Filters








1,106 Hits in 5.2 sec

Speed Invariant Time Surface for Learning to Detect Corner Points with Event-Based Cameras [article]

Jacques Manderscheid, Amos Sironi, Nicolas Bourdis, Davide Migliore, Vincent Lepetit
2019 arXiv   pre-print
We propose a learning approach to corner detection for event-based cameras that is stable even under fast and abrupt motions.  ...  Event-based cameras offer high temporal resolution, power efficiency, and high dynamic range.  ...  Learning from Events Machine learning approaches for event-based cameras can also be divided in two categories.  ... 
arXiv:1903.11332v2 fatcat:5gjyq5jwovhpfpb4bycms4cjrm

Speed Invariant Time Surface for Learning to Detect Corner Points With Event-Based Cameras

Jacques Manderscheid, Amos Sironi, Nicolas Bourdis, Davide Migliore, Vincent Lepetit
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
We propose a learning approach to corner detection for event-based cameras that is stable even under fast and abrupt motions.  ...  Event-based cameras offer high temporal resolution, power efficiency, and high dynamic range.  ...  Learning from Events Machine learning approaches for event-based cameras can also be divided in two categories.  ... 
doi:10.1109/cvpr.2019.01049 dblp:conf/cvpr/ManderscheidSBM19 fatcat:nywagnyvjbeydawzq2t5sw2ozq

A Survey on Deep Learning for Localization and Mapping: Towards the Age of Spatial Machine Intelligence [article]

Changhao Chen, Bing Wang, Chris Xiaoxuan Lu, Niki Trigoni, Andrew Markham
2020 arXiv   pre-print
In this work, we provide a comprehensive survey, and propose a new taxonomy for localization and mapping using deep learning.  ...  A wide range of topics are covered, from learning odometry estimation, mapping, to global localization and simultaneous localization and mapping (SLAM).  ...  Acknowledgments This work is supported by the EPSRC Project "ACE-OPS: From Autonomy to Cognitive assistance in Emergency OPerationS" (Grant Number: EP/S030832/1).  ... 
arXiv:2006.12567v2 fatcat:snb2byqamfcblauw5lzccb7umy

High-level event recognition in unconstrained videos

Yu-Gang Jiang, Subhabrata Bhattacharya, Shih-Fu Chang, Mubarak Shah
2012 International Journal of Multimedia Information Retrieval  
Such videos depicting complex events have limited quality control, and therefore, may include severe camera motion, poor lighting, heavy background clutter, and occlusion.  ...  However, due to the fast growing popularity of such videos, especially on the Web, solutions to this problem are in high demands and have attracted great interest from researchers.  ...  Yu-Gang Jiang was partially supported by grants from the National Natural Science Foundation of China (#61201387 and #61228205).  ... 
doi:10.1007/s13735-012-0024-2 fatcat:mfzttic3svb4tho2xb6aczgp4y

Dual-Mode Vehicle Motion Pattern Learning for High Performance Road Traffic Anomaly Detection

Yan Xu, Xi Ouyang, Yu Cheng, Shining Yu, Lin Xiong, Choon-Ching Ng, Sugiri Pranata, Shengmei Shen, Junliang Xing
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
In this work, we present a model to detect anomaly in road traffic by learning from the vehicle motion patterns in two distinctive yet correlated modes, i.e., the static mode and the dynamic mode, of the  ...  The dynamic mode analysis of the vehicles is learned from detected and tracked vehicle trajectories to find the abnormal trajectory which is aberrant from the dominant motion patterns.  ...  Conclusions In this paper, we present a dual-mode motion pattern learning model for anomaly detection in urban road traffic, which jointly analyzes the static and dynamic properties of the vehicles.  ... 
doi:10.1109/cvprw.2018.00027 dblp:conf/cvpr/XuOCYXNPSX18 fatcat:x73kkxrmsfaphkjvpkwt6wqtlm

Multi-domain Collaborative Feature Representation for Robust Visual Object Tracking [article]

Jiqing Zhang and Kai Zhao and Bo Dong and Yingkai Fu and Yuxin Wang and Xin Yang and Baocai Yin
2021 arXiv   pre-print
Specifically, we propose Common Features Extractor (CFE) to learn potential common representations from the RGB domain and event domain.  ...  This paper focuses on effectively representing and utilizing complementary features from the frame domain and event domain for boosting object tracking performance in challenge scenarios.  ...  .: Jointly learning visual motion and confidence from local patches in event cameras. In: Proceedings of the European Conference on Computer Vision (2020) 27.  ... 
arXiv:2108.04521v2 fatcat:eefdlvkfm5g6djtyrnvwa7dtyy

Storyline Representation of Egocentric Videos with an Applications to Story-Based Search

Bo Xiong, Gunhee Kim, Leonid Sigal
2015 2015 IEEE International Conference on Computer Vision (ICCV)  
objects and events, depicted on a timeline.  ...  Our representation promotes story-based search with queries in the form of AND-OR graphs, which span any subset of story elements and their spatio-temporal composition.  ...  However, multiple activities may have similar motion patterns; for example, the camera motion is relatively stationary in both watching performance and dining events.  ... 
doi:10.1109/iccv.2015.514 dblp:conf/iccv/XiongKS15 fatcat:ebbhrf7f3zai5efmtrtd7e34fq

Online Multi-Object Tracking with Visual and Radar Features

Seung-Hwan Bae
2020 IEEE Access  
In many autonomous systems equipped with a camera and a radar, an amplitude and visual features can be measured.  ...  To achieve it, we propose a unified MOT framework based on object model learning and confidence-based association.  ...  From visual features, we learn object appearance, motion and shape models during tracking, whereas learn an amplitude model from a radar feature.  ... 
doi:10.1109/access.2020.2994000 fatcat:65ihpxygvffhbpkfsyu2jiifsy

Bidirectional Attentive Fusion with Context Gating for Dense Video Captioning [article]

Jingwen Wang, Wenhao Jiang, Lin Ma, Wei Liu, Yong Xu
2018 arXiv   pre-print
Dense video captioning is a newly emerging task that aims at both localizing and describing all events in a video.  ...  We further propose a novel context gating mechanism to balance the contributions from the current event and its surrounding contexts dynamically.  ...  from localization and captioning.  ... 
arXiv:1804.00100v2 fatcat:snnkr2e2fzcqxjghqaafqnsdzq

Deep Learning for HDR Imaging: State-of-the-Art and Future Trends [article]

Lin Wang, Kuk-Jin Yoon
2021 arXiv   pre-print
In recent years, there has been a significant advancement in HDR imaging using deep learning (DL).  ...  learning strategies, and (5) applications.  ...  In particular, a hybrid camera system is set up to jointly take a single HR LDR image and an LR intensity map generated from the events.  ... 
arXiv:2110.10394v3 fatcat:pvsktnd5wrgo5lstughzlhon7i

Deep Learning based Monocular Depth Prediction: Datasets, Methods and Applications [article]

Qing Li, Jiasong Zhu, Jun Liu, Rui Cao, Qingquan Li, Sen Jia, Guoping Qiu
2020 arXiv   pre-print
Estimating depth from RGB images can facilitate many computer vision tasks, such as indoor localization, height estimation, and simultaneous localization and mapping (SLAM).  ...  They surpass traditional machine learning-based methods by a large margin in terms of accuracy and speed.  ...  [123] also perform a multi-task learning strategy to jointly learn dense depth, optical flow and camera pose.  ... 
arXiv:2011.04123v1 fatcat:by6swdegvvdrxk73ti46k2rj2e

Video Abnormal Event Detection by Learning to Complete Visual Cloze Tests [article]

Siqi Wang, Guang Yu, Zhiping Cai, Xinwang Liu, En Zhu, Jianping Yin
2021 arXiv   pre-print
Although deep neural networks (DNNs) enable great progress in video abnormal event detection (VAD), existing solutions typically suffer from two issues: (1) The localization of video events cannot be both  ...  To tackle those issues, we are motivated by the prevalent cloze test in education and propose a novel approach named Visual Cloze Completion (VCC), which conducts VAD by learning to complete "visual cloze  ...  in [71] , as motion cues for localizing video events.  ... 
arXiv:2108.02356v2 fatcat:7sl2musf7vecrdtdhwcqb2nsjy

Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Art [article]

Joel Janai, Fatma Güney, Aseem Behl, Andreas Geiger
2021 arXiv   pre-print
Recent years have witnessed enormous progress in AI-related fields such as computer vision, machine learning, and autonomous vehicles.  ...  , scene understanding, and end-to-end learning for autonomous driving.  ...  Structure from Motion In Structure-from-Motion (SfM), the camera parameters (intrinsic and extrinsic) need to be estimated jointly with the 3D structure while in Multi-View Stereo (MVS), the camera parameters  ... 
arXiv:1704.05519v3 fatcat:xiintiarqjbfldheeg2hsydyra

A comparison of crowd commotion measures from generative models

Sadegh Mohammadi, Hamed Kiani, Alessandro Perina, Vittorio Murino
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
The main challenges come from the lack of a clear definition of abnormality and from the scarcity, often absence, of abnormal training samples.  ...  Detecting abnormal events in video sequences is a challenging task that has been broadly investigated over the last decade.  ...  , camera motion, illumination and abnormality.  ... 
doi:10.1109/cvprw.2015.7301283 dblp:conf/cvpr/MohammadiKPM15 fatcat:ci347whzb5alpdug2sos6yywci

Human Action Recognition Bases on Local Action Attributes

Jing Zhang, Hong Lin, Weizhi Nie, Lekha Chaisorn, Yongkang Wong, Mohan S Kankanhalli
2015 Journal of Electrical Engineering and Technology  
In this paper we explore the idea of using local action attributes to form an action descriptor, where an action is no longer characterized with the motion changes in the temporal domain but the local  ...  In addition, we conduct some study on the impact of using body local and global low-level feature for the aforementioned attributes.  ...  Then, the attributes and parts are jointly model for action recognition in still images. Recently, Liu [12] do a lot of work on attribute-based human action recognition from videos.  ... 
doi:10.5370/jeet.2015.10.3.1264 fatcat:hg2hab5gmvhuneqfviw2hwgcne
« Previous Showing results 1 — 15 out of 1,106 results