Semantic segmentation using Vision Transformers: A survey

H Thisanke, C Deshan, K Chamith… - … Applications of Artificial …, 2023 - Elsevier
Semantic segmentation has a broad range of applications in a variety of domains including
land coverage analysis, autonomous driving, and medical image analysis. Convolutional …

[HTML][HTML] Coarse-to-fine video instance segmentation with factorized conditional appearance flows

Z Qin, X Lu, X Nie, D Liu, Y Yin, W Wang - IEEE/CAA Journal of …, 2023 - ieee-jas.net
We introduce a novel method using a new generative model that automatically learns
effective representations of the target and background appearance to detect, segment and …

Minvis: A minimal video instance segmentation framework without video-based training

DA Huang, Z Yu, A Anandkumar - Advances in Neural …, 2022 - proceedings.neurips.cc
We propose MinVIS, a minimal video instance segmentation (VIS) framework that achieves
state-of-the-art VIS performance with neither video-based architectures nor training …

Video transformers: A survey

J Selva, AS Johansen, S Escalera… - … on Pattern Analysis …, 2023 - ieeexplore.ieee.org
Transformer models have shown great success handling long-range interactions, making
them a promising tool for modeling video. However, they lack inductive biases and scale …

Vita: Video instance segmentation via object token association

M Heo, S Hwang, SW Oh, JY Lee… - Advances in Neural …, 2022 - proceedings.neurips.cc
We introduce a novel paradigm for offline Video Instance Segmentation (VIS), based on the
hypothesis that explicit object-oriented information can be a strong clue for understanding …

Tube-Link: A flexible cross tube framework for universal video segmentation

X Li, H Yuan, W Zhang, G Cheng… - Proceedings of the …, 2023 - openaccess.thecvf.com
Video segmentation aims to segment and track every pixel in diverse scenarios accurately.
In this paper, we present Tube-Link, a versatile framework that addresses multiple core tasks …

Ctvis: Consistent training for online video instance segmentation

K Ying, Q Zhong, W Mao, Z Wang… - Proceedings of the …, 2023 - openaccess.thecvf.com
The discrimination of instance embeddings plays a vital role in associating instances across
time for online video instance segmentation (VIS). Instance embedding learning is directly …

Videotrack: Learning to track objects via video transformer

F Xie, L Chu, J Li, Y Lu, C Ma - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Existing Siamese tracking methods, which are built on pair-wise matching between two
single frames, heavily rely on additional sophisticated mechanism to exploit temporal …

Temporal collection and distribution for referring video object segmentation

J Tang, G Zheng, S Yang - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
Referring video object segmentation aims to segment a referent throughout a video
sequence according to a natural language expression. It requires aligning the natural …

A generalized framework for video instance segmentation

M Heo, S Hwang, J Hyun, H Kim… - Proceedings of the …, 2023 - openaccess.thecvf.com
The handling of long videos with complex and occluded sequences has recently emerged
as a new challenge in the video instance segmentation (VIS) community. However, existing …