mlsanityData to 14 Oct 2026

The Runner-up Solution for YouTube-VIS Long Video Challenge 2022

arXiv 2211.09973 ↗First posted 18 Nov 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

This technical report describes our 2nd-place solution for the ECCV 2022 YouTube-VIS Long Video Challenge. We adopt the previously proposed online video instance segmentation method IDOL for this challenge. In addition, we use pseudo labels to further help contrastive learning, so as to obtain more temporally consistent instance embedding to improve tracking performance between frames. The proposed method obtains 40.2 AP on the YouTube-VIS 2022 long video dataset and was ranked second place in this challenge. We hope our simple and effective method could benefit further research.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 20 references that are in the map. First posted on arXiv 18 Nov 2022.

Builds on

20 of 20 references.

References · 20

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  3. 2020End-to-End Object Detection with Transformerscited by 7,414
  4. 2017Mask R-CNNcited by 7,277
  5. 2022A ConvNet for the 2020scited by 3,579
  6. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  7. 2020End-to-End Video Instance Segmentation with Transformerscited by 443
  8. 2019Video Instance Segmentationcited by 393
  9. 2020Conditional Convolutions for Instance Segmentationcited by 314
  10. 2019Classifying, Segmenting, and Tracking Object Instances in Video with Mask Propagationcited by 125
  11. 2020STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videoscited by 121
  12. 2020SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentationcited by 108
8 more
  1. 2021Video Instance Segmentation using Inter-Frame Communication Transformerscited by 105
  2. 2021SeqFormer: Sequential Transformer for Video Instance Segmentationcited by 98
  3. 2022In Defense of Online Models for Video Instance Segmentationcited by 97
  4. 2021Crossover Learning for Fast Online Video Instance Segmentationcited by 83
  5. 2021Video Instance Segmentation with a Propose-Reduce Paradigmcited by 74
  6. 2020CompFeat: Comprehensive Feature Aggregation for Video Instance Segmentationcited by 53
  7. 2021Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentationcited by 43
  8. 2021Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentationcited by 42

Built on by

Not cited yet.