Filters








217 Hits in 6.0 sec

Local compressed convex spectral embedding for bird species identification

Anshul Thakur, Vinayak Abrol, Pulkit Sharma, Padmanabhan Rajan
2018 Journal of the Acoustical Society of America  
The framework takes audio recordings of bird vocalizations and produces compressed convex spectral embeddings (CCSE).  ...  This paper proposes a multi-layer alternating sparseÀdense framework for bird species identification.  ...  Local compressed convex spectral embedding for bird species identification This paper proposes a multi-layer alternating sparseÀdense framework for bird species identification.  ... 
doi:10.1121/1.5042241 pmid:29960469 fatcat:rktstunw2re7zk3ylqv26uyxeq

Multiscale CNN based Deep Metric Learning for Bioacoustic Classification: Overcoming Training Data Scarcity Using Dynamic Triplet Loss [article]

Anshul Thakur, Daksh Thapar, Padmanabhan Rajan, Aditya Nigam
2019 arXiv   pre-print
This paper proposes multiscale convolutional neural network (CNN)-based deep metric learning for bioacoustic classification, under low training data conditions.  ...  A dynamic triplet loss is employed in the proposed CNN architecture to learn a transformation from the input space to the embedding space, where classification is performed.  ...  ACKNOWLEDGMENTS The authors thank Dr Vincent Lostanlen for helpful discussions on data augmentation in context of bioacoustics and bird vocalizations.  ... 
arXiv:1903.10713v2 fatcat:rhvrv4zjc5ep3eqgijebbfd4bq

Real-time classification via sparse representation in acoustic sensor networks

Bo Wei, Mingrui Yang, Yiran Shen, Rajib Rana, Chun Tung Chou, Wen Hu
2013 Proceedings of the 11th ACM Conference on Embedded Networked Sensor Systems - SenSys '13  
The key component of Sparse Approximation based Classification (SAC),'1 minimization, is a convex optimization problem, and is known to be computationally expensive.  ...  Therefore, we propose several techniques to reduce the size of the problem, so as to fit SAC for in-network classification in ASNs.  ...  Pedro José Marrón, and the anonymous reviewers for their helpful feedbacks on earlier versions of this paper.  ... 
doi:10.1145/2517351.2517357 dblp:conf/sensys/WeiYSRCH13 fatcat:iqogwxrt3va3nonbctyzlwujae

2019 Index IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Vol. 12

2019 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
Gleason, S., +, JSTARS Jan. 2019 37-49 Embedded systems Real-Time Hyperspectral Image Compression Onto Embedded GPUs.  ...  Tobin, K.J., +, JSTARS Sept. 2019 3351-3365 Data compression Real-Time Hyperspectral Image Compression Onto Embedded GPUs.  ...  Interference Spectral  ... 
doi:10.1109/jstars.2020.2973794 fatcat:sncrozq3fjg4bgjf4lnkslbz3u

A Two-Level Sound Classification Platform for Environmental Monitoring

Stelios A. Mitilineos, Stelios M. Potirakis, Nicolas-Alexander Tatlas, Maria Rangoussi
2018 Journal of Sensors  
sounds for the anthropogenic sound class; bird, dog, and snake sounds for the biophysical sound class; and fire, waterfall, and gale for the geophysical sound class.  ...  automatic classification.  ...  For example, often we are not interested in identifying a specific bird species or subspecies but rather identify whether or not birds are present at a specific point of an area.  ... 
doi:10.1155/2018/5828074 fatcat:5kkhyjk7ijgeblctejqlz3sxri

Rethinking Positive Sampling for Contrastive Learning with Kernel [article]

Benoit Dufumier, Carlo Alberto Barbano, Robin Louiset, Edouard Duchesnay, Pietro Gori
2022 arXiv   pre-print
We draw a connection between contrastive learning and the conditional mean embedding theory to derive tight bounds on the downstream classification loss.  ...  While efficient augmentations have been found for standard vision datasets, such as ImageNet, it is still an open problem in other applications, such as medical imaging, or in datasets with easy-to-learn  ...  CUB-200-2011 contains 11788 images of 200 bird species with 312 binary attributes available (encoding size, wing shape, color, etc.).  ... 
arXiv:2206.01646v1 fatcat:grqlyarvajexjjzaaabbjx6xl4

Machine learning in acoustics: theory and applications [article]

Michael J. Bianco, Peter Gerstoft, James Traer, Emma Ozanich, Marie A. Roch, Sharon Gannot, Charles-Alban Deledalle
2019 arXiv   pre-print
ML is a broad family of techniques, which are often based in statistics, for automatically detecting and utilizing patterns in data.  ...  Deep CNNs have been used for bat species identification 203 and have become one of the dominant types of recognizers for bird species identification since the successful introduction of CNNs in the LifeCLEF  ...  GMMs have been used to capture statistical variation of spectral parameters of the calls of toothed whales 58 and sequence information has been exploited with hidden Markov models for classifying bird  ... 
arXiv:1905.04418v3 fatcat:xuhykqhrk5bqbg5x7gaajcksay

MARVEL - D3.1: Multimodal and privacy-aware audio-visual intelligence – initial version

Alexandros Iosifidis
2022 Zenodo  
as methodologies for improving the training and efficiency of AI models under supervised, unsupervised, and cross-modal contrastive learning settings.  ...  These include methods for Sound Event De- tection, Sound Event Localisation and Detection, Automated Audio Captioning, Visual Anomaly Detection, Visual Crowd Counting, Audio-Visual Crowd Counting, as well  ...  Such scalability features allow for extreme model compression and optimisation, while decoupling parameter count and computational cost in alignment with the harware-aware scaling paradigm.  ... 
doi:10.5281/zenodo.6821317 fatcat:eia7rkk5lfbg7khs3qcat5qd3m

Multi-Sensor Fusion via Reduction of Dimensionality [article]

Alon Schclar
2012 arXiv   pre-print
The proposed method is utilized for: (a) segmentation and detection of anomalies in hyper-spectral images; (b) segmentation of multi-contrast MRI images; and (c) segmentation of video sequences.  ...  We also present algorithms for: (a) the characterization of materials using their spectral signatures to enable their identification; (b) detection of vehicles according to their acoustic signatures; and  ...  Figure 1 .1 illustrates a hyper-spectral image, which is also referred as a hyper-spectral cube (see Chapter 5) . The image is a birds-eye view of Washington DC mall, USA, and its surroundings.  ... 
arXiv:1211.2863v1 fatcat:rtqwctr4ynghpd2jblcvfvgpuq

Kızılgerdan Kuş Popülasyonu Kayıtlarının Takibi İçin Kuş Sesi Tanıma Yöntemi Geliştirilmesi

Selim ARAS, Seda ÜSTÜN ERCAN
2020 Düzce Üniversitesi Bilim ve Teknoloji Dergisi  
ABSTRACT In this study, suitable features and classification methods were investigated to determine the four subspecies of Robin birds population from their bioacoustic characteristics.  ...  Mel Frequency Cepstrum Coefficients were taken as basis for the determination of the features and a suitable feature search was performed by using statistical parameters from these coefficients.  ...  Rajan, "Local Compressed Convex Spectral Embedding for Bird Species Identification," The Journal of the Acoustical Society of America, c. 143(6), ss. 3819-3828, 2018.  ... 
doi:10.29130/dubited.569642 fatcat:nr22nj5xgbeufkgzqyilzyadzi

ProLFA: Representative Prototype Selection for Local Feature Aggregation [article]

Xingxing Zhang, Zhenfeng Zhu, Yao Zhao
2019 arXiv   pre-print
images from 200 bird species.  ...  Each species has approximately 30 images for training and 30 for testing. Totally, there are 5994 training images and 5794 test images.  ... 
arXiv:1910.11010v1 fatcat:bppdyqcdrjerffy4qdoissk2ha

Learning Neural Textual Representations for Citation Recommendation

Binh Thanh Kieu, Inigo Jauregi Unanue, Son Bao Pham, Hieu Xuan Phan, Massimo Piccardi
2021 2020 25th International Conference on Pattern Recognition (ICPR)  
Acoustic Identification of Bird Species in Non-Stationary Environments DAY 2 -Jan 13, 2021 Morra, Lia; Piano, Luca; Lamberti, Fabrizio; Tommasi, Tatiana 404 Bridging the Gap between Natural and  ...  Generation of Bird Species Using Generative Adversarial Networks DAY 3 -Jan 14, 2021 Zhao, Kaikai; Imaseki, Takashi; Mouri, Hiroshi; Suzuki, Einoshin; Matsukawa, Tetsu 796 From Certain to Uncertain  ... 
doi:10.1109/icpr48806.2021.9412725 fatcat:3vge2tpd2zf7jcv5btcixnaikm

Feature Pyramid Hashing [article]

Yifan Yang, Libing Geng, Hanjiang Lai, Yan Pan, Jian Yin
2019 arXiv   pre-print
In recent years, deep-networks-based hashing has become a leading approach for large-scale image retrieval.  ...  To this end, we propose a novel two-pyramid hashing architecture to learn both the semantic information and the subtle appearance details for fine-grained image search.  ...  to 120 species aimed at fine-grained image tasks.  ... 
arXiv:1904.02325v1 fatcat:wjp6syjdufd5pezneepvglifaa

Design of large polyphase filters in the Quadratic Residue Number System

Gian Carlo Cardarilli, Alberto Nannarelli, Yann Oster, Massimo Petricca, Marco Re
2010 2010 Conference Record of the Forty Fourth Asilomar Conference on Signals, Systems and Computers  
Speech, Image and Video Processing Session: Mpa7 -Video Compression Mp7a-1 1:30 pM Spectral Entropy- Track 1 -A.  ...  We show that the non-convex sum-rate maximization problem becomes convex under some simplifying assumptions.  ... 
doi:10.1109/acssc.2010.5757589 fatcat:ccxnu5owr5fyrcjcqukumerueq

Book reports

2002 Computers and Mathematics with Applications  
Birds and bees. 6. Evolving eomlexity. Ant smarts, Complex adaptive systems. E-volution. Species of origin. MOrphing. Punctuation. 7. Screening information. How this book is being written.  ...  Compression schemes and generalization error. 5.2.2. On-line learning and compression schemes. 5.3. Algorithmic stability bounds. 5.3.1. Algorithmic stability for regression. 5.3.2.  ... 
doi:10.1016/s0898-1221(02)00272-9 fatcat:dlkuzp6p5nbilivckq5ezj5cbe
« Previous Showing results 1 — 15 out of 217 results