{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:34:02Z","timestamp":1730266442096,"version":"3.28.0"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9892839","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T15:56:04Z","timestamp":1664553364000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["Investigation of Performance of Visual Attention Mechanisms for Environmental Sound Classification: A Comparative Study"],"prefix":"10.1109","author":[{"given":"Achyut Mani","family":"Tripathi","sequence":"first","affiliation":[{"name":"Indian Institute of Technology Guwahati,Department of Computer Science & Engineering,Guwahati,Assam,India,781039"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Swarup Ranjan","family":"Behera","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Guwahati,Department of Computer Science & Engineering,Guwahati,Assam,India,781039"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Konark","family":"Paul","sequence":"additional","affiliation":[{"name":"Independent Researcher,Banguluru,Karnataka,India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2020.107413"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1253"},{"journal-title":"S-2mlpv2 Improved spatial-shift mlp architecture for vision","year":"2021","author":"yu","key":"ref33"},{"journal-title":"CoAtNet Marrying convolution and attention for all data sizes","year":"2021","author":"dai","key":"ref32"},{"journal-title":"Polarized Self-Attention Towards High-quality Pixel-wise Regression","year":"2021","author":"liu","key":"ref31"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414568"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2017.08.250"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01350"},{"journal-title":"Non-deep networks","year":"2021","author":"goyal","key":"ref35"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00318"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-440"},{"key":"ref40","article-title":"Wavelet based mel-scaled features for dcase 2019 task la and task 1b","author":"waldekar","year":"2019","journal-title":"Tech Rep DCASE2019 Challenge Tech Rep"},{"key":"ref11","article-title":"Self-attention mechanism based system for dcase2018 challenge task1 and task4","author":"wang","year":"2018","journal-title":"IEEE AASP Challenge on DCASE 2018 technical reports"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2939495"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413498"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3034230"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2019.00074"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"107101","DOI":"10.1016\/j.asoc.2021.107101","article-title":"Att-net: Enhanced emotion recognition system using lightweight self-attention module","volume":"102","author":"kwon","year":"2021","journal-title":"Applied Soft Computing"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351090"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.3390\/app10062020","article-title":"A review of deep learning based methods for acoustic scene classification","volume":"10","author":"abe\u00dfer","year":"2020","journal-title":"Applied Sciences"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"journal-title":"Spatial group-wise enhance Improving semantic feature learning in convolutional networks","year":"2019","author":"li","key":"ref28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1219"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00060"},{"key":"ref3","article-title":"Acoustic scene and event recognition using recurrent neural networks","volume":"2016","author":"vu","year":"2016","journal-title":"Detection and Classification of Acoustic Scenes and Events"},{"journal-title":"Acoustic scene classification based on deep convolutional neuralnetwork with spatial-temporal attention pooling","year":"2019","author":"zhenyi","key":"ref6"},{"key":"ref29","article-title":"Eca-net: efficient channel attention for deep convolutional neural networks, 2020 ieee","author":"wang","year":"2020","journal-title":"CVF Conference on Computer Vision and Pattern Recognition (CVPR) IEEE"},{"journal-title":"Self-attention mechanism based system for dcase 2018 challenge task 1 and task 4","year":"2018","author":"wang","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683434"},{"key":"ref7","article-title":"Acoustic scene classification based on deep convolutional neuralnetwork with spatial-temporal attention pooling","author":"huang","year":"2019","journal-title":"DCASE2019 Challenge Tech Rep"},{"key":"ref2","first-page":"1","article-title":"Environmental sound classification with convolutional neural networks","author":"piczak","year":"2015","journal-title":"Machine Learning for Signal Processing (MLSP) 2015 IEEE 25th International Workshop on"},{"key":"ref9","article-title":"Attention based convolutional recurrent neural network for environmental sound classification","author":"zhang","year":"2020","journal-title":"Neurocomputing"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178031"},{"key":"ref46","article-title":"Stratified time-frequency features for cnn-based acoustic scene classification","author":"wu","year":"2019","journal-title":"Tech Rep DCASE2016 Challenge"},{"journal-title":"AST Audio Spectrogram Transformer","year":"2021","author":"gong","key":"ref20"},{"key":"ref45","article-title":"Acoustic scene classification using specaugment and convolutional neural network with inception modules","author":"sangwon","year":"2019","journal-title":"DCASE2019 Challenge Tech Rep"},{"key":"ref48","article-title":"Acoustic scene classification using various pre-processed features and convolutional neural networks","author":"hyeji","year":"2019","journal-title":"DCASE2019 Challenge Tech Rep June"},{"journal-title":"An image is worth 16x16 words Transformers for image recognition at scale","year":"2020","author":"dosovitskiy","key":"ref22"},{"key":"ref47","article-title":"Acoustic scene classification and audio tagging with receptive-field-regularized CNNs","author":"koutini","year":"2019","journal-title":"DCASE2019 Challenge Tech Rep June"},{"journal-title":"Ssast Self-supervised audio spectrogram transformer","year":"2021","author":"gong","key":"ref21"},{"key":"ref42","article-title":"DCASE 2019 task la: Acoustic scene classification by sffcc and DNN","author":"paseddula","year":"2019","journal-title":"DCASE2019 Challenge Tech Rep"},{"key":"ref24","first-page":"9","article-title":"A multi-device dataset for urban acoustic scene classification","author":"mesaros","year":"2019","journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events 2019 Workshop (DCASE2019)"},{"key":"ref41","article-title":"Audio scene calssification based on deeper CNN and mixed mono channel feature","author":"zhou","year":"2019","journal-title":"DCASE2019 Challenge Tech Rep"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref44","article-title":"Cdnn-CRNN joined model for acoustic scene classification","author":"pham","year":"2019","journal-title":"DCASE2019 Challenge Tech Rep"},{"key":"ref26","first-page":"3","article-title":"Cbam: Convolutional block attention module","author":"woo","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref43","article-title":"Jsnu_wdxy submission for DCASE-2019: Acoustic scene classification with convolution neural networks","author":"ma","year":"2019","journal-title":"DCASE2019 Challenge Tech Rep"},{"key":"ref25","first-page":"7132","article-title":"Squeeze-and-excitation networks","author":"hu","year":"2018","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"}],"event":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2022,7,18]]},"location":"Padua, Italy","end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9891857\/9889787\/09892839.pdf?arnumber=9892839","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T18:57:01Z","timestamp":1667501821000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9892839\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9892839","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}