English
Related papers

Related papers: Observation-Aligned Mask Priors for Learning Physi…

200 papers

Satellite-derived fire observations are the primary input for learning-based wildfire spread prediction, yet they are inherently incomplete due to cloud cover, smoke obscuration, and sensor artifacts. This partial observability introduces a…

Image and Video Processing · Electrical Eng. & Systems 2026-03-11 Chen Yang , Mehdi Zafari , Ziheng Duan , A. Lee Swindlehurst

Masked autoencoding has achieved great success for self-supervised learning in the image and language domains. However, mask based pretraining has yet to show benefits for point cloud understanding, likely due to standard backbones like…

Computer Vision and Pattern Recognition · Computer Science 2022-08-02 Haotian Liu , Mu Cai , Yong Jae Lee

Occlusion presents a significant challenge in human pose estimation. The challenges posed by occlusion can be attributed to the following factors: 1) Data: The collection and annotation of occluded human pose samples are relatively…

Computer Vision and Pattern Recognition · Computer Science 2024-01-10 Linhao Xu , Lin Zhao , Xinxin Sun , Di Wang , Guangyu Li , Kedong Yan

Navigating complex and dynamic environments requires autonomous vehicles (AVs) to reason about both visible and occluded regions. This involves predicting the future motion of observed agents, inferring occluded ones, and modeling their…

Robotics · Computer Science 2024-03-12 Bernard Lange , Jiachen Li , Mykel J. Kochenderfer

Panoramic image processing is essential for omni-context perception, yet faces constraints like distortions, perspective occlusions, and limited annotations. Previous unsupervised domain adaptation methods transfer knowledge from labeled…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 Yihong Cao , Jiaming Zhang , Xu Zheng , Hao Shi , Kunyu Peng , Hang Liu , Kailun Yang , Hui Zhang

The goal of this paper is to discover, segment, and track independently moving objects in complex visual scenes. Previous approaches have explored the use of optical flow for motion segmentation, leading to imperfect predictions due to…

Computer Vision and Pattern Recognition · Computer Science 2024-08-20 Junyu Xie , Weidi Xie , Andrew Zisserman

Vision-based motion capture solutions often struggle with occlusions, which result in the loss of critical joint information and hinder accurate 3D motion reconstruction. Other wearable alternatives also suffer from noisy or unstable data,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Junkun Jiang , Jie Chen , Ho Yin Au , Jingyu Xiang

As a flexible passive 3D sensing means, unsupervised learning of depth from monocular videos is becoming an important research topic. It utilizes the photometric errors between the target view and the synthesized views from its adjacent…

Computer Vision and Pattern Recognition · Computer Science 2021-08-31 Hualie Jiang , Laiyan Ding , Zhenglong Sun , Rui Huang

Convolutional neural network (CNN) based architectures, such as Mask R-CNN, constitute the state of the art in object detection and segmentation. Recently, these methods have been extended for model-based segmentation where the network…

Computer Vision and Pattern Recognition · Computer Science 2021-01-14 Wenbo Dong , Volkan Isler

Real-world scientific applications frequently encounter incomplete observational data due to sensor limitations, geographic constraints, or measurement costs. Although neural operators significantly advanced PDE solving in terms of…

Machine Learning · Computer Science 2026-01-28 Jingren Hou , Hong Wang , Pengyu Xu , Chang Gao , Huafeng Liu , Liping Jing

Amodal completion is a visual task that humans perform easily but which is difficult for computer vision algorithms. The aim is to segment those object boundaries which are occluded and hence invisible. This task is particularly challenging…

Computer Vision and Pattern Recognition · Computer Science 2022-07-12 Yihong Sun , Adam Kortylewski , Alan Yuille

Most objects in the visual world are partially occluded, but humans can recognize them without difficulty. However, it remains unknown whether object recognition models like convolutional neural networks (CNNs) can handle real-world…

Computer Vision and Pattern Recognition · Computer Science 2019-06-05 Hongru Zhu , Peng Tang , Jeongho Park , Soojin Park , Alan Yuille

Deep learning has revolutionized the field of computer vision by introducing large scale neural networks with millions of parameters. Training these networks requires massive datasets and leads to intransparent models that can fail to…

Computer Vision and Pattern Recognition · Computer Science 2024-05-24 Tom Fischer , Pascal Peter , Joachim Weickert , Eddy Ilg

The paper presents a scalable approach for learning spatially distributed visual representations over individual tokens and a holistic instance representation simultaneously. We use self-attention blocks to represent spatially distributed…

Computer Vision and Pattern Recognition · Computer Science 2023-03-09 Zhirong Wu , Zihang Lai , Xiao Sun , Stephen Lin

In the absence of vaccines or medicines to stop COVID-19, one of the effective methods to slow the spread of the coronavirus and reduce the overloading of healthcare is to wear a face mask. Nevertheless, to mandate the use of face masks or…

Computer Vision and Pattern Recognition · Computer Science 2021-10-04 Chun-Wei Yang , Thanh-Hai Phung , Hong-Han Shuai , Wen-Huang Cheng

This paper proposes a method for visually explaining the decision-making process of video recognition networks with a temporal extension of occlusion sensitivity analysis, called Adaptive Occlusion Sensitivity Analysis (AOSA). The key idea…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Tomoki Uchiyama , Naoya Sogi , Satoshi Iizuka , Koichiro Niinuma , Kazuhiro Fukui

Unsupervised anomaly segmentation aims to detect patterns that are distinct from any patterns processed during training, commonly called abnormal or out-of-distribution patterns, without providing any associated manual segmentations. Since…

Image and Video Processing · Electrical Eng. & Systems 2023-11-06 Ziyun Liang , Harry Anthony , Felix Wagner , Konstantinos Kamnitsas

We consider the effect of structure-agnostic and structure-dependent masking schemes when training a universal marginaliser (arXiv:1711.00695) in order to learn conditional distributions of the form $P(x_i |\mathbf x_{\mathbf b})$, where…

Machine Learning · Computer Science 2020-01-17 Divya Gautam , Maria Lomeli , Kostis Gourgoulias , Daniel H. Thompson , Saurabh Johri

Face recognition remains a challenging task in unconstrained scenarios, especially when faces are partially occluded. To improve the robustness against occlusion, augmenting the training images with artificial occlusions has been proved as…

Computer Vision and Pattern Recognition · Computer Science 2022-01-19 Mingjie He , Jie Zhang , Shiguang Shan , Xiao Liu , Zhongqin Wu , Xilin Chen

Current perception models in autonomous driving heavily rely on large-scale labelled 3D data, which is both costly and time-consuming to annotate. This work proposes a solution to reduce the dependence on labelled 3D training data by…

Computer Vision and Pattern Recognition · Computer Science 2023-10-10 Chen Min , Xinli Xu , Dawei Zhao , Liang Xiao , Yiming Nie , Bin Dai