Auxadapt: Stable and efficient test-time adaptation for temporally consistent video semantic segmentation
In video segmentation, generating temporally consistent results across frames is as
important as achieving frame-wise accuracy. Existing methods rely either on optical flow …
important as achieving frame-wise accuracy. Existing methods rely either on optical flow …
An optical flow estimation method based on multiscale anisotropic convolution
Y Wang, Y Li, J Wang, H Lv - Applied Intelligence, 2024 - Springer
To solve the tracking accuracy degradation problem in scenarios with large displacements
or nonrigid motion during target tracking, this paper proposes an optical flow estimation …
or nonrigid motion during target tracking, this paper proposes an optical flow estimation …
Spatio-temporal pixel-level contrastive learning-based source-free domain adaptation for video semantic segmentation
Abstract Unsupervised Domain Adaptation (UDA) of semantic segmentation transfers
labeled source knowledge to an unlabeled target domain by relying on accessing both the …
labeled source knowledge to an unlabeled target domain by relying on accessing both the …
Boosting object representation learning via motion and object continuity
Q Delfosse, W Stammer, T Rothenbächer… - … Conference on Machine …, 2023 - Springer
Recent unsupervised multi-object detection models have shown impressive performance
improvements, largely attributed to novel architectural inductive biases. Unfortunately …
improvements, largely attributed to novel architectural inductive biases. Unfortunately …
A dataset for temporal semantic segmentation dedicated to smart mobility of wheelchairs on sidewalks
B Decoux, R Khemmar, N Ragot, A Venon… - Journal of …, 2022 - mdpi.com
In smart mobility, the semantic segmentation of images is an important task for a good
understanding of the environment. In recent years, many studies have been made on this …
understanding of the environment. In recent years, many studies have been made on this …
Temporal feature warping for video shadow detection
While single image shadow detection has been improving rapidly in recent years, video
shadow detection remains a challenging task due to data scarcity and the difficulty in …
shadow detection remains a challenging task due to data scarcity and the difficulty in …
Robust Computer Vision Against Adversarial Examples and Domain Shifts
SY Lo - 2023 - jscholarship.library.jhu.edu
Recent advances in deep learning have achieved remarkable success in various computer
vision problems. Driven by progressive computing resources and a vast amount of data …
vision problems. Driven by progressive computing resources and a vast amount of data …