The 2nd Pixel-level Video Understanding in the Wild Challenge Workshop
18 June, 2023
CVPR 2023, VANCOUVER
Introduction
Pixel-level Scene Understanding is one of the fundamental problems in computer vision, which aims at recognizing object classes, masks and semantics of each pixel in the given image. Since the real-world is actually video-based rather than a static state, learning to perform video semantic/panoptic segmentation is more reasonable and practical for realistic applications. To advance the semantic/panoptic segmentation task from images to videos, we present two large-scale datasets (VSPW[1] and VIPSeg[2]) and a competition in this workshop, aiming at performing the challenging yet practical Pixel-level Video Understanding in the Wild (PVUW). This workshop includes workshop papers
This workshop will cover but not limit to the following topics:
● Semantic/panoptic segmentation for images/videos
● Video object/instance segmentation
● Efficient computation for video scene parsing
● Object tracking
● Semi-supervised recognition in videos
● New metrics to evaluate the quality of video scene parsing results
● Real-world video applications, including autonomous driving, indoor robotics, visual navigation, etc.
[1] VSPW: A Large-scale Dataset for Video Scene Parsing in the Wild. CVPR 2021
[2] Large-scale Video Panoptic Segmentation in the Wild: A Benchmark. CVPR 2022
Challenges
Pixel-level Video Understanding in the Wild Challenge (PVUW) challenge includes two tracks, the video semantic segmentation track and the video panoptic segmentation track.
Track 1: Video Semantic Segmentation (VSS) Track
The video semantic segmentation task aims to recognize the semantics of all frames in a given video. To participant Track 1, please visit this link.
Track 2: Video Panoptic Segmentation (VPS) Track
The video panoptic segmentation task aims to jointly predict object classes, bounding boxes, masks, instance id tracking, and semantic segmentation in video frames. To participant Track 2, please visit this link.
Important Dates:
Jan 20th: Codalab websites open for registration. Training, validation and test data are released.
May 15th - 25th: Open the submission of the final test results.
May 30th: The final competition results will be announced and top teams will be invited to give oral/poster presentations at our CVPR 2023 workshop.
Call for Papers
Submission: We invite authors to submit unpublished papers (8-page CVPR format) to our workshop, to be presented at a poster session upon acceptance. All submissions will go through a double-blind review process. All contributions must be submitted (along with supplementary materials, if any) at this CMT link.
Accepted papers will be published in the official CVPR Workshops proceedings and the Computer Vision Foundation (CVF) Open Access archive.
Important Dates:
Workshop paper submission deadline: 5 March 2023 (23:59 PST)
Notification to authors: 25 March 2023
Camera ready deadline: 2 April 2023
Invited Speakers

Hengshuang Zhao
Assistant Professor
The University of Hong Kong

Yuhui Yuan
Senior Researcher
Microsoft Research Asia
Workshop Schedule
18 June 1:30 PM (PT time) Chairs’ opening remarks
18 June 1:45 PM (PT time) Yuhui Yuan, Microsoft Research Asia
18 June 2:20 PM (PT time) Hengshuang Zhao, The University of Hong Kong
18 June 2:55 PM (PT time) Challenge 1st place Winners’ Oral Presentation (VSS Track)
18 June 3:10 PM (PT time) Break
18 June 3:25 PM (PT time) Challenge 2st place Winners’ Oral Presentation (VSS Track)
18 June 3:40 PM (PT time) Challenge 3st place Winners’ Oral Presentation (VSS Track)
18 June 3:55 PM (PT time) Challenge 1st place Winners’ Oral Presentation (VPS Track)
18 June 4:10 PM (PT time) Challenge 2st place Winners’ Oral Presentation (VPS Track)
18 June 4:25 PM (PT time) Challenge 3st place Winners’ Oral Presentation (VPS Track)
18 June 4:40 PM (PT time) Workshop Paper Hidetomo SAKAINO
Organizers

Jiaxu Miao
Zhejiang University

Zongxin Yang
Zhejiang University

Yunchao Wei
University of Technology Sydney

Yi Yang
Zhejiang University

Si Liu
Beihang University

Zhu Yi
Amazon

Elisa Ricci
University of Trento

Cees Snoek
University of Amsterdam