Filters








1,052 Hits in 3.6 sec

Large-Scale Object Discovery and Detector Adaptation from Unlabeled Video [article]

Aljoša Ošep and Paul Voigtlaender and Jonathon Luiten and Stefan Breuers and Bastian Leibe
2017 arXiv   pre-print
We explore object discovery and detector adaptation based on unlabeled video sequences captured from a mobile platform.  ...  By applying this method to three large video datasets from autonomous driving and mobile robotics scenarios, we demonstrate its robustness and generality.  ...  We would like to thank Alexander Hermans, Wolfgang Mehner and István Sárándi for helpful discussions  ... 
arXiv:1712.08832v1 fatcat:5uj26t7vijajrdcu3umhyexwha

Towards Large-Scale Video Video Object Mining [article]

Aljosa Osep, Paul Voigtlaender, Jonathon Luiten, Stefan Breuers, Bastian Leibe
2018 arXiv   pre-print
We propose to leverage a generic object tracker in order to perform object mining in large-scale unlabeled videos, captured in a realistic automotive setting.  ...  We present a dataset of more than 360'000 automatically mined object tracks from 10+ hours of video data (560'000 frames) and propose a method for automated novel category discovery and detector learning  ...  In this paper, we propose a method for large-scale video-object mining.  ... 
arXiv:1809.07316v1 fatcat:mlm5oscinrfzlfqpihr6arpqhq

Large-Scale Object Mining for Object Discovery from Unlabeled Video [article]

Aljosa Osep, Paul Voigtlaender, Jonathon Luiten, Stefan Breuers, Bastian Leibe
2019 arXiv   pre-print
This paper addresses the problem of object discovery from unlabeled driving videos captured in a realistic automotive setting.  ...  In order to facilitate further research in object discovery, we release a collection of more than 360,000 automatically mined object tracks from 10+ hours of video data (560,000 frames).  ...  Acknowledgements: We would like to thank Bin Huang and Michael Krause for annotation work. This project was funded, in parts, by ERC Consolidator Grant DeeVise (ERC-2017-COG-773161).  ... 
arXiv:1903.00362v2 fatcat:mn7gephdsfcadfar7g4yzyrd4y

Shifting Weights: Adapting Object Detectors from Image to Video

Kevin D. Tang, Vignesh Ramanathan, Fei-Fei Li, Daphne Koller
2012 Neural Information Processing Systems  
In this paper, we tackle the problem of adapting object detectors learned from images to work well on videos.  ...  We show promising results on the 2011 TRECVID Multimedia Event Detection [1] and LabelMe Video [2] datasets that illustrate the benefit of our approach to adapt object detectors to video.  ...  Disclaimer: The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied  ... 
dblp:conf/nips/TangR0K12 fatcat:feprso7hu5ed3kknfydgrvqt24

Self-Learning Scene-Specific Pedestrian Detectors Using a Progressive Latent Model

Qixiang Ye, Tianliang Zhang, Wei Ke, Qiang Qiu, Jie Chen, Guillermo Sapiro, Baochang Zhang
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
The selflearning approach is deployed as progressive steps of object discovery, object enforcement, and label propagation.  ...  Compared with conventional latent models, the proposed PLM incorporates a spatial regularization term to reduce ambiguities in object proposals and to enforce object localization, and also a graph-based  ...  Tekes and Infotech Oulu are gratefully acknowledged.  ... 
doi:10.1109/cvpr.2017.222 dblp:conf/cvpr/YeZKQCSZ17 fatcat:4b6uc7qvfvhkhj5gljgim5a7ai

Self-learning Scene-specific Pedestrian Detectors using a Progressive Latent Model [article]

Qixiang Ye, Tianliang Zhang, Qiang Qiu, Baochang Zhang, Jie Chen, Guillermo Sapiro
2016 arXiv   pre-print
The self-learning approach is deployed as progressive steps of object discovery, object enforcement, and label propagation.  ...  Compared with conventional latent models, the proposed PLM incorporates a spatial regularization term to reduce ambiguities in object proposals and to enforce object localization, and also a graph-based  ...  Acknowledgement The partial support of this work by ONR, NGA, ARO, NSF, NSFC under Grant 61271433 and 61671427, and Beijing Municipal Science & Technology Commission under Grant Z161100001616005 is gratefully  ... 
arXiv:1611.07544v1 fatcat:d6fvdn2hjzgurmd2nquvcli7mu

Self-supervisory Signals for Object Discovery and Detection [article]

Etienne Pot, Alexander Toshev, Jana Kosecka
2018 arXiv   pre-print
Knowledge of ego-motion and depth perception enables the agent to effectively associate multiple object proposals, which serve as training data for learning object representations from unlabelled images  ...  First, we can automatically discover objects by performing clustering in the learned embedding space. Each resulting cluster contains examples of one instance seen from various viewpoints and scales.  ...  SSOD allows for such an agent to be able to quickly learn new objects and be able to detect them.  ... 
arXiv:1806.03370v1 fatcat:3xnxv55whjcvfniswciwuxocvm

Co-Separating Sounds of Visual Objects [article]

Ruohan Gao, Kristen Grauman
2019 arXiv   pre-print
We introduce a co-separation training paradigm that permits learning object-level sounds from unlabeled multi-source videos.  ...  Learning how objects sound from video is challenging, since they often heavily overlap in a single audio channel.  ...  Our CO-SEPARATION approach can leverage noisy object detections as supervision to learn from large-scale unlabeled videos.  ... 
arXiv:1904.07750v2 fatcat:qwv5rx3o3recngpgv6wqkd6mde

A Deep Detector Classifier (DeepDC) for moving objects segmentation and classification in video surveillance

SIRINE AMMAR, Thierry Bouwmans, Nizar Zaghden, Mahmoud Neji
2020 IET Image Processing  
of segmenting and classifying moving objects from videos surveillance.  ...  In this study, the authors present a new approach to segment and classify moving objects in video sequences by combining an unsupervised anomaly discovery framework called DeepSphere and generative adversarial  ...  Acknowledgments We first would like to thank Xian Teng, Muheng Yan, Ali Mert Ertugrul, and Yu-Ru Lin for providing us the source code of DeepSphere [1] .  ... 
doi:10.1049/iet-ipr.2019.0769 fatcat:cpth6r4f2nbdhobv5r23bgw2ie

Watch and Learn: Semi-Supervised Learning of Object Detectors from Videos [article]

Ishan Misra, Abhinav Shrivastava, Martial Hebert
2015 arXiv   pre-print
an object detector.  ...  We present a semi-supervised approach that localizes multiple unknown object instances in long videos.  ...  Acknowledgments: The authors thank Robert Collins and the reviewers for many helpful comments. This project was supported by NSF Grant IIS1065336 and a Google Faculty Research Award.  ... 
arXiv:1505.05769v1 fatcat:cpshxqbebneuxgjmfyakw2k4g4

Watch and learn: Semi-supervised learning of object detectors from videos

Ishan Misra, Abhinav Shrivastava, Martial Hebert
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
an object detector.  ...  We present a semi-supervised approach that localizes multiple unknown object instances in long videos.  ...  Acknowledgments: The authors thank Robert Collins and the reviewers for many helpful comments. This project was supported by NSF Grant IIS1065336 and a Google Faculty Research Award.  ... 
doi:10.1109/cvpr.2015.7298982 dblp:conf/cvpr/MisraSH15 fatcat:7lg5fekquva7bkyrsk3evxkkz4

Learning Scene-specific Object Detectors Based on a Generative-Discriminative Model with Minimal Supervision [article]

Dapeng Luo, Zhipeng Zeng, Nong Sang, Xiang Wu, Longsheng Wei, Quanzheng Mou, Jun Cheng, Chen Luo
2018 arXiv   pre-print
One object class may show large variations due to diverse illuminations, backgrounds and camera viewpoints.  ...  First, a scene-specific objector is obtained from a fully autonomous learning process triggered by marking several bounding boxes around the object in the first video frame via a mouse.  ...  Acknowledgment This work was supported by the National Natural Science Foundation of China (61302137, 61603357, 61271328 and 61603354), Wuhan huanghe Elite Project, Fundamental Research Funds for the Central  ... 
arXiv:1611.03968v4 fatcat:6o2xcfztifd2vmsct7jo26ae7a

Semi-supervised Object Detection via Virtual Category Learning [article]

Changrui Chen, Kurt Debattista, Jungong Han
2022 arXiv   pre-print
Due to the costliness of labelled data in real-world applications, semi-supervised object detectors, underpinned by pseudo labelling, are appealing.  ...  It is attributed to specifying the embedding distance between the training sample and the virtual category as the lower bound of the inter-class distance.  ...  Introduction The Deep Learning community is suffering from the expensive labelling cost of large-scale datasets.  ... 
arXiv:2207.03433v1 fatcat:d72wuoiftrfv7ltg7vho5zejpi

Selecting Relevant Web Trained Concepts for Automated Event Retrieval [article]

Bharat Singh, Xintong Han, Zhe Wu, Vlad I. Morariu, Larry S. Davis
2015 arXiv   pre-print
Our approach also addresses calibration and domain adaptation issues that arise when applying concept detectors to unseen videos.  ...  Therefore, recent approaches automate concept discovery and training by leveraging large amounts of weakly annotated web data.  ...  The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of IARPA  ... 
arXiv:1509.07845v1 fatcat:dg6ykgqagjdm7hpac2xsyrwaom

Watch, Ask, Learn, and Improve: a lifelong learning cycle for visual recognition

Christoph Käding, Erik Rodner, Alexander Freytag, Joachim Denzler
2016 The European Symposium on Artificial Neural Networks  
We present WALI, a prototypical system that learns object categories over time by continuously watching online videos.  ...  WALI actively asks questions to a human annotator about the visual content of observed video frames.  ...  Query images are selected according to the best vs. second-best strategy as proposed in [14] which scales even to large number of labeled and unlabeled examples.  ... 
dblp:conf/esann/KadingRFD16 fatcat:qg5czg4z65auvgpsemhwo7djgm
« Previous Showing results 1 — 15 out of 1,052 results