@article{bb386300,
AUTHOR = "Zhang, Z. and Wen, F.Q. and Shi, J.P. and He, J. and Truong, T.K.",
TITLE = "2D-DOA Estimation for Coherent Signals via a Polarized Uniform
Rectangular Array",
JOURNAL = SPLetters,
VOLUME = "30",
YEAR = "2023",
PAGES = "893-897",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380367"}
@article{bb386301,
AUTHOR = "Bando, Y. and Sekiguchi, K. and Masuyama, Y. and Nugraha, A.A. and Fontaine, M. and Yoshii, K.",
TITLE = "Neural Full-Rank Spatial Covariance Analysis for Blind Source
Separation",
JOURNAL = SPLetters,
VOLUME = "28",
YEAR = "2021",
PAGES = "1670-1674",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380368"}
@article{bb386302,
AUTHOR = "Munakata, H. and Bando, Y. and Takeda, R. and Komatani, K. and Onishi, M.",
TITLE = "Joint Separation and Localization of Moving Sound Sources Based on
Neural Full-Rank Spatial Covariance Analysis",
JOURNAL = SPLetters,
VOLUME = "30",
YEAR = "2023",
PAGES = "384-388",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380369"}
@article{bb386303,
AUTHOR = "Zhu, G. and Darefsky, J. and Jiang, F. and Selitskiy, A. and Duan, Z.Y.",
TITLE = "Music Source Separation With Generative Flow",
JOURNAL = SPLetters,
VOLUME = "29",
YEAR = "2022",
PAGES = "2288-2292",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380370"}
@article{bb386304,
AUTHOR = "Hu, D. and Chen, Z. and Yin, F.",
TITLE = "Acoustic SLAM With Moving Sound Event Based on Auxiliary Microphone
Arrays",
JOURNAL = ITS,
VOLUME = "24",
YEAR = "2023",
NUMBER = "11",
MONTH = "November",
PAGES = "11823-11834",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380371"}
@article{bb386305,
AUTHOR = "Liu, D. and Zhang, T.Q. and Christensen, M.G. and Yi, C. and Wei, Y.",
TITLE = "Multi-layer encoder-decoder time-domain single channel speech
separation",
JOURNAL = PRL,
VOLUME = "181",
YEAR = "2024",
PAGES = "86-91",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380372"}
@article{bb386306,
AUTHOR = "Sun, D.J. and Fu, X.Y. and Teng, T.T.",
TITLE = "A Deep Learning Localization Method for Acoustic Source via Improved
Input Features and Network Structure",
JOURNAL = RS,
VOLUME = "16",
YEAR = "2024",
NUMBER = "8",
PAGES = "1391",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380373"}
@article{bb386307,
AUTHOR = "Hu, K.Y. and Chu, N. and Yu, L. and Jiang, H. and Mohammad Djafari, A.",
TITLE = "A Separation-Based Localization Method Between Rotating and Static
Sources",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "1359-1363",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380374"}
@article{bb386308,
AUTHOR = "Juanola, X. and Haro, G.",
TITLE = "A Brief Analysis of SLAVC method for Sound Source Localization",
JOURNAL = IPOL,
VOLUME = "14",
YEAR = "2024",
PAGES = "159-172",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380375"}
@article{bb386309,
AUTHOR = "Akhter, S. and Alam, M.M. and Islam, M.S. and Momen, M.A. and Islam, M.S. and Shoyaib, M.",
TITLE = "Low-cost orthogonal basis-core extraction for classification and
reconstruction using tensor ring",
JOURNAL = PR,
VOLUME = "154",
YEAR = "2024",
PAGES = "110548",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380376"}
@article{bb386310,
AUTHOR = "Ge, Y. and Meng, W.X. and Li, X.D. and Zheng, C.S.",
TITLE = "Geometry Calibration for Deformable Linear Microphone Arrays With
Bézier Curve Fitting",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "1620-1624",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380377"}
@article{bb386311,
AUTHOR = "Lu, Y.L. and Pan, C. and Chen, J.D. and Benesty, J.",
TITLE = "A Closed-Form DOA Estimator Using Spherical Microphone Arrays in the
Presence of Interference",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "1770-1774",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380378"}
@article{bb386312,
AUTHOR = "Zhu, B. and Zhang, W. and Chen, J.D. and Zhu, M.Y. and Li, C.J.",
TITLE = "Multi-Source DOA Estimation Using Higher-Order Pseudo Intensity
Vector on a Spherical Microphone Array",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "1935-1939",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380379"}
@article{bb386313,
AUTHOR = "Elminshawi, M. and Chetupalli, S.R. and Habets, E.A.P.",
TITLE = "Dynamic Slimmable Network for Speech Separation",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "2205-2209",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380380"}
@article{bb386314,
AUTHOR = "Zhang, W.J. and Yu, P. and Yin, J. and Jiang, X.H. and Xu, M.L.",
TITLE = "Automated Audio Data Augmentation Network Using Bi-Level Optimization
for Sound Event Localization and Detection",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "2770-2774",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380381"}
@article{bb386315,
AUTHOR = "Xie, J.L. and Zhao, X.D. and Zhang, J.Q. and Benesty, J. and Chen, J.D.",
TITLE = "On the Design of Robust Differential Beamformers From the Beampattern
Error Perspective",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "2685-2689",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380382"}
@article{bb386316,
AUTHOR = "Song, Z.J. and Zhang, J.S. and Wang, Y.X. and Fan, J.S. and Zhang, Z.X.",
TITLE = "Enhancing Sound Source Localization via False Negative Elimination",
JOURNAL = PAMI,
VOLUME = "46",
YEAR = "2024",
NUMBER = "12",
MONTH = "December",
PAGES = "10499-10514",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380383"}
@article{bb386317,
AUTHOR = "Guo, J.Y. and Wang, C.X. and Xu, J. and Jia, S. and Yang, H. and Sun, Z. and Wang, X.B.",
TITLE = "Study and Analysis of the Thunder Source Location Error Based on
Acoustic Ray-Tracing",
JOURNAL = RS,
VOLUME = "16",
YEAR = "2024",
NUMBER = "21",
PAGES = "4000",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380384"}
@article{bb386318,
AUTHOR = "Lu, X. and Li, G.N. and Song, X.Q. and Zhou, L.C. and Lv, G.N.",
TITLE = "Concept, Framework, and Data Model for Geographical Soundscapes",
JOURNAL = IJGI,
VOLUME = "14",
YEAR = "2025",
NUMBER = "1",
PAGES = "36",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380385"}
@article{bb386319,
AUTHOR = "Qian, X.Y. and Yue, X. and Wang, J. and Zhuang, H.P. and Li, H.Z.",
TITLE = "Analytic Class Incremental Learning for Sound Source Localization
With Privacy Protection",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "726-730",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380386"}
@article{bb386320,
AUTHOR = "Koldovsky, Z. and Cmejla, J. and O'Regan, S.",
TITLE = "Blind Capon Beamformer Based on Independent Component Extraction:
Single-Parameter Algorithm",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "801-805",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380387"}
@article{bb386321,
AUTHOR = "Strauss, M. and Mack, W. and Valero, M.L. and Kopuklu, O.",
TITLE = "Inference-Adaptive Steering of Neural Networks for Real-Time
Area-Based Sound Source Separation",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "1041-1045",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380388"}
@article{bb386322,
AUTHOR = "Chen, W.G. and Zhang, J.J. and Yang, J.L. and Chng, E.S. and Zhong, X.H.",
TITLE = "UniArray: Unified Spectral-Spatial Modeling for
Array-Geometry-Agnostic Speech Separation",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "2164-2168",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380389"}
@article{bb386323,
AUTHOR = "Rybicka, M. and Kowalczyk, K. and Thebaud, T. and Dehak, N. and Villalba, J.",
TITLE = "Joint Diarization and Separation Using SepFormer With
Non-Autoregressive Attractors",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "2913-2917",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380390"}
@article{bb386324,
AUTHOR = "Zhang, S. and Zhang, J. and Wang, Y. and Yan, H.Y.",
TITLE = "DOA or Speaker Embedding: Which is Better for Multi-Microphone Target
Speaker Extraction",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "3350-3354",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380391"}
@article{bb386325,
AUTHOR = "Chen, Y.J. and Xiao, Y. and Yin, H. and Guan, Y.D. and Liu, X.",
TITLE = "Noise-Robust Sound Event Detection and Counting via Language-Queried
Sound Separation",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "3974-3978",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380392"}
@article{bb386326,
AUTHOR = "Xiang, M. and Liang, R. and Ni, Y. and Zhao, L. and Schuller, B.W.",
TITLE = "Lightweight Attentive ConvNeXt-TCN for Causal Target Sound Extraction",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "4234-4238",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380393"}
@article{bb386327,
AUTHOR = "Huang, C. and Liang, S. and Tian, Y.P. and Kumar, A. and Xu, C.L.",
TITLE = "High-Quality Sound Separation Across Diverse Categories via
Visually-Guided Generative Modeling",
JOURNAL = IJCV,
VOLUME = "134",
YEAR = "2026",
NUMBER = "1",
MONTH = "January",
PAGES = "104",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380394"}
@inproceedings{bb386328,
AUTHOR = "Huang, C. and Liang, S. and Tian, Y.P. and Kumar, A. and Xu, C.L.",
TITLE = "High-quality Visually-guided Sound Separation from Diverse Categories",
BOOKTITLE = ACCV24,
YEAR = "2024",
PAGES = "VI: 104-122",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380395"}
@article{bb386329,
AUTHOR = "Park, S. and Senocak, A. and Chung, J.S.",
TITLE = "Hearing and Seeing Through CLIP: A Framework for Self-Supervised Sound
Source Localization",
JOURNAL = IJCV,
VOLUME = "134",
YEAR = "2026",
NUMBER = "4",
MONTH = "April",
PAGES = "179",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380396"}
@article{bb386330,
AUTHOR = "Berghi, D. and Jackson, P.J.B.",
TITLE = "Reverberation-Based Features for Sound Event Localization and
Detection With Distance Estimation",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "1841-1845",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380397"}
@article{bb386331,
AUTHOR = "Yeow, J.W. and Tan, E.L. and Peksi, S. and Gan, W.S.",
TITLE = "WINTER: Wrapped Interval Normalization for Elevation Representation
in Stereo 3-D Sound Event Localization and Detection",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "1851-1855",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380398"}
@article{bb386332,
AUTHOR = "Luo, L.J. and Wu, J. and Fan, L.C. and Luo, Z.B. and Luan, J. and Hong, Q.Y. and Li, L.",
TITLE = "ZoneSep: A Lightweight End-to-End Neural Beamformer With Post-Mask
Decoder for In-Vehicle Multi-Zone Speech Separation",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "2575-2579",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380399"}
@article{bb386333,
AUTHOR = "Shi, Y. and Han, J.Q.",
TITLE = "Dual-Path Conditional Chain for CTC-Based Multi-Talker Speech
Recognition",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "2570-2574",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380400"}
@article{bb386334,
AUTHOR = "Liang, Y.F. and Li, A.D. and Li, X.D. and Zheng, C.",
TITLE = "OmniControl: Unified Audio Extraction and Elimination via
Subband-Aware Separation",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "2914-2918",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380401"}
@article{bb386335,
AUTHOR = "Sakurai, S. and Bando, Y. and Imoto, K. and Onishi, M.",
TITLE = "General-Purpose Audio-Visual Sounding Object Localization Based on
Semi-Automatic Annotation",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "2949-2953",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380402"}
@article{bb386336,
AUTHOR = "Xu, Y. and Tao, X.Y.",
TITLE = "Soft-VAP: A Learned Decoder for Frozen Voice Activity Projection
States",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "3192-3196",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380403"}
@article{bb386337,
AUTHOR = "Massi, O. and Miotello, F. and Albertini, D. and Bernardini, A.",
TITLE = "Differential Beamforming With Planar Arrays of Arbitrary-Order
Directional Elements",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "3352-3356",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380404"}
@article{bb386338,
AUTHOR = "Wang, Y. and Yang, B. and Li, X.F.",
TITLE = "IPDnet2A: An Efficient Direct-Path IPD Estimation Network for
Arbitrary Array Geometries",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "3781-3785",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380405"}
@inproceedings{bb386339,
AUTHOR = "Liu, X.L. and Kumar, A. and Calamia, P. and Amengual, S.V. and Murdock, C. and Ananthabhotla, I. and Robinson, P. and Shlizerman, E. and Ithapu, V.K. and Gao, R.H.",
TITLE = "Hearing Anywhere in Any Environment",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "5732-5741",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380406"}
@inproceedings{bb386340,
AUTHOR = "Min, A. and Chen, Z.Y. and Zhao, H. and Owens, A.",
TITLE = "Supervising Sound Localization by In-the-wild Egomotion",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "23936-23946",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380407"}
@inproceedings{bb386341,
AUTHOR = "He, Y.H. and Shin, S. and Cherian, A. and Trigoni, N. and Markham, A.",
TITLE = "SoundLoc3D: Invisible 3D Sound Source Localization and Classification
Using a Multimodal RGB-D Acoustic Camera",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "5408-5418",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380408"}
@inproceedings{bb386342,
AUTHOR = "Shi, D. and Deng, Y.J. and Wei, Y.",
TITLE = "Visually-guided Order-fixed Speech Separation Algorithm",
BOOKTITLE = ICIVC24,
YEAR = "2024",
PAGES = "445-449",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380409"}
@inproceedings{bb386343,
AUTHOR = "Mahmud, T. and Tian, Y.P. and Marculescu, D.",
TITLE = "T-VSL: Text-Guided Visual Sound Source Localization in Mixtures",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "26732-26741",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380410"}
@inproceedings{bb386344,
AUTHOR = "Kim, D.J. and Um, S.J. and Lee, S. and Kim, J.U.",
TITLE = "Learning to Visually Localize Sound Sources from Mixtures without
Prior Source Knowledge",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "26457-26466",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380411"}
@inproceedings{bb386345,
AUTHOR = "Islam, M.A. and Nabavi, S.S. and Kezele, I. and Wang, Y. and Yu, Y.H. and Tang, J.",
TITLE = "Visually Guided Audio Source Separation with Meta Consistency
Learning",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "3002-3011",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380412"}
@inproceedings{bb386346,
AUTHOR = "Park, S. and Senocak, A. and Chung, J.S.",
TITLE = "Can CLIP Help Sound Source Localization?",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "5699-5708",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380413"}
@inproceedings{bb386347,
AUTHOR = "Yun, H. and Na, J. and Kim, G.",
TITLE = "Dense 2D-3D Indoor Prediction with Sound via Aligned Cross-Modal
Distillation",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "7829-7838",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380414"}
@inproceedings{bb386348,
AUTHOR = "Chen, Z.Y. and Qian, S. and Owens, A.",
TITLE = "Sound Localization from Motion: Jointly Learning Sound Direction and
Camera Rotation",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "7863-7874",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380415"}
@inproceedings{bb386349,
AUTHOR = "Senocak, A. and Ryu, H. and Kim, J. and Oh, T.H. and Pfister, H. and Chung, J.S.",
TITLE = "Sound Source Localization is All about Cross-Modal Alignment",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "7743-7753",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380416"}
@inproceedings{bb386350,
AUTHOR = "Ryan, F. and Jiang, H. and Shukla, A. and Rehg, J.M. and Ithapu, V.K.",
TITLE = "Egocentric Auditory Attention Localization in Conversations",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "14663-14674",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380417"}
@inproceedings{bb386351,
AUTHOR = "Mo, S.T. and Tian, Y.P.",
TITLE = "Audio-Visual Grouping Network for Sound Localization from Mixtures",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "10565-10574",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380418"}
@inproceedings{bb386352,
AUTHOR = "Buchanan, C. and Bi, Y. and Xue, B. and Vennell, R. and Childerhouse, S. and Pine, M.K. and Briscoe, D. and Zhang, M.J.",
TITLE = "Deep Convolutional Neural Networks for Detecting Dolphin Echolocation
Clicks",
BOOKTITLE = IVCNZ21,
YEAR = "2021",
PAGES = "1-6",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380419"}
@inproceedings{bb386353,
AUTHOR = "Hu, X. and Chen, Z.Y. and Owens, A.",
TITLE = "Mix and Localize: Localizing Sound Sources in Mixtures",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "10473-10482",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380420"}
@inproceedings{bb386354,
AUTHOR = "Chen, Z.Y. and Fouhey, D.F. and Owens, A.",
TITLE = "Sound Localization by Self-supervised Time Delay Estimation",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXVI:489-508",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380421"}
@inproceedings{bb386355,
AUTHOR = "Zhou, X.C. and Zhou, D.Z. and Hu, D. and Zhou, H. and Ouyang, W.L.",
TITLE = "Exploiting Visual Context Semantics for Sound Source Localization",
BOOKTITLE = WACV23,
YEAR = "2023",
PAGES = "5188-5197",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380422"}
@inproceedings{bb386356,
AUTHOR = "Zhou, X.C. and Zhou, D.Z. and Ouyang, W.L. and Zhou, H. and Hu, D.",
TITLE = "SeCo: Separating Unknown Musical Visual Sounds with Consistency
Guidance",
BOOKTITLE = WACV23,
YEAR = "2023",
PAGES = "5157-5166",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380423"}
@inproceedings{bb386357,
AUTHOR = "Chatterjee, M. and Le Roux, J. and Ahuja, N. and Cherian, A.",
TITLE = "Visual Scene Graphs for Audio Source Separation",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "1184-1193",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380424"}
@inproceedings{bb386358,
AUTHOR = "Senocak, A. and Ryu, H.G. and Kim, J. and Kweon, I.S.",
TITLE = "Less Can Be More: Sound Source Localization With a Classification
Model",
BOOKTITLE = WACV22,
YEAR = "2022",
PAGES = "577-586",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380425"}
@inproceedings{bb386359,
AUTHOR = "Shi, J.Y. and Ma, C.",
TITLE = "Unsupervised Sounding Object Localization with Bottom-Up and Top-Down
Attention",
BOOKTITLE = WACV22,
YEAR = "2022",
PAGES = "2161-2170",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380426"}
@inproceedings{bb386360,
AUTHOR = "Zhu, L.Y. and Rahtu, E.",
TITLE = "V-SlowFast Network for Efficient Visual Sound Separation",
BOOKTITLE = WACV22,
YEAR = "2022",
PAGES = "2182-2192",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380427"}
@inproceedings{bb386361,
AUTHOR = "Cokelek, M. and Imamoglu, N. and Ozcinar, C. and Erdem, E. and Erdem, A.",
TITLE = "Leveraging Frequency Based Salient Spatial Sound Localization to
Improve 360° Video Saliency Prediction",
BOOKTITLE = MVA21,
YEAR = "2021",
PAGES = "1-5",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380428"}
@inproceedings{bb386362,
AUTHOR = "Tanaka, T. and Shinozaki, T.",
TITLE = "Unsupervised Sound Source Localization From Audio-Image Pairs Using
Input Gradient Map",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "6501-6508",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380429"}
@inproceedings{bb386363,
AUTHOR = "Zhu, L.Y. and Rahtu, E.",
TITLE = "Visually Guided Sound Source Separation and Localization using
Self-Supervised Motion Representations",
BOOKTITLE = WACV22,
YEAR = "2022",
PAGES = "2171-2181",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380430"}
@inproceedings{bb386364,
AUTHOR = "Zhu, L.Y. and Rahtu, E.",
TITLE = "Visually Guided Sound Source Separation Using Cascaded Opponent Filter
Network",
BOOKTITLE = ACCV20,
YEAR = "2020",
PAGES = "VI:409-426",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380431"}
@inproceedings{bb386365,
AUTHOR = "Oya, T. and Iwase, S. and Natsume, R. and Itazuri, T. and Yamaguchi, S. and Morishima, S.",
TITLE = "Do We Need Sound for Sound Source Localization?",
BOOKTITLE = ACCV20,
YEAR = "2020",
PAGES = "VI:119-136",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380432"}
@inproceedings{bb386366,
AUTHOR = "Chen, W. and Hu, R.M. and Wang, X.C. and Li, D.S.",
TITLE = "HRTF Representation with Convolutional Auto-encoder",
BOOKTITLE = MMMod20,
YEAR = "2020",
PAGES = "I:605-616",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380433"}
@inproceedings{bb386367,
AUTHOR = "Guan, D.Z. and Li, D.S. and Cai, X.B. and Wang, X.C. and Hu, R.M.",
TITLE = "Perceptual Localization of Virtual Sound Source Based on Loudspeaker
Triplet",
BOOKTITLE = MMMod20,
YEAR = "2020",
PAGES = "II:189-200",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380434"}
@inproceedings{bb386368,
AUTHOR = "Qian, R. and Hu, D. and Dinkel, H. and Wu, M.Y. and Xu, N. and Lin, W.Y.",
TITLE = "Multiple Sound Sources Localization from Coarse to Fine",
BOOKTITLE = ECCV20,
YEAR = "2020",
PAGES = "XX:292-308",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380435"}
@inproceedings{bb386369,
AUTHOR = "San Juan, E. and Firoozabadi, A.D. and Soto, I. and Adasme, P. and Canete, L.",
TITLE = "Proposed Integration Algorithm to Optimize the Separation of Audio
Signals Using the Ica and Wavelet Transform",
BOOKTITLE = ICISP20,
YEAR = "2020",
PAGES = "367-376",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380436"}
@inproceedings{bb386370,
AUTHOR = "Gao, R. and Grauman, K.",
TITLE = "Co-Separating Sounds of Visual Objects",
BOOKTITLE = ICCV19,
YEAR = "2019",
PAGES = "3878-3887",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380437"}
@inproceedings{bb386371,
AUTHOR = "Xu, X. and Dai, B. and Lin, D.",
TITLE = "Recursive Visual Sound Separation Using Minus-Plus Net",
BOOKTITLE = ICCV19,
YEAR = "2019",
PAGES = "882-891",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380438"}
@inproceedings{bb386372,
AUTHOR = "Colangelo, F. and Battisti, F. and Carli, M. and Neri, A. and Calabro, F.",
TITLE = "Enhancing audio surveillance with hierarchical recurrent neural
networks",
BOOKTITLE = AVSS17,
YEAR = "2017",
PAGES = "1-6",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380439"}
@inproceedings{bb386373,
AUTHOR = "Saggese, A. and Strisciuglio, N. and Vento, M. and Petkov, N.",
TITLE = "A real-time system for audio source localization with cheap sensor
device",
BOOKTITLE = AVSS17,
YEAR = "2017",
PAGES = "1-7",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380440"}
@inproceedings{bb386374,
AUTHOR = "Moon, S.K. and Shon, S. and Kim, W. and Han, D.K.",
TITLE = "Generalized cross-correlation based noise robust abnormal acoustic
event localization utilizing non-negative matrix factorization",
BOOKTITLE = AVSS14,
YEAR = "2014",
PAGES = "171-174",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380441"}
@inproceedings{bb386375,
AUTHOR = "Stachurski, J. and Netsch, L. and Cole, R.",
TITLE = "Sound source localization for video surveillance camera",
BOOKTITLE = AVSS13,
YEAR = "2013",
PAGES = "93-98",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380442"}
@inproceedings{bb386376,
AUTHOR = "Zhang, Z.L. and Li, W.H. and Gong, W.G. and Zhong, J.H.",
TITLE = "An improved EEMD model for feature extraction and classification of
gunshot in public places",
BOOKTITLE = ICPR12,
YEAR = "2012",
PAGES = "1517-1520",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380443"}
@inproceedings{bb386377,
AUTHOR = "Lecomte, S. and Lengelle, R. and Richard, C. and Capman, F. and Ravera, B.",
TITLE = "Abnormal events detection using unsupervised One-Class SVM:
Application to audio surveillance and evaluation",
BOOKTITLE = AVSBS11,
YEAR = "2011",
PAGES = "124-129",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380444"}
@inproceedings{bb386378,
AUTHOR = "Salvati, D. and Roda, A. and Canazza, S. and Foresti, G.L.",
TITLE = "Multiple acoustic sources localization using incident Signal Power
comparison",
BOOKTITLE = AVSBS11,
YEAR = "2011",
PAGES = "77-82",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380445"}
@inproceedings{bb386379,
AUTHOR = "Han, Y. and Wu, C.N.",
TITLE = "A new moving sound source localization method based on the time
difference of arrival",
BOOKTITLE = IASP10,
YEAR = "2010",
PAGES = "118-122",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380446"}
@inproceedings{bb386380,
AUTHOR = "Hao, Q.Q. and Li, S.M. and Shen, H. and Lei, Y.B.",
TITLE = "Blind Separation for Cabin Acoustic Signals in Complex Environment",
BOOKTITLE = CISP09,
YEAR = "2009",
PAGES = "1-5",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380447"}
@inproceedings{bb386381,
AUTHOR = "Martens, W.L. and Sakamoto, S. and Suzuki, Y.",
TITLE = "Multimodal interaction of auditory spatial cues and passive observer
movement in simulated self motion",
BOOKTITLE = "3DTV09",
YEAR = "2009",
PAGES = "1-4",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380448"}
@inproceedings{bb386382,
AUTHOR = "Kwak, K.C.",
TITLE = "Sound Localization Based on Excitation Source Information for
Intelligent Home Service Robots",
BOOKTITLE = ICISP08,
YEAR = "2008",
PAGES = "536-543",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380449"}
@inproceedings{bb386383,
AUTHOR = "Munguia, R. and Grau, A.",
TITLE = "Single Sound Source SLAM",
BOOKTITLE = CIARP08,
YEAR = "2008",
PAGES = "70-77",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380450"}
@inproceedings{bb386384,
AUTHOR = "Keyrouz, F. and Diepold, K. and Keyrouz, S.",
TITLE = "High performance 3D sound localization for surveillance applications",
BOOKTITLE = AVSBS07,
YEAR = "2007",
PAGES = "563-566",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380451"}
@inproceedings{bb386385,
AUTHOR = "Valenzise, G. and Gerosa, L. and Tagliasacchi, M. and Antonacci, F. and Sarti, A.",
TITLE = "Scream and gunshot detection and localization for audio-surveillance
systems",
BOOKTITLE = AVSBS07,
YEAR = "2007",
PAGES = "21-26",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380452"}
@inproceedings{bb386386,
AUTHOR = "Antonacci, F. and Riva, D. and Sarti, A. and Tagliasacchi, M. and Tubaro, S.",
TITLE = "Tracking of two acoustic sources in reverberant environments using a
particle swarm optimizer",
BOOKTITLE = AVSBS07,
YEAR = "2007",
PAGES = "567-572",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380453"}
@inproceedings{bb386387,
AUTHOR = "Korhonen, T. and Pertila, P.",
TITLE = "TUT Acoustic Source Tracking System 2007",
BOOKTITLE = MTPH07,
YEAR = "2007",
PAGES = "xx-yy",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380454"}
@inproceedings{bb386388,
AUTHOR = "Marzabal, A. and Grau, A. and Bolea, Y.",
TITLE = "Model-Based Localization Method by Non-speech Sound Via Wavelet
Transform and Dynamic Neural Network",
BOOKTITLE = CIARP06,
YEAR = "2006",
PAGES = "363-370",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020ausrc2.html#TT380455"}
@article{bb386389,
AUTHOR = "Zotkin, D.N. and Duraiswami, R. and Davis, L.S.",
TITLE = "Joint Audio-Visual Tracking Using Particle Filters",
JOURNAL = JASP,
VOLUME = "2002",
YEAR = "2002",
NUMBER = "11",
MONTH = "November",
PAGES = "1154",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT380456"}
@article{bb386390,
AUTHOR = "Garg, A. and Pavlovic, V. and Rehg, J.M.",
TITLE = "Boosted learning in dynamic Bayesian networks for multimodal speaker
detection",
JOURNAL = PIEEE,
VOLUME = "91",
YEAR = "2003",
NUMBER = "9",
MONTH = "September",
PAGES = "1355-1369",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT380457"}
@inproceedings{bb386391,
AUTHOR = "Garg, A. and Pavlovic, V. and Rehg, J.M.",
TITLE = "Audio-visual speaker detection using dynamic Bayesian networks",
BOOKTITLE = AFGR00,
YEAR = "2000",
PAGES = "384-390",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT380458"}
@inproceedings{bb386392,
AUTHOR = "Pavlovic, V. and Garg, A. and Rehg, J.M. and Huang, T.S.",
TITLE = "Multimodal Speaker Detection using Error Feedback Dynamic Bayesian
Networks",
BOOKTITLE = CVPR00,
YEAR = "2000",
PAGES = "II: 34-41",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT380459"}
@inproceedings{bb386393,
AUTHOR = "Pavlovic, V. and Berry, G. and Huang, T.S.",
TITLE = "Integration of Audio/Visual Information for Use in
Human-Computer Intelligent Interaction",
BOOKTITLE = ICIP97,
YEAR = "1997",
PAGES = "I: 121-124",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT380460"}
@inproceedings{bb386394,
AUTHOR = "Choudhury, T. and Rehg, J.M. and Pavlovic, V. and Pentland, A.P.",
TITLE = "Boosting and structure learning in dynamic Bayesian networks for
audio-visual speaker detection",
BOOKTITLE = ICPR02,
YEAR = "2002",
PAGES = "III: 789-794",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT380461"}
@inproceedings{bb386395,
AUTHOR = "Pavlovic, V.",
TITLE = "Multimodal tracking and classification of audio-visual features",
BOOKTITLE = ICIP98,
YEAR = "1998",
PAGES = "I: 343-347",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT380462"}
@inproceedings{bb386396,
AUTHOR = "Rehg, J.M. and Murphy, K.P. and Fieguth, P.W.",
TITLE = "Vision-Based Speaker Detection Using Bayesian Networks",
BOOKTITLE = CVPR99,
YEAR = "1999",
PAGES = "II: 110-116",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT380463"}
@article{bb386397,
AUTHOR = "Vajaria, H. and Sankar, R. and Kasturi, R.",
TITLE = "Exploring Co-Occurence Between Speech and Body Movement for
Audio-Guided Video Localization",
JOURNAL = CirSysVideo,
VOLUME = "18",
YEAR = "2008",
NUMBER = "11",
MONTH = "November",
PAGES = "1608-1617",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT380464"}
@inproceedings{bb386398,
AUTHOR = "Vajaria, H. and Islam, T. and Sarkar, S. and Sankar, R. and Kasturi, R.",
TITLE = "Audio Segmentation and Speaker Localization in Meeting Videos",
BOOKTITLE = ICPR06,
YEAR = "2006",
PAGES = "II: 1150-1153",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT380465"}
@article{bb386399,
AUTHOR = "Talantzis, F. and Pnevmatikakis, A. and Constantinides, A.G.",
TITLE = "Audio-Visual Active Speaker Tracking in Cluttered Indoors Environments",
JOURNAL = SMC-B,
VOLUME = "39",
YEAR = "2009",
NUMBER = "1",
MONTH = "February",
PAGES = "7-15",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT380466"}
Last update:Sep 30, 2026 at 11:45:00