@article{bb382800,
        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#TT376885"}

@article{bb382801,
        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#TT376886"}

@article{bb382802,
        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#TT376887"}

@article{bb382803,
        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#TT376888"}

@article{bb382804,
        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#TT376889"}

@article{bb382805,
        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#TT376890"}

@article{bb382806,
        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#TT376891"}

@article{bb382807,
        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#TT376892"}

@article{bb382808,
        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#TT376893"}

@article{bb382809,
        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#TT376894"}

@article{bb382810,
        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#TT376895"}

@article{bb382811,
        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#TT376896"}

@article{bb382812,
        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#TT376897"}

@inproceedings{bb382813,
        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#TT376898"}

@article{bb382814,
        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#TT376899"}

@article{bb382815,
        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#TT376900"}

@article{bb382816,
        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#TT376901"}

@article{bb382817,
        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#TT376902"}

@article{bb382818,
        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#TT376903"}

@article{bb382819,
        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#TT376904"}

@article{bb382820,
        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#TT376905"}

@article{bb382821,
        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#TT376906"}

@inproceedings{bb382822,
        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#TT376907"}

@inproceedings{bb382823,
        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#TT376908"}

@inproceedings{bb382824,
        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#TT376909"}

@inproceedings{bb382825,
        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#TT376910"}

@inproceedings{bb382826,
        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#TT376911"}

@inproceedings{bb382827,
        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#TT376912"}

@inproceedings{bb382828,
        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#TT376913"}

@inproceedings{bb382829,
        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#TT376914"}

@inproceedings{bb382830,
        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#TT376915"}

@inproceedings{bb382831,
        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#TT376916"}

@inproceedings{bb382832,
        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#TT376917"}

@inproceedings{bb382833,
        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#TT376918"}

@inproceedings{bb382834,
        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#TT376919"}

@inproceedings{bb382835,
        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#TT376920"}

@inproceedings{bb382836,
        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#TT376921"}

@inproceedings{bb382837,
        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#TT376922"}

@inproceedings{bb382838,
        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#TT376923"}

@inproceedings{bb382839,
        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#TT376924"}

@inproceedings{bb382840,
        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#TT376925"}

@inproceedings{bb382841,
        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#TT376926"}

@inproceedings{bb382842,
        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#TT376927"}

@inproceedings{bb382843,
        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#TT376928"}

@inproceedings{bb382844,
        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#TT376929"}

@inproceedings{bb382845,
        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#TT376930"}

@inproceedings{bb382846,
        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#TT376931"}

@inproceedings{bb382847,
        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#TT376932"}

@inproceedings{bb382848,
        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#TT376933"}

@inproceedings{bb382849,
        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#TT376934"}

@inproceedings{bb382850,
        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#TT376935"}

@inproceedings{bb382851,
        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#TT376936"}

@inproceedings{bb382852,
        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#TT376937"}

@inproceedings{bb382853,
        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#TT376938"}

@inproceedings{bb382854,
        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#TT376939"}

@inproceedings{bb382855,
        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#TT376940"}

@inproceedings{bb382856,
        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#TT376941"}

@inproceedings{bb382857,
        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#TT376942"}

@inproceedings{bb382858,
        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#TT376943"}

@inproceedings{bb382859,
        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#TT376944"}

@inproceedings{bb382860,
        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#TT376945"}

@inproceedings{bb382861,
        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#TT376946"}

@inproceedings{bb382862,
        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#TT376947"}

@inproceedings{bb382863,
        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#TT376948"}

@inproceedings{bb382864,
        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#TT376949"}

@inproceedings{bb382865,
        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#TT376950"}

@inproceedings{bb382866,
        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#TT376951"}

@inproceedings{bb382867,
        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#TT376952"}

@inproceedings{bb382868,
        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#TT376953"}

@article{bb382869,
        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#TT376954"}

@article{bb382870,
        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#TT376955"}

@inproceedings{bb382871,
        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#TT376956"}

@inproceedings{bb382872,
        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#TT376957"}

@inproceedings{bb382873,
        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#TT376958"}

@inproceedings{bb382874,
        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#TT376959"}

@inproceedings{bb382875,
        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#TT376960"}

@inproceedings{bb382876,
        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#TT376961"}

@article{bb382877,
        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#TT376962"}

@inproceedings{bb382878,
        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#TT376963"}

@article{bb382879,
        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#TT376964"}

@article{bb382880,
        AUTHOR = "Constantinides, A.G. and Pnevmatikakis, A. and Talantzis, F.",
        TITLE = "Audio-Visual Active Speaker Tracking in Cluttered Indoors Environments",
        JOURNAL = SMC-B,
        VOLUME = "38",
        YEAR = "2008",
        NUMBER = "3",
        MONTH = "June",
        PAGES = "799-807",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT376964"}

@article{bb382881,
        AUTHOR = "Lee, J.S. and de Simone, F. and Ebrahimi, T.",
        TITLE = "Efficient video coding based on audio-visual focus of attention",
        JOURNAL = JVCIR,
        VOLUME = "22",
        YEAR = "2011",
        NUMBER = "8",
        MONTH = "November",
        PAGES = "704-711",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT376965"}

@article{bb382882,
        AUTHOR = "Blauth, D.A. and Minotto, V.P. and Jung, C.R. and Lee, B. and Kalker, T.",
        TITLE = "Voice activity detection and speaker localization using audiovisual
cues",
        JOURNAL = PRL,
        VOLUME = "33",
        YEAR = "2012",
        NUMBER = "4",
        MONTH = "March",
        PAGES = "373-380",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT376966"}

@inproceedings{bb382883,
        AUTHOR = "Montazzolli, S. and Jung, C.R. and Gelb, D.",
        TITLE = "Audiovisual voice activity detection using off-the-shelf cameras",
        BOOKTITLE = ICIP15,
        YEAR = "2015",
        PAGES = "3886-3890",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT376967"}

@article{bb382884,
        AUTHOR = "Minotto, V.P. and Jung, C.R. and Lee, B.",
        TITLE = "Simultaneous-Speaker Voice Activity Detection and Localization Using
Mid-Fusion of SVM and HMMs",
        JOURNAL = MultMed,
        VOLUME = "16",
        YEAR = "2014",
        NUMBER = "4",
        MONTH = "June",
        PAGES = "1032-1044",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT376968"}

@article{bb382885,
        AUTHOR = "Qian, X. and Brutti, A. and Lanz, O. and Omologo, M. and Cavallaro, A.",
        TITLE = "Multi-Speaker Tracking From an Audio-Visual Sensing Device",
        JOURNAL = MultMed,
        VOLUME = "21",
        YEAR = "2019",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "2576-2588",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT376969"}

@article{bb382886,
        AUTHOR = "Pu, J. and Panagakis, Y. and Pantic, M.",
        TITLE = "Active Speaker Detection and Localization in Videos Using Low-Rank
and Kernelized Sparsity",
        JOURNAL = SPLetters,
        VOLUME = "27",
        YEAR = "2020",
        PAGES = "865-869",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT376970"}

@article{bb382887,
        AUTHOR = "Qian, X.Y. and Liu, Q. and Wang, J.D. and Li, H.Z.",
        TITLE = "Three-Dimensional Speaker Localization: Audio-Refined Visual Scaling
Factor Estimation",
        JOURNAL = SPLetters,
        VOLUME = "28",
        YEAR = "2021",
        PAGES = "1405-1409",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT376971"}

@article{bb382888,
        AUTHOR = "Ban, Y.T. and Alameda Pineda, X. and Girin, L. and Horaud, R.",
        TITLE = "Variational Bayesian Inference for Audio-Visual Tracking of Multiple
Speakers",
        JOURNAL = PAMI,
        VOLUME = "43",
        YEAR = "2021",
        NUMBER = "5",
        MONTH = "May",
        PAGES = "1761-1776",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT376972"}

@inproceedings{bb382889,
        AUTHOR = "Ban, Y.T. and Girin, L. and Alameda Pineda, X. and Horaud, R.",
        TITLE = "Exploiting the Complementarity of Audio and Visual Data in
Multi-speaker Tracking",
        BOOKTITLE = CVAVM17,
        YEAR = "2017",
        PAGES = "446-454",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT376973"}

@article{bb382890,
        AUTHOR = "Qian, X.Y. and Brutti, A. and Lanz, O. and Omologo, M. and Cavallaro, A.",
        TITLE = "Audio-Visual Tracking of Concurrent Speakers",
        JOURNAL = MultMed,
        VOLUME = "24",
        YEAR = "2022",
        PAGES = "942-954",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT376974"}

@article{bb382891,
        AUTHOR = "Hu, D. and Wei, Y. and Qian, R. and Lin, W.Y. and Song, R.H. and Wen, J.R.",
        TITLE = "Class-Aware Sounding Objects Localization via Audiovisual
Correspondence",
        JOURNAL = PAMI,
        VOLUME = "44",
        YEAR = "2022",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "9844-9859",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT376975"}

@article{bb382892,
        AUTHOR = "Zheng, A. and Hu, M. and Jiang, B. and Huang, Y. and Yan, Y. and Luo, B.",
        TITLE = "Adversarial-Metric Learning for Audio-Visual Cross-Modal Matching",
        JOURNAL = MultMed,
        VOLUME = "24",
        YEAR = "2022",
        PAGES = "338-351",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT376976"}

@article{bb382893,
        AUTHOR = "Wang, H. and Zha, Z.J. and Li, L. and Chen, X.J. and Luo, J.B.",
        TITLE = "Semantic and Relation Modulation for Audio-Visual Event Localization",
        JOURNAL = PAMI,
        VOLUME = "45",
        YEAR = "2023",
        NUMBER = "6",
        MONTH = "June",
        PAGES = "7711-7725",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT376977"}

@article{bb382894,
        AUTHOR = "Garg, R. and Gao, R.H. and Grauman, K.",
        TITLE = "Visually-Guided Audio Spatialization in Video with Geometry-Aware
Multi-task Learning",
        JOURNAL = IJCV,
        VOLUME = "131",
        YEAR = "2023",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "2723-2737",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT376978"}

@article{bb382895,
        AUTHOR = "Wang, J.X. and Li, C.L. and Zheng, A. and Tang, J. and Luo, B.",
        TITLE = "Looking and Hearing Into Details:
Dual-Enhanced Siamese Adversarial Network for Audio-Visual Matching",
        JOURNAL = MultMed,
        VOLUME = "25",
        YEAR = "2023",
        PAGES = "7505-7516",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT376979"}

@article{bb382896,
        AUTHOR = "Traa, J. and Smaragdis, P.",
        TITLE = "A Wrapped Kalman Filter for Azimuthal Speaker Tracking",
        JOURNAL = SPLetters,
        VOLUME = "20",
        YEAR = "2013",
        NUMBER = "12",
        PAGES = "1257-1260",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT376980"}

@article{bb382897,
        AUTHOR = "Qian, X.Y. and Zhang, Q. and Guan, G.H. and Xue, W.",
        TITLE = "Deep Audio-Visual Beamforming for Speaker Localization",
        JOURNAL = SPLetters,
        VOLUME = "29",
        YEAR = "2022",
        PAGES = "1132-1136",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT376981"}

@article{bb382898,
        AUTHOR = "Xuan, H.Y. and Wu, Z.L. and Yang, J. and Jiang, B. and Luo, L. and Alameda Pineda, X. and Yan, Y.",
        TITLE = "Robust Audio-Visual Contrastive Learning for Proposal-Based
Self-Supervised Sound Source Localization in Videos",
        JOURNAL = PAMI,
        VOLUME = "46",
        YEAR = "2024",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "4896-4907",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT376982"}

@inproceedings{bb382899,
        AUTHOR = "Xuan, H.Y. and Wu, Z.L. and Yang, J. and Yan, Y. and Alameda Pineda, X.",
        TITLE = "A Proposal-based Paradigm for Self-supervised Sound Source
Localization in Videos",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "1019-1028",
        BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT376983"}

Last update:Aug 19, 2026 at 13:26:35