Mask propagation for efficient video semantic segmentation

Y Weng, M Han, H He, M Li, L Yao… - Advances in …, 2023 - proceedings.neurips.cc
Abstract Video Semantic Segmentation (VSS) involves assigning a semantic label to each
pixel in a video sequence. Prior work in this field has demonstrated promising results by …

X-Align: Cross-modal cross-view alignment for bird's-eye-view segmentation

S Borse, M Klingner, VR Kumar, H Cai… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract Bird's-eye-view (BEV) grid is a common representation for the perception of road
components, eg, drivable area, in autonomous driving. Most existing approaches rely on …

Motion-state alignment for video semantic segmentation

J Su, R Yin, S Zhang, J Luo - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
In recent years, video semantic segmentation has made great progress with advanced deep
neural networks. However, there still exist two main challenges ie, information inconsistency …

Dejavu: Conditional regenerative learning to enhance dense prediction

S Borse, D Das, H Park, H Cai… - Proceedings of the …, 2023 - openaccess.thecvf.com
We present DejaVu, a novel framework which leverages conditional image regeneration as
additional supervision during training to improve deep networks for dense prediction tasks …

Panoptic, instance and semantic relations: A relational context encoder to enhance panoptic segmentation

S Borse, H Park, H Cai, D Das… - Proceedings of the …, 2022 - openaccess.thecvf.com
This paper presents a novel framework to integrate both semantic and instance contexts for
panoptic segmentation. In existing works, it is common to use a shared backbone to extract …

Deep Common Feature Mining for Efficient Video Semantic Segmentation

Y Zheng, H Yang, D Huang - … on Circuits and Systems for Video …, 2024 - ieeexplore.ieee.org
Recent advancements in video semantic segmentation have made substantial progress by
exploiting temporal correlations. Nevertheless, persistent challenges, including redundant …

Real-time, accurate, and consistent video semantic segmentation via unsupervised adaptation and cross-unit deployment on mobile device

H Park, A Yessenbayev, T Singhal… - Proceedings of the …, 2022 - openaccess.thecvf.com
This demonstration showcases our innovations on efficient, accurate, and temporally
consistent video semantic segmentation on mobile device. We employ our test-time …

Transadapt: A transformative framework for online test time adaptive semantic segmentation

D Das, S Borse, H Park, K Azarian… - ICASSP 2023-2023 …, 2023 - ieeexplore.ieee.org
Test-time adaptive (TTA) semantic segmentation adapts a source pre-trained image
semantic segmentation model to unlabeled batches of target domain test images, different …

Pose constraints for consistent self-supervised monocular depth and ego-motion

ZK Suri - Scandinavian Conference on Image Analysis, 2023 - Springer
Self-supervised monocular depth estimation approaches suffer not only from scale
ambiguity but also infer temporally inconsistent depth maps wrt scale. While disambiguating …

Deep video representation learning: a survey

E Ravanbakhsh, Y Liang, J Ramanujam… - Multimedia Tools and …, 2024 - Springer
This paper provides a review on representation learning for videos. We classify recent spatio-
temporal feature learning methods for sequential visual data and compare their pros and …