Filters








128,549 Hits in 3.7 sec

Representative-Discriminative Learning for Open-set Land Cover Classification of Satellite Imagery [article]

Razieh Kaviani Baghbaderani, Ying Qu, Hairong Qi, Craig Stutts
2020 arXiv   pre-print
We propose a representative-discriminative open-set recognition (RDOSR) framework, which 1) projects data from the raw image space to the embedding feature space that facilitates differentiating similar  ...  We also show the generality of the proposed approach by achieving promising results on open-set classification tasks using RGB images.  ...  [29] incorporated the latent representation for reconstruction along with the discriminative features obtained from a classification model to enhance the feature vector used for open-set detection.  ... 
arXiv:2007.10891v1 fatcat:sdrxjtjnzbfj7dbmkevxx3w5ci

An Adversarial Framework for Open-Set Human Action Recognition Using Skeleton Data

2020 Turkish Journal of Electrical Engineering and Computer Sciences  
In this study, we propose an open-set action recognition system, HARNAD, 7 which consists of two stages and uses only 3D skeleton information.  ...  We evaluate the performance of the system experimentally both in terms of recognition and novelty detection. 10 We also compare the system performance with state of the art open-set recognition methods  ...  Models for Open Set Recognition.'  ... 
doi:10.3906/elk-2003-124 fatcat:khzpsf2p2jehthfsn2csdz7ami

PA-GAN: A Patch-Attention based Aggregation Network for Face Recognition in Surveillance

Ming Liu, Jinjin Liu, Ping Zhang, Qingbao Li
2020 IEEE Access  
Thus, it leads to the open-set protocol.  ...  Loss Function 1) DISCRIMINATIVE LOSS In practice, real-world surveillance FR is an open-set problem.  ...  Author Name: Preparation of Papers for IEEE Access (February 2017) VOLUME XX, 2017  ... 
doi:10.1109/access.2020.3017779 fatcat:z62ycxblifdydoshfte6nka6le

Exploring the Encoding Layer and Loss Function in End-to-End Speaker and Language Recognition System [article]

Weicheng Cai, Jinkun Chen, Ming Li
2018 arXiv   pre-print
In terms of loss function for open-set speaker verification, to get more discriminative speaker embedding, center loss and angular softmax loss is introduced in the end-to-end system.  ...  First, a unified and interpretable end-to-end system for both speaker and language recognition is developed. It accepts variable-length input and produces an utterance level result.  ...  He gives insightful advice on the implementation of end-to-end discriminative loss. This research was funded in part by the National Natural Science  ... 
arXiv:1804.05160v1 fatcat:5ar3oyo23zb5hcnrhozpvpx6cq

Statistics of Pairwise Co-occurring Local Spatio-temporal Features for Human Action Recognition [chapter]

Piotr Bilinski, Francois Bremond
2012 Lecture Notes in Computer Science  
Using two benchmark datasets for human action recognition, we demonstrate that our representation enhances the discriminative power of features and improves action recognition performance.  ...  The bag-of-words approach with local spatio-temporal features have become a popular video representation for action recognition in videos.  ...  Local spatio-temporal features have recently become a very popular video representation for action recognition. They have demonstrated promising recognition results for a number of action classes.  ... 
doi:10.1007/978-3-642-33863-2_31 fatcat:ksm5kwvt4rc7fott5r5st5njwy

Sparse Graphical Representation based Discriminant Analysis for Heterogeneous Face Recognition [article]

Chunlei Peng, Xinbo Gao, Nannan Wang, Jie Li
2016 arXiv   pre-print
In this paper, we propose a novel sparse graphical representation based discriminant analysis (SGR-DA) approach to address aforementioned face recognition in heterogeneous scenarios.  ...  To handle the complex facial structure and further improve the discriminability, a spatial partition-based discriminant analysis framework is presented to refine the adaptive sparse vectors for face matching  ...  The open source face recognition algorithm OpenBR is developed for general face recognition and it performed poorly on the composite sketches (a rank-50 accuracy of 2.55%).  ... 
arXiv:1607.00137v1 fatcat:tlgxc5ahrzgm7nil2jwhqo6nwu

Region-Based Facial Expression Recognition in Still Images

Gawed M. Nagi, Rahmita O.K. Rahmat, Fatimah Khalid, Muhamad Taufik
2013 Journal of Information Processing Systems  
In Facial Expression Recognition Systems (FERS), only particular regions of the face are utilized for discrimination.  ...  Then, LBP is applied to these image files for facial texture representation and a feature-vector per subject is obtained by concatenating the resulting LBP histograms of the decomposed region-based features  ...  Zhao & Zhang (2011) proposed LBP for facial expression representation and kernel discriminant isometric mapping (KDIsomap) for producing the low-dimensional discriminant embedded data representations  ... 
doi:10.3745/jips.2013.9.1.173 fatcat:zogb4mkry5gx5n6mr4gdiwv7be

Identity Management in Face Recognition Systems [chapter]

Massimo Tistarelli, Enrico Grosso
2008 Lecture Notes in Computer Science  
Face recognition is one of the most challenging biometric modalities for personal identification.  ...  Data dimensionality reduction, compactness of the representation, uniqueness of the template and ageing effects, are just but a few of the issues to be addressed.  ...  In the bunch graph structure for every node a set of Gabor jets is computed for different instances of a face (e.g., with mouth open or closed, etc.).  ... 
doi:10.1007/978-3-540-89991-4_8 fatcat:qtaifrlzmnaw5mbnkx52hdagay

Discriminative FaceTopics for face recognition via latent Dirichlet allocation

Tejas Indulal Dhamecha, Praneet Sharma, Richa Singh, Mayank Vatsa
2016 2016 IEEE Winter Conference on Applications of Computer Vision (WACV)  
Further, linear discriminant analysis is utilized to obtain discriminative FaceTopics which are more suitable for classification tasks.  ...  In this paper, we introduce this modeling technique for face recognition, by making an analogy between the two domains.  ...  These topic features are transformed into discriminative topic feature representation that makes the features more suitable for classification (face recognition) task.  ... 
doi:10.1109/wacv.2016.7477451 dblp:conf/wacv/DhamechaSSV16 fatcat:m6m4bpbu4ng6hjyynqc7khg57u

A Novel Distribution of Local Invariant Features for Classification of Scene and Object Categories [chapter]

LiJun Guo, JieYu Zhao, Rong Zhang
2010 IFIP Advances in Information and Communication Technology  
A new image representation based on distribution of local invariant features to be used in a discriminative approach to image categorization is presented.  ...  The PS representation retains high discriminative power of PDF model, and is suited for measuring dissimilarity of images with Earth Mover's Distance (EMD), which allows for partial matches of compared  ...  However, the image representation produced by local features is an unordered set of feature vectors, one for each interest point found in the image.  ... 
doi:10.1007/978-3-642-16327-2_37 fatcat:nxhwpi5jsjfjvk5dvf5llj5upe

OpenGAN: Open-Set Recognition via Open Data Generation [article]

Shu Kong, Deva Ramanan
2021 arXiv   pre-print
Two conceptually elegant ideas for open-set discrimination are: 1) discriminatively learning an open-vs-closed binary discriminator by exploiting some outlier data as the open-set, and 2) unsupervised  ...  In K-way classification, this is crisply formulated as open-set recognition, core to which is the ability to discriminate open-set data outside the K closed-set classes.  ...  Acknowledgement This work was supported by the CMU Argo AI Center for Autonomous Vehicle Research.  ... 
arXiv:2104.02939v3 fatcat:kunevlgjorfedkhvhekwubjnqu

MMF: A loss extension for feature learning in open set recognition [article]

Jingyun Jia, Philip K. Chan
2021 arXiv   pre-print
Open set recognition (OSR) is the problem of classifying the known classes, meanwhile identifying the unknown classes when the collected samples cannot exhaust all the classes.  ...  Our contributions include: First, we introduce an extension that can be incorporated into different loss functions to find more discriminative representations.  ...  Hassen and Chan [5] propose ii loss for open set recognition.  ... 
arXiv:2006.15117v2 fatcat:yty7dop6fze57owfhdzpu6joay

Multiview discriminative learning for age-invariant face recognition

Diana Sungatullina, Jiwen Lu, Gang Wang, Pierre Moulin
2013 2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)  
information can be boosted for recognition.  ...  Then, we develop a discriminative learning method with multiview feature representations, called MDL, to project different types of local features into a latent discriminative subspace where the intraclass  ...  ACKNOWLEDGEMENT This work is supported by the research grant for the Human Sixth Sense Program at the Advanced Digital Sciences Center (ADSC) from the Agency for Science, Technology and Research (A*STAR  ... 
doi:10.1109/fg.2013.6553724 dblp:conf/fgr/SungatullinaLWM13 fatcat:h5l6namqmbdabkgagsz43qw2sm

Spatio-Temporal Representation Matching-based Open-set Action Recognition by Joint Learning of Motion and Appearance

Yongsang Yoon, Jongmin Yu, Moongu Jeon
2019 IEEE Access  
In this paper, we propose the spatio-temporal representation matching (STRM) for video-based action recognition under the open-set condition.  ...  We set the experimental protocol for open-set action recognition and carried out experiments on UCF101 and HMDB51 to evaluate STRM.  ...  recognition methods for closed-set and open-set conditions.  ... 
doi:10.1109/access.2019.2953455 fatcat:knlfdwfefvgv3d4cuwzssneuiu

Conditional Variational Capsule Network for Open Set Recognition [article]

Yunrui Guo, Guglielmo Camporese, Wenjing Yang, Alessandro Sperduti, Lamberto Ballan
2021 arXiv   pre-print
In open set recognition, a classifier has to detect unknown classes that are not known at training time.  ...  In order to recognize new categories, the classifier has to project the input samples of known classes in very compact and separated regions of the features space for discriminating samples of unknown  ...  Finally, we would like to thank the anonymous reviewers for their valuable comments and suggestions.  ... 
arXiv:2104.09159v2 fatcat:khhxdd4eyfhwtmcfzlvaebhlq4
« Previous Showing results 1 — 15 out of 128,549 results