

2 papers 149

ODMS

LaRS

0

Paper Graph

Fully convolutional networks for semantic segmentation

Evan Shelhamer, Trevor Darrell, Jonathan Long•Thu Nov 13 2014

The key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning.

40974 0

Paper Graph

PReMVOS: Proposal-generation, Refinement and Merging for Video Object Segmentation

B. Leibe, P. Voigtlaender, Jonathon Luiten•Mon Jul 23 2018

This work addresses semi-supervised video object segmentation, the task of automatically generating accurate and consistent pixel masks for objects in a video sequence, given the first-frame ground truth annotations, with the PReMVOS algorithm.

283 0

Paper Graph

Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion

Yu-Wing Tai, Chi-Keung Tang, Ho Kei Cheng•Sat Mar 13 2021

The MiVOS framework is presented, which decouples interaction-to-mask and mask propagation, allowing for higher generalizability and better performance, and a large-scale synthetic VOS dataset with pixel-accurate segmentation of 4.8M frames is contributed to facilitate future research.

237 0

Paper Graph

Mask2Former for Video Instance Segmentation

A. Schwing, Ishan Misra, Alexander Kirillov, Rohit Girdhar, Bowen Cheng, Anwesa Choudhuri•Sun Dec 19 2021

It is found Mask2Former achieves state-of-the-art performance on video instance segmentation without modifying the architecture, the loss or even the training pipeline, and is also capable of handling video semantic and panoptic segmentation.

216 0

Paper Graph

Rethinking Self-supervised Correspondence Learning: A Video Frame-level Similarity Perspective

Xiaolong Wang, Jiarui Xu•Tue Mar 30 2021

The hypothesis is that if the representation is good for recognition, it requires the convolutional features to find correspondence between similar objects or parts, and VFS surpasses state-of-the-art self-supervised approaches for both OTB visual object tracking and DAVIS video object segmentation.

109 0

Paper Graph

Lucid Data Dreaming for Video Object Segmentation

T. Brox, Eddy Ilg, B. Schiele, Rodrigo Benenson, A. Khoreva•Mon Mar 27 2017

The results indicate that using a larger training set is not automatically better, and that for the video object segmentation task a smaller training set that is closer to the target domain is more effective.

139 0

Paper Graph

YouTube-VOS: Sequence-to-Sequence Video Object Segmentation

Jianchao Yang, Thomas S. Huang, L. Yang, Scott D. Cohen, Brian L. Price, Yuchen Fan, Dingcheng Yue, N. Xu, Yuchen Liang•Sun Sep 02 2018

This work builds a new large-scale video object segmentation dataset called YouTube Video Object Segmentation dataset (YouTube-VOS) and proposes a novel sequence-to-sequence network to fully exploit long-term spatial-temporal information in videos for segmentation.

512 0

Paper Graph

CCNet: Criss-Cross Attention for Semantic Segmentation

Xinggang Wang, Chang Huang, Humphrey Shi, Yunchao Wei, Zilong Huang, Lichao Huang•Tue Nov 27 2018

For each pixel, a novel criss-cross attention module in CCNet harvests the contextual information of all the pixels on its criss-cross path by taking a further recurrent operation, each pixel can finally capture the full-image dependencies from all pixels.

2893 0

Paper Graph

Interactive Video Object Segmentation Using Global and Local Transfer Modules

Yuk Heo, Y. Koh, Chang-Su Kim•Wed Jul 15 2020

An interactive video object segmentation algorithm, which takes scribble annotations on query objects as input, is proposed in this paper and outperforms the state-of-the-art conventional algorithms.

41 0

Paper Graph

Adding a benchmark result helps the community track progress.