@inproceedings{bb387400,
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#TT381464"}
@inproceedings{bb387401,
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#TT381465"}
@inproceedings{bb387402,
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#TT381466"}
@inproceedings{bb387403,
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#TT381467"}
@inproceedings{bb387404,
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#TT381468"}
@inproceedings{bb387405,
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#TT381469"}
@inproceedings{bb387406,
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#TT381470"}
@inproceedings{bb387407,
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#TT381471"}
@inproceedings{bb387408,
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#TT381472"}
@inproceedings{bb387409,
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#TT381473"}
@inproceedings{bb387410,
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#TT381474"}
@inproceedings{bb387411,
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#TT381475"}
@inproceedings{bb387412,
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#TT381476"}
@inproceedings{bb387413,
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#TT381477"}
@inproceedings{bb387414,
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#TT381478"}
@inproceedings{bb387415,
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#TT381479"}
@inproceedings{bb387416,
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#TT381480"}
@inproceedings{bb387417,
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#TT381481"}
@inproceedings{bb387418,
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#TT381482"}
@inproceedings{bb387419,
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#TT381483"}
@article{bb387420,
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#TT381484"}
@article{bb387421,
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#TT381485"}
@inproceedings{bb387422,
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#TT381486"}
@inproceedings{bb387423,
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#TT381487"}
@inproceedings{bb387424,
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#TT381488"}
@inproceedings{bb387425,
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#TT381489"}
@inproceedings{bb387426,
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#TT381490"}
@inproceedings{bb387427,
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#TT381491"}
@article{bb387428,
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#TT381492"}
@inproceedings{bb387429,
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#TT381493"}
@article{bb387430,
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#TT381494"}
@article{bb387431,
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#TT381494"}
@article{bb387432,
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#TT381495"}
@article{bb387433,
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#TT381496"}
@inproceedings{bb387434,
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#TT381497"}
@article{bb387435,
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#TT381498"}
@article{bb387436,
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#TT381499"}
@article{bb387437,
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#TT381500"}
@article{bb387438,
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#TT381501"}
@article{bb387439,
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#TT381502"}
@inproceedings{bb387440,
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#TT381503"}
@article{bb387441,
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#TT381504"}
@article{bb387442,
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#TT381505"}
@article{bb387443,
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#TT381506"}
@article{bb387444,
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#TT381507"}
@article{bb387445,
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#TT381508"}
@article{bb387446,
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#TT381509"}
@article{bb387447,
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#TT381510"}
@article{bb387448,
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#TT381511"}
@article{bb387449,
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#TT381512"}
@inproceedings{bb387450,
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#TT381513"}
@article{bb387451,
AUTHOR = "Li, Y. and Liu, H. and Yang, B.",
TITLE = "STNet: Deep Audio-Visual Fusion Network for Robust Speaker Tracking",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "1835-1847",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381514"}
@article{bb387452,
AUTHOR = "Li, Y. and Li, Y.H. and Xu, Z. and Wan, W.W. and Liu, H.",
TITLE = "Global-local distillation network-based audio-visual speaker tracking
with incomplete modalities",
JOURNAL = PR,
VOLUME = "179",
YEAR = "2026",
PAGES = "113916",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381515"}
@article{bb387453,
AUTHOR = "Senocak, A. and Ryu, H. and Kim, J. and Oh, T.H. and Pfister, H. and Chung, J.S.",
TITLE = "Toward Interactive Sound Source Localization:
Better Align Sight and Sound!",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "9",
MONTH = "September",
PAGES = "7643-7659",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381516"}
@article{bb387454,
AUTHOR = "Liao, J.H. and Duan, H.H. and Feng, K.H. and Zhao, W.B. and Yang, Y.B. and Chen, L.Y. and Chen, Y.R.",
TITLE = "LR-ASD: Lightweight and Robust Network for Active Speaker Detection",
JOURNAL = IJCV,
VOLUME = "133",
YEAR = "2025",
NUMBER = "7",
MONTH = "July",
PAGES = "4749-4769",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381517"}
@article{bb387455,
AUTHOR = "Jiang, Z.Y. and Chen, X. and Wang, S. and Qian, X.Y. and Li, H.Z.",
TITLE = "TPEech: Target Speaker Extraction and Noise Suppression With
Historical Dialogue Text Cues",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "351-355",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381518"}
@article{bb387456,
AUTHOR = "Yang, W.H. and Wei, J.G. and Lu, W.H. and Song, X.Y. and Yue, X.",
TITLE = "Listening for 'You': Enhancing Speech Image Retrieval via Target
Speaker Extraction",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "201-205",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381519"}
@article{bb387457,
AUTHOR = "Li, Z.J. and Li, J.B. and Huang, D. and Jiao, J.B. and Li, J.Z. and Zhao, B.",
TITLE = "Audio denoising and audio-visual localization for unmanned aerial
vehicles",
JOURNAL = PR,
VOLUME = "179",
YEAR = "2026",
PAGES = "113931",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381520"}
@article{bb387458,
AUTHOR = "He, Y.Z. and Liu, Y. and Zhang, C. and Zhu, D.C. and Wang, L.",
TITLE = "Learning to chase: Adaptive audio-visual navigation for moving sounds
in complex environments",
JOURNAL = PRL,
VOLUME = "206",
YEAR = "2026",
PAGES = "69-74",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381521"}
@inproceedings{bb387459,
AUTHOR = "Zeng, Z. and Peng, C. and Celiktutan, O.",
TITLE = "Multimodal Voice Activity Projection for Multi-Party Conversations",
BOOKTITLE = FG26,
YEAR = "2026",
PAGES = "1-5",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381522"}
@inproceedings{bb387460,
AUTHOR = "Wang, Y. and Ha, J. and Ramirez, F.M. and Wang, Y.C. and Crandall, D.J.",
TITLE = "GateFusion: Hierarchical Gated Cross-Modal Fusion for Active Speaker
Detection",
BOOKTITLE = WACV26,
YEAR = "2026",
PAGES = "1074-1083",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381523"}
@inproceedings{bb387461,
AUTHOR = "Um, S.J. and Kim, D.J. and Lee, S. and Kim, J.U.",
TITLE = "Object-aware Sound Source Localization via Audio-Visual Scene
Understanding",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "8342-8351",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381524"}
@inproceedings{bb387462,
AUTHOR = "Kim, I.H. and Song, Y. and Park, J. and Kim, W.H. and Kwak, S.",
TITLE = "Improving Sound Source Localization with Joint Slot Attention on
Image and Audio",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "3121-3130",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381525"}
@inproceedings{bb387463,
AUTHOR = "Ryu, H. and Kim, S. and Chung, J.S. and Senocak, A.",
TITLE = "Seeing Speech and Sound: Distinguishing and Locating Audio Sources in
Visual Scenes",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "13540-13549",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381526"}
@inproceedings{bb387464,
AUTHOR = "Ye, Y.X. and Yang, W.M. and Tian, Y.P.",
TITLE = "LAVSS: Location-Guided Audio-Visual Spatial Audio Separation",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "5496-5507",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381527"}
@inproceedings{bb387465,
AUTHOR = "Wang, X.Z. and Cheng, F. and Bertasius, G.",
TITLE = "LoCoNet: Long-Short Context Network for Active Speaker Detection",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "18462-18472",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381528"}
@inproceedings{bb387466,
AUTHOR = "Chen, J.B. and Zhang, R.R. and Lian, D.Z. and Yang, J.Q. and Zeng, Z.Y. and Shi, J.B.",
TITLE = "iQuery: Instruments as Queries for Audio-Visual Sound Separation",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "14675-14686",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381529"}
@inproceedings{bb387467,
AUTHOR = "Tan, R. and Ray, A. and Burns, A. and Plummer, B.A. and Salamon, J. and Nieto, O. and Russell, B. and Saenko, K.",
TITLE = "Language-Guided Audio-Visual Source Separation via Trimodal
Consistency",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "10575-10584",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381530"}
@inproceedings{bb387468,
AUTHOR = "Sun, W.X. and Zhang, J.Y. and Wang, J.Y. and Liu, Z.Y. and Zhong, Y.R. and Feng, T.P. and Guo, Y.D. and Zhang, Y.H. and Barnes, N.M.",
TITLE = "Learning Audio-Visual Source Localization via False Negative Aware
Contrastive Learning",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "6420-6429",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381531"}
@inproceedings{bb387469,
AUTHOR = "Huang, C. and Tian, Y.P. and Kumar, A. and Xu, C.L.",
TITLE = "Egocentric Audio-Visual Object Localization",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "22910-22921",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381532"}
@inproceedings{bb387470,
AUTHOR = "Nugroho, M.A. and Woo, S. and Lee, S. and Kim, C.",
TITLE = "Audio-Visual Glance Network for Efficient Video Recognition",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "10116-10125",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381533"}
@inproceedings{bb387471,
AUTHOR = "Liu, Y. and Tan, Y. and Lan, H.Y.",
TITLE = "Self-Supervised Contrastive Learning for Audio-Visual Action
Recognition",
BOOKTITLE = ICIP23,
YEAR = "2023",
PAGES = "1000-1004",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381534"}
@inproceedings{bb387472,
AUTHOR = "Alcazar, J.L. and Cordes, M. and Zhao, C. and Ghanem, B.",
TITLE = "End-to-End Active Speaker Detection",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXXVII:126-143",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381535"}
@inproceedings{bb387473,
AUTHOR = "Mo, S.T. and Morgado, P.",
TITLE = "Localizing Visual Sounds the Easy Way",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXXVII:218-234",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381536"}
@inproceedings{bb387474,
AUTHOR = "Xia, Y. and Zhao, Z.",
TITLE = "Cross-modal Background Suppression for Audio-Visual Event
Localization",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "19957-19966",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381537"}
@inproceedings{bb387475,
AUTHOR = "Wang, H. and Gao, L.L. and Tan, Q.C. and Ji, L.P.",
TITLE = "Visual Sound Source Separation with Partial Supervision Learning",
BOOKTITLE = ICIP22,
YEAR = "2022",
PAGES = "2127-2131",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381538"}
@inproceedings{bb387476,
AUTHOR = "Jiang, H. and Murdock, C. and Ithapu, V.K.",
TITLE = "Egocentric Deep Multi-Channel Audio-Visual Active Speaker
Localization",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "10534-10542",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381539"}
@inproceedings{bb387477,
AUTHOR = "Min, K. and Roy, S. and Tripathi, S. and Guha, T. and Majumdar, S.",
TITLE = "Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXXV:371-387",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381540"}
@inproceedings{bb387478,
AUTHOR = "Duan, B. and Tang, H. and Wang, W. and Zong, Z.L. and Yang, G.W. and Yan, Y.",
TITLE = "Audio-Visual Event Localization via Recursive Fusion by Joint
Co-Attention",
BOOKTITLE = WACV21,
YEAR = "2021",
PAGES = "4012-4021",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381541"}
@inproceedings{bb387479,
AUTHOR = "Nguyen, Q. and Richter, J. and Lauri, M. and Gerkmann, T. and Frintrop, S.",
TITLE = "Improving mix-and-separate training in audio-visual sound source
separation with an object prior",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "5844-5851",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381542"}
@inproceedings{bb387480,
AUTHOR = "Wu, Y. and Zhu, L.C. and Yan, Y. and Yang, Y.",
TITLE = "Dual Attention Matching for Audio-Visual Event Localization",
BOOKTITLE = ICCV19,
YEAR = "2019",
PAGES = "6291-6299",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381543"}
@inproceedings{bb387481,
AUTHOR = "Majumder, S. and Grauman, K.",
TITLE = "Active Audio-Visual Separation of Dynamic Sound Sources",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXIX:551-569",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381544"}
@inproceedings{bb387482,
AUTHOR = "Majumder, S. and Al Halah, Z. and Grauman, K.",
TITLE = "Move2Hear: Active Audio-Visual Source Separation",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "275-285",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381545"}
@inproceedings{bb387483,
AUTHOR = "Alcazar, J.L. and Heilbron, F.C. and Thabet, A.K. and Ghanem, B.",
TITLE = "MAAS: Multi-modal Assignation for Active Speaker Detection",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "265-274",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381546"}
@inproceedings{bb387484,
AUTHOR = "Kopuklu, O. and Taseska, M. and Rigoll, G.",
TITLE = "How to Design a Three-Stage Architecture for Audio-Visual Active
Speaker Detection in the Wild",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "1173-1183",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381547"}
@inproceedings{bb387485,
AUTHOR = "Wu, Y. and Yang, Y.",
TITLE = "Exploring Heterogeneous Clues for Weakly-Supervised Audio-Visual
Video Parsing",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "1326-1335",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381548"}
@inproceedings{bb387486,
AUTHOR = "Liu, H. and Sun, Y.H. and Li, Y.D. and Yang, B.",
TITLE = "3D Audio-Visual Speaker Tracking with A Novel Particle Filter",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "7343-7348",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381549"}
@inproceedings{bb387487,
AUTHOR = "Liu, H. and Li, Y.D. and Yang, B.",
TITLE = "3D Audio-Visual Speaker Tracking with A Two-Layer Particle Filter",
BOOKTITLE = ICIP19,
YEAR = "2019",
PAGES = "1955-1959",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381550"}
@inproceedings{bb387488,
AUTHOR = "He, G. and Liu, X. and Fan, F. and You, J.",
TITLE = "Image2Audio: Facilitating Semi-supervised Audio Emotion Recognition
with Facial Expression Image",
BOOKTITLE = VL3W20,
YEAR = "2020",
PAGES = "3978-3983",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381551"}
@inproceedings{bb387489,
AUTHOR = "Le, N. and Heili, A. and Wu, D. and Odobez, J.M.",
TITLE = "Temporally subsampled detection for accurate and efficient face
tracking and diarization",
BOOKTITLE = ICPR16,
YEAR = "2016",
PAGES = "1792-1797",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381552"}
@inproceedings{bb387490,
AUTHOR = "Saeed, A. and Al Hamadi, A. and Heuer, M.",
TITLE = "Speaker Tracking Using Multi-modal Fusion Framework",
BOOKTITLE = ICISP12,
YEAR = "2012",
PAGES = "539-546",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381553"}
@inproceedings{bb387491,
AUTHOR = "Kelly, D. and Pitie, F. and Kokaram, A. and Boland, F.",
TITLE = "A Comparative Error Analysis of Audio-Visual Source Localization",
BOOKTITLE = M2SFA208,
YEAR = "2008",
PAGES = "xx-yy",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381554"}
@inproceedings{bb387492,
AUTHOR = "Katsarakis, N. and Talantzis, F. and Pnevmatikakis, A. and Polymenakos, L.",
TITLE = "The AIT 3D Audio / Visual Person Tracker for CLEAR 2007",
BOOKTITLE = MTPH07,
YEAR = "2007",
PAGES = "xx-yy",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381555"}
@inproceedings{bb387493,
AUTHOR = "Kushal, A. and Rahurkar, M. and Fei Fei, L. and Ponce, J. and Huang, T.",
TITLE = "Audio-Visual Speaker Localization Using Graphical Models",
BOOKTITLE = ICPR06,
YEAR = "2006",
PAGES = "I: 291-294",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381556"}
@inproceedings{bb387494,
AUTHOR = "Tsuji, T. and Yamamoto, K. and Ishii, I.",
TITLE = "Real-time Sound Source Localization Based on Audiovisual Frequency
Integration",
BOOKTITLE = ICPR06,
YEAR = "2006",
PAGES = "IV: 322-325",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381557"}
@inproceedings{bb387495,
AUTHOR = "Megherbi, N. and Ambellouis, S. and Colot, O. and Cabestaing, F.",
TITLE = "Data Association in Multi-Target Tracking Using Belief Theory:
Handling Target Emergence and Disappearance Issue",
BOOKTITLE = AVSBS05,
YEAR = "2005",
PAGES = "517-521",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381558"}
@inproceedings{bb387496,
AUTHOR = "Megherbi, N. and Ambellouis, S. and Colot, O. and Cabestaing, F.",
TITLE = "Joint audio-video people tracking using belief theory",
BOOKTITLE = AVSBS05,
YEAR = "2005",
PAGES = "135-140",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381559"}
@inproceedings{bb387497,
AUTHOR = "Li, X. and Sun, L. and Tao, L.M. and Xu, G.Y. and Jia, Y.",
TITLE = "A Speaker Tracking Algorithm Based on Audio and Visual Information
Fusion Using Particle Filter",
BOOKTITLE = ICIAR04,
YEAR = "2004",
PAGES = "II: 572-580",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381560"}
@inproceedings{bb387498,
AUTHOR = "Lange, C. and Hermann, T. and Ritter, H.",
TITLE = "Holistic Body Tracking for Gestural Interfaces",
BOOKTITLE = GW03,
YEAR = "2003",
PAGES = "132-139",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381561"}
@inproceedings{bb387499,
AUTHOR = "Blake, A. and Gangnet, M. and Perez, P. and Vermaak, J.",
TITLE = "Integrated tracking with vision and sound",
BOOKTITLE = CIAP01,
YEAR = "2001",
PAGES = "354-357",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1020avt1.html#TT381562"}
Last update: