@inproceedings{bb111400,
AUTHOR = "Salcedo, J.N. and Lackey, S.J. and Maraj, C.",
TITLE = "Impact of Instructional Strategies on Workload, Stress, and Flow in
Simulation-Based Training for Behavior Cue Analysis",
BOOKTITLE = VAMR16,
YEAR = "2016",
PAGES = "184-195",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108059"}
@inproceedings{bb111401,
AUTHOR = "Jain, S. and Barsness, K.A. and Argall, B.",
TITLE = "Automated and Objective Assessment of Surgical Training:
Detection of Procedural Steps on Videotaped Performances",
BOOKTITLE = DICTA15,
YEAR = "2015",
PAGES = "1-6",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108060"}
@inproceedings{bb111402,
AUTHOR = "Ridene, T. and Leroy, L. and Chendeb, S.",
TITLE = "Innovative Virtual Reality Application for Road Safety Education of
Children in Urban Areas",
BOOKTITLE = ISVC15,
YEAR = "2015",
PAGES = "II: 797-808",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108061"}
@inproceedings{bb111403,
AUTHOR = "Mostafa, A.E. and Takashima, K. and Sousa, M.C. and Sharlin, E.",
TITLE = "JackVR: A Virtual Reality Training System for Landing Oil Rigs",
BOOKTITLE = ISVC15,
YEAR = "2015",
PAGES = "II: 453-462",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108062"}
@inproceedings{bb111404,
AUTHOR = "Meixner, B. and Gold, M.",
TITLE = "Second-Layer Navigation in Mobile Hypervideo for Medical Training",
BOOKTITLE = MMMod16,
YEAR = "2016",
PAGES = "I: 382-394",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108063"}
@inproceedings{bb111405,
AUTHOR = "Bogoni, T. and Scarparo, R. and Pinho, M.",
TITLE = "A virtual reality simulator for training endodontics procedures using
manual files",
BOOKTITLE = "3DUI15",
YEAR = "2015",
PAGES = "39-42",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108064"}
@inproceedings{bb111406,
AUTHOR = "Papadimitriou, K.",
TITLE = "Course Outline for a Scuba Diving Speciality 'Underwater Survey Diver'",
BOOKTITLE = Underwater15,
YEAR = "2015",
PAGES = "161-166",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108065"}
@inproceedings{bb111407,
AUTHOR = "Sathyanarayana, S. and Littlewort, G. and Bartlett, M.",
TITLE = "Hand Gestures for Intelligent Tutoring Systems:
Dataset, Techniques and Evaluation",
BOOKTITLE = SocialInter13,
YEAR = "2013",
PAGES = "769-776",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108066"}
@inproceedings{bb111408,
AUTHOR = "Ogawa, Y. and Shimada, N. and Shirai, Y. and Kurumi, Y. and Komori, M.",
TITLE = "Temporal-spatial validation of knot-tying procedures using RGB-D
sensor for training of surgical operation",
BOOKTITLE = MVA15,
YEAR = "2015",
PAGES = "263-266",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108067"}
@inproceedings{bb111409,
AUTHOR = "Kimber, D. and Proppe, P. and Kratz, S. and Vaughan, J. and Liew, B. and Severns, D. and Su, W.Q.",
TITLE = "Polly: Telepresence from a Guide's Shoulder",
BOOKTITLE = ACVR14,
YEAR = "2014",
PAGES = "509-523",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108068"}
@inproceedings{bb111410,
AUTHOR = "Kamphorst, B.A. and Klein, M.C.A. and van Wissen, A.",
TITLE = "Human Involvement in E-Coaching:
Effects on Effectiveness, Perceived Influence and Trust",
BOOKTITLE = HBU14,
YEAR = "2014",
PAGES = "16-29",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108069"}
@inproceedings{bb111411,
AUTHOR = "Margetis, G. and Ntelidakis, A. and Zabulis, X. and Ntoa, S. and Koutlemanis, P. and Stephanidis, C.",
TITLE = "Augmenting physical books towards education enhancement",
BOOKTITLE = "UCCV13 2013",
YEAR = "2013",
PAGES = "43-49",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108070"}
@inproceedings{bb111412,
AUTHOR = "Abasolo, M.J. and Bauza, C.G. and Lazo, M. and d'Amato, J.P. and Venere, M. and de Giusti, A. and Manresa Yee, C. and Mas Sanso, R.",
TITLE = "From a Serious Training Simulator for Ship Maneuvering to an
Entertainment Simulator",
BOOKTITLE = AMDO14,
YEAR = "2014",
PAGES = "106-117",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108071"}
@inproceedings{bb111413,
AUTHOR = "Parmar, D. and Bertrand, J. and Shannon, B. and Babu, S.V. and Madathil, K. and Zelaya, M. and Wang, T.W. and Wagner, J. and Frady, K. and Gramopadhye, A.K.",
TITLE = "Interactive breadboard activity simulation (IBAS) for psychomotor
skills education in electrical circuitry",
BOOKTITLE = "3DUI14",
YEAR = "2014",
PAGES = "181-182",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108072"}
@inproceedings{bb111414,
AUTHOR = "Pick, S. and Bonsch, A. and Tedjo Palczynski, I. and Hentschel, B. and Kuhlen, T.",
TITLE = "Guided tour creation in immersive virtual environments",
BOOKTITLE = "3DUI14",
YEAR = "2014",
PAGES = "151-152",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108073"}
@inproceedings{bb111415,
AUTHOR = "del Bimbo, A. and Ferracani, A.",
TITLE = "A Natural Interface for the Training of Medical Personnel in an
Immersive and Virtual Reality System",
BOOKTITLE = CIAP13,
YEAR = "2013",
PAGES = "I:763-772",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108074"}
@inproceedings{bb111416,
AUTHOR = "Segundo, J.T. and Soares, E. and Machado, L.S. and Moraes, R.",
TITLE = "Performance Profile of Online Training Assessment Based on Virtual
Reality:",
BOOKTITLE = CIARP13,
YEAR = "2013",
PAGES = "II:158-165",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108075"}
@inproceedings{bb111417,
AUTHOR = "Hold Geoffroy, Y. and Gardner, M.A. and Gagne, C. and Latulippe, M. and Giguere, P.",
TITLE = "ros4mat: A Matlab Programming Interface for Remote Operations of
ROS-Based Robotic Devices in an Educational Context",
BOOKTITLE = CRV13,
YEAR = "2013",
PAGES = "242-248",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108076"}
@inproceedings{bb111418,
AUTHOR = "Boeing, A. and Braunl, T.",
TITLE = "Leveraging multiple simulators for crossing the reality gap",
BOOKTITLE = ICARCV12,
YEAR = "2012",
PAGES = "1113-1119",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108077"}
@inproceedings{bb111419,
AUTHOR = "Schneeberger, M. and Uray, M. and Mayer, H.",
TITLE = "Image Completion Optimised for Realistic Simulations of Wound
Development",
BOOKTITLE = DAGM12,
YEAR = "2012",
PAGES = "448-457",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108078"}
@inproceedings{bb111420,
AUTHOR = "Moraes, R.M. and Machado, L.S. and Souza, L.C.",
TITLE = "Skills Assessment of Users in Medical Training Based on Virtual Reality
Using Bayesian Networks",
BOOKTITLE = CIARP12,
YEAR = "2012",
PAGES = "805-812",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108079"}
@inproceedings{bb111421,
AUTHOR = "Ng, C.L. and Ng, T.C. and Nguyen, T.A.N. and Yang, G.L. and Chen, W.J.",
TITLE = "Intuitive robot tool path teaching using laser and camera in Augmented
Reality environment",
BOOKTITLE = ICARCV10,
YEAR = "2010",
PAGES = "114-119",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108080"}
@inproceedings{bb111422,
AUTHOR = "Chuah, K.M. and Chen, C.J. and Teh, C.S.",
TITLE = "ViSTREET: An Educational Virtual Environment for the Teaching of Road
Safety Skills to School Students",
BOOKTITLE = IVIC09,
YEAR = "2009",
PAGES = "392-403",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108081"}
@inproceedings{bb111423,
AUTHOR = "Boudreaux, H. and Bible, P. and Cruz Neira, C. and Parham, T. and Cervato, C. and Gallus, W. and Stelling, P.",
TITLE = "V-Volcano: Addressing Students' Misconceptions in Earth Sciences
Learning through Virtual Reality Simulations",
BOOKTITLE = ISVC09,
YEAR = "2009",
PAGES = "I: 1009-1018",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108082"}
@inproceedings{bb111424,
AUTHOR = "Zaman, H.B. and Bakar, N. and Ahmad, A. and Sulaiman, R. and Arshad, H. and Yatim, N.F.M.",
TITLE = "Virtual Visualisation Laboratory for Science and Mathematics Content
(Vlab-SMC) with Special Reference to Teaching and Learning of Chemistry",
BOOKTITLE = IVIC09,
YEAR = "2009",
PAGES = "356-370",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108083"}
@inproceedings{bb111425,
AUTHOR = "Periasamy, E. and Zaman, H.B.",
TITLE = "Augmented Reality as a Remedial Paradigm for Negative Numbers:
Content Aspect",
BOOKTITLE = IVIC09,
YEAR = "2009",
PAGES = "371-381",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108084"}
@inproceedings{bb111426,
AUTHOR = "Andersen, M. and Andersen, R. and Larsen, C. and Moeslund, T.B. and Madsen, O.",
TITLE = "Interactive Assembly Guide Using Augmented Reality",
BOOKTITLE = ISVC09,
YEAR = "2009",
PAGES = "I: 999-1008",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108085"}
@inproceedings{bb111427,
AUTHOR = "Sin, A.K. and Zaman, H.B.",
TITLE = "Tangible Interaction in Learning Astronomy through Augmented Reality
Book-Based Educational Tool",
BOOKTITLE = IVIC09,
YEAR = "2009",
PAGES = "302-313",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108086"}
@inproceedings{bb111428,
AUTHOR = "Ali, N.M. and Smeaton, A.F.",
TITLE = "Are Visual Informatics Actually Useful in Practice:
A Study in a Film Studies Context",
BOOKTITLE = IVIC09,
YEAR = "2009",
PAGES = "811-821",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108087"}
@inproceedings{bb111429,
AUTHOR = "Hincapie Ossa, D.A. and Ordonez Medina, S.A. and Rodriguez, C.F. and Hernandez, J.T.",
TITLE = "Immersive Simulator for Fluvial Combat Training",
BOOKTITLE = ISVC08,
YEAR = "2008",
PAGES = "I: 1018-1027",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108088"}
@inproceedings{bb111430,
AUTHOR = "d'Angelo, D. and Wesche, G. and Foursa, M. and Bogen, M.",
TITLE = "The Benefits of Co-located Collaboration and Immersion on Assembly
Modeling in Virtual Environments",
BOOKTITLE = ISVC08,
YEAR = "2008",
PAGES = "I: 478-487",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108089"}
@inproceedings{bb111431,
AUTHOR = "Moraes, R.M. and Machado, L.S.",
TITLE = "Multiple Assessment for Multiple Users in Virtual Reality Training
Environments",
BOOKTITLE = CIARP07,
YEAR = "2007",
PAGES = "950-956",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108090"}
@inproceedings{bb111432,
AUTHOR = "Salonen, T. and Saaski, J. and Hakkarainen, M. and Kannetis, T. and Perakakis, M. and Siltanen, S. and Potamianos, A. and Korkalo, O. and Woodward, C.",
TITLE = "Demonstration of assembly work using augmented reality",
BOOKTITLE = CIVR07,
YEAR = "2007",
PAGES = "120-123",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108091"}
@inproceedings{bb111433,
AUTHOR = "Li, W.H. and Tang, H. and Zhu, Z.G.",
TITLE = "Vision-Based Projection-Handwriting Integration in Classroom",
BOOKTITLE = PROCAMS06,
YEAR = "2006",
PAGES = "9",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108092"}
@inproceedings{bb111434,
AUTHOR = "Rogers, T.J. and Benes, B. and Bertoline, G.R.",
TITLE = "Towards a Modular Network-Distributed Mixed-Reality Learning Space
System",
BOOKTITLE = ISVC06,
YEAR = "2006",
PAGES = "II: 637-646",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108093"}
@inproceedings{bb111435,
AUTHOR = "Zhu, Z.G. and McKittrick, C. and Li, W.H.",
TITLE = "Virtualized Classroom:
Automated Production, Media Integration and User-Customized Presentation",
BOOKTITLE = MMDE04,
YEAR = "2004",
PAGES = "138",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108094"}
@inproceedings{bb111436,
AUTHOR = "Nakajima, C. and Itho, N.",
TITLE = "A support system for maintenance training by augmented reality",
BOOKTITLE = CIAP03,
YEAR = "2003",
PAGES = "158-163",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108095"}
@inproceedings{bb111437,
AUTHOR = "Brown, L.M.",
TITLE = "Visual Venture: investigations with images and videos for middle school
education",
BOOKTITLE = CVPR00,
YEAR = "2000",
PAGES = "II: 792-793",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497in1.html#TT108096"}
@article{bb111438,
AUTHOR = "Hoshino, K.",
TITLE = "Dexterous Robot Hand Control with Data Glove by Human Imitation",
JOURNAL = IEICE,
VOLUME = "E89-D",
YEAR = "2006",
NUMBER = "6",
MONTH = "June",
PAGES = "1820-1825",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108099"}
@article{bb111439,
AUTHOR = "Choudary, C. and Liu, T.C.",
TITLE = "Summarization of Visual Content in Instructional Videos",
JOURNAL = MultMed,
VOLUME = "9",
YEAR = "2007",
NUMBER = "7",
MONTH = "November",
PAGES = "1443-1455",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108100"}
@inproceedings{bb111440,
AUTHOR = "Liu, T.C. and Choudary, C.",
TITLE = "Content Extraction and Summarization of Instructional Videos",
BOOKTITLE = ICIP06,
YEAR = "2006",
PAGES = "149-152",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108101"}
@inproceedings{bb111441,
AUTHOR = "Liu, T.C. and Katpelly, R.",
TITLE = "Content-Adaptive Video Summarization Combining Queueing and Clustering",
BOOKTITLE = ICIP06,
YEAR = "2006",
PAGES = "145-148",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108102"}
@article{bb111442,
AUTHOR = "Alayrac, J.B. and Bojanowski, P. and Agrawal, N. and Sivic, J. and Laptev, I. and Lacoste Julien, S.",
TITLE = "Learning from Narrated Instruction Videos",
JOURNAL = PAMI,
VOLUME = "40",
YEAR = "2018",
NUMBER = "9",
MONTH = "September",
PAGES = "2194-2208",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108103"}
@inproceedings{bb111443,
AUTHOR = "Alayrac, J.B. and Bojanowski, P. and Agrawal, N. and Sivic, J. and Laptev, I. and Lacoste Julien, S.",
TITLE = "Unsupervised Learning from Narrated Instruction Videos",
BOOKTITLE = CVPR16,
YEAR = "2016",
PAGES = "4575-4583",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108104"}
@article{bb111444,
AUTHOR = "Doering, M. and Glas, D.F. and Ishiguro, H.",
TITLE = "Modeling Interaction Structure for Robot Imitation Learning of Human
Social Behavior",
JOURNAL = HMS,
VOLUME = "49",
YEAR = "2019",
NUMBER = "3",
MONTH = "June",
PAGES = "219-231",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108105"}
@article{bb111445,
AUTHOR = "Wu, A. and Piergiovanni, A.J. and Ryoo, M.S.",
TITLE = "Model-Based Robot Imitation with Future Image Similarity",
JOURNAL = IJCV,
VOLUME = "128",
YEAR = "2020",
NUMBER = "5",
MONTH = "May",
PAGES = "1360-1374",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108106"}
@article{bb111446,
AUTHOR = "Ryoo, M.S. and Piergiovanni, A.J. and Wu, A.",
TITLE = "Model-Based Robot Imitation with Future Image Similarity",
JOURNAL = IJCV,
VOLUME = "128",
YEAR = "2020",
NUMBER = "5",
MONTH = "May",
PAGES = "1375",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108106"}
@article{bb111447,
AUTHOR = "Tang, Y.S. and Lu, J.W. and Zhou, J.",
TITLE = "Comprehensive Instructional Video Analysis:
The COIN Dataset and Performance Evaluation",
JOURNAL = PAMI,
VOLUME = "43",
YEAR = "2021",
NUMBER = "9",
MONTH = "September",
PAGES = "3138-3153",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108107"}
@inproceedings{bb111448,
AUTHOR = "Tang, Y.S. and Ding, D.J. and Rao, Y.M. and Zheng, Y. and Zhang, D.Y. and Zhao, L. and Lu, J.W. and Zhou, J.",
TITLE = "COIN: A Large-Scale Dataset for Comprehensive Instructional Video
Analysis",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "1207-1216",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108108"}
@article{bb111449,
AUTHOR = "He, T.Y. and Liu, H.B. and Luo, W.H. and Ran, H.Z. and Shi, Z.G. and Lin, W.Y.",
TITLE = "Achieving Procedure-Aware Instructional Video Correlation Learning
Under Weak Supervision from a Collaborative Perspective",
JOURNAL = IJCV,
VOLUME = "133",
YEAR = "2025",
NUMBER = "4",
MONTH = "April",
PAGES = "2070-2095",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108109"}
@article{bb111450,
AUTHOR = "Tan, C. and Zhao, H. and Ding, H.",
TITLE = "Sparse Bayesian learning for dynamical modelling on product manifolds",
JOURNAL = PR,
VOLUME = "168",
YEAR = "2025",
PAGES = "111708",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108110"}
@article{bb111451,
AUTHOR = "Plini, L. and Scofano, L. and de Matteis, E. and di Melendugno, G.M.D. and Flaborea, A. and Sanchietti, A. and Farinella, G.M. and Galasso, F. and Furnari, A.",
TITLE = "TI-PREGO: Chain of Thought and In-Context Learning for online mistake
detection in PRocedural EGOcentric videos",
JOURNAL = CVIU,
VOLUME = "264",
YEAR = "2026",
PAGES = "104613",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108111"}
@article{bb111452,
AUTHOR = "Fang, F. and Yang, M. and Wu, M. and Yang, Y.H. and Xu, Q.L. and Lim, J.H. and Yang, X. and Zhu, H.Y.",
TITLE = "Toward Accurate Procedure Planning in Instructional Videos: Visual
State Generation Helps Task-Selective Diffusion",
JOURNAL = PAMI,
VOLUME = "48",
YEAR = "2026",
NUMBER = "4",
MONTH = "April",
PAGES = "4033-4050",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108112"}
@article{bb111453,
AUTHOR = "Xu, Y. and Shen, W. and Xu, J. and Zhang, X. and Wen, J.R.",
TITLE = "IBCB: Efficient Inverse Batched Contextual Bandit for Behavioral
Evolution History",
JOURNAL = PAMI,
VOLUME = "48",
YEAR = "2026",
NUMBER = "5",
MONTH = "May",
PAGES = "5655-5671",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108113"}
@article{bb111454,
AUTHOR = "Bacharidis, K. and Argyros, A.A.",
TITLE = "Vision-based mistake analysis in procedural activities:
A review of advances and challenges",
JOURNAL = CVIU,
VOLUME = "270",
YEAR = "2026",
PAGES = "104842",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108114"}
@inproceedings{bb111455,
AUTHOR = "Bacharidis, K. and Argyros, A.A.",
TITLE = "Repetition-aware Image Sequence Sampling for Recognizing Repetitive
Human Actions",
BOOKTITLE = ACVR23,
YEAR = "2023",
PAGES = "1870-1879",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108115"}
@inproceedings{bb111456,
AUTHOR = "Mahmood, S.A. and Ali, A.S. and Ahmed, U. and Fateh, F.J. and Zia, M.Z. and Tran, Q.H.",
TITLE = "Procedure Learning via Regularized Gromov-Wasserstein Optimal
Transport",
BOOKTITLE = WACV26,
YEAR = "2026",
PAGES = "6925-6935",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108116"}
@inproceedings{bb111457,
AUTHOR = "Safaei, B. and Siddiqui, F. and Xu, J.C. and Patel, V.M. and Lo, S.Y.",
TITLE = "Filter Images First, Generate Instructions Later: Pre-Instruction
Data Selection for Visual Instruction Tuning",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "14247-14256",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108117"}
@inproceedings{bb111458,
AUTHOR = "Ohkawa, T. and Yagi, T. and Nishimura, T. and Furuta, R. and Hashimoto, A. and Ushiku, Y. and Sato, Y.",
TITLE = "Exo2EgoDVC: Dense Video Captioning of Egocentric Procedural
Activities Using Web Instructional Videos",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "8324-8335",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108118"}
@inproceedings{bb111459,
AUTHOR = "Shi, L. and Burkner, P. and Bulling, A.",
TITLE = "ActionDiffusion: An Action-Aware Diffusion Model for Procedure
Planning in Instructional Videos",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "8816-8825",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108119"}
@inproceedings{bb111460,
AUTHOR = "Walsman, A. and Zhang, M. and Fishman, A. and Farhadi, A. and Fox, D.",
TITLE = "Learning to Build by Building Your Own Instructions",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXXXIX: 261-278",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108120"}
@inproceedings{bb111461,
AUTHOR = "Hojel, A. and Bai, Y.T. and Darrell, T.J. and Globerson, A. and Bar, A.",
TITLE = "Finding Visual Task Vectors",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XLIII: 257-273",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108121"}
@inproceedings{bb111462,
AUTHOR = "Batra, A. and Moltisanti, D. and Sevilla Lara, L. and Rohrbach, M. and Keller, F.",
TITLE = "Efficient Pre-training for Localized Instruction Generation of
Procedural Videos",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XXXIX: 347-363",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108122"}
@inproceedings{bb111463,
AUTHOR = "Chen, Y.X. and Li, K. and Bao, W.T. and Patel, D. and Kong, Y. and Min, M.R.Q. and Metaxas, D.N.",
TITLE = "Learning to Localize Actions in Instructional Videos with Llm-based
Multi-pathway Text-video Alignment",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXXXII: 193-210",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108123"}
@inproceedings{bb111464,
AUTHOR = "Zare, A. and Niu, Y. and Ayyubi, H. and Chang, S.F.",
TITLE = "RAP: Retrieval-augmented Planner for Adaptive Procedure Planning in
Instructional Videos",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXXVII: 410-426",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108124"}
@inproceedings{bb111465,
AUTHOR = "Li, Z.Q. and Chen, Q.R. and Han, T.D. and Zhang, Y. and Wang, Y.F. and Xie, W.",
TITLE = "Multi-sentence Grounding for Long-term Instructional Video",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LVI: 200-216",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108125"}
@inproceedings{bb111466,
AUTHOR = "Islam, M.M. and Nagarajan, T. and Wang, H.Y. and Chu, F.J. and Kitani, K. and Bertasius, G. and Yang, X.T.",
TITLE = "Propose, Assess, Search: Harnessing Llms for Goal-oriented Planning in
Instructional Videos",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XIX: 436-452",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108126"}
@inproceedings{bb111467,
AUTHOR = "Nagasinghe, K.R.Y. and Zhou, H.L. and Gunawardhana, M. and Min, M.R.Q. and Harari, D. and Khan, M.H.",
TITLE = "Why Not Use Your Textbook? Knowledge-Enhanced Procedure Planning of
Instructional Videos",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "18816-18826",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108127"}
@inproceedings{bb111468,
AUTHOR = "Ashutosh, K. and Xue, Z. and Nagarajan, T. and Grauman, K.",
TITLE = "Detours for Navigating Instructional Videos",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "18804-18815",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108128"}
@inproceedings{bb111469,
AUTHOR = "Nagarajan, T. and Torresani, L.",
TITLE = "Step Differences in Instructional Video",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "18740-18750",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108129"}
@inproceedings{bb111470,
AUTHOR = "Cui, J.M. and Liu, T.Y. and Meng, Z.Y. and Yu, J. and Song, R. and Zhang, W. and Zhu, Y.X. and Huang, S.Y.",
TITLE = "GROVE: A Generalized Reward for Learning Open-Vocabulary Physical
Skill",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "15781-15790",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108130"}
@inproceedings{bb111471,
AUTHOR = "Cui, J.M. and Liu, T.Y. and Liu, N. and Yang, Y.D. and Zhu, Y.X. and Huang, S.Y.",
TITLE = "AnySkill: Learning Open-Vocabulary Physical Skill for Interactive
Agents",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "852-862",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108131"}
@inproceedings{bb111472,
AUTHOR = "Bansal, S. and Arora, C. and Jawahar, C.V.",
TITLE = "United We Stand, Divided We Fall:
UnityGraph for Unsupervised Procedure Learning from Videos",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "6495-6505",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108132"}
@inproceedings{bb111473,
AUTHOR = "Ben Shabat, Y.Z. and Paul, J. and Segev, E. and Shrout, O. and Gould, S.",
TITLE = "IKEA Ego 3D Dataset: Understanding furniture assembly actions from
ego-view 3D Point Clouds",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "4343-4352",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108133"}
@inproceedings{bb111474,
AUTHOR = "Schoonbeek, T.J. and Houben, T. and Onvlee, H. and de With, P.H.N. and van der Sommen, F.",
TITLE = "IndustReal: A Dataset for Procedure Step Recognition Handling
Execution Errors in Egocentric Videos in an Industrial-Like Setting",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "4353-4362",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108134"}
@inproceedings{bb111475,
AUTHOR = "Abdelslam, M.A. and Rangrej, S.B. and Hadji, I. and Dvornik, N. and Derpanis, K.G. and Fazly, A.",
TITLE = "GePSAn: Generative Procedure Step Anticipation in Cooking Videos",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "2976-2985",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108135"}
@inproceedings{bb111476,
AUTHOR = "Zhong, Y. and Yu, L.C. and Bai, Y. and Li, S.W. and Yan, X.T. and Li, Y.",
TITLE = "Learning Procedure-aware Video Representation from Instructional
Videos and Their Narrations",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "14825-14835",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108136"}
@inproceedings{bb111477,
AUTHOR = "Zhang, J.H. and Cherian, A. and Liu, Y.B. and Ben Shabat, Y.Z. and Rodriguez, C. and Gould, S.",
TITLE = "Aligning Step-by-Step Instructional Diagrams to Video Demonstrations",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "2483-2492",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108137"}
@inproceedings{bb111478,
AUTHOR = "Kosaka, T. and Kosaka, M.",
TITLE = "Development and Discussion of an Authentic Game to Develop Cleaning
Skills",
BOOKTITLE = VAMR23,
YEAR = "2023",
PAGES = "33-42",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108138"}
@inproceedings{bb111479,
AUTHOR = "Pan, Y. and Wu, J.X. and Ju, R. and Zhou, Z. and Gu, J.Y. and Zeng, S.T. and Yuan, L. and Li, M.",
TITLE = "A Multimodal Framework for Automated Teaching Quality Assessment of
One-to-many Online Instruction Videos",
BOOKTITLE = "ICPR22",
YEAR = "2022",
PAGES = "1777-1783",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108139"}
@inproceedings{bb111480,
AUTHOR = "Qin, Y.Z. and Wu, Y.H. and Liu, S.W. and Jiang, H.W. and Yang, R. and Fu, Y. and Wang, X.L.",
TITLE = "DexMV: Imitation Learning for Dexterous Manipulation from Human Videos",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXIX:570-587",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108140"}
@inproceedings{bb111481,
AUTHOR = "Sener, F. and Chatterjee, D. and Shelepov, D. and He, K. and Singhania, D. and Wang, R. and Yao, A.",
TITLE = "Assembly101: A Large-Scale Multi-View Video Dataset for Understanding
Procedural Activities",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "21064-21074",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108141"}
@inproceedings{bb111482,
AUTHOR = "Ghoddoosian, R. and Dwivedi, I. and Agarwal, N. and Dariush, B.",
TITLE = "Weakly-Supervised Action Segmentation and Unseen Error Detection in
Anomalous Instructional Videos",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "10094-10104",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108142"}
@inproceedings{bb111483,
AUTHOR = "Ghoddoosian, R. and Dwivedi, I. and Agarwal, N. and Choi, C. and Dariush, B.",
TITLE = "Weakly-Supervised Online Action Segmentation in Multi-View
Instructional Videos",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "13770-13780",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108143"}
@inproceedings{bb111484,
AUTHOR = "Ghoddoosian, R. and Sayed, S. and Athitsos, V.",
TITLE = "Hierarchical Modeling for Task Recognition and Action Segmentation in
Weakly-Labeled Instructional Videos",
BOOKTITLE = WACV22,
YEAR = "2022",
PAGES = "120-130",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108144"}
@inproceedings{bb111485,
AUTHOR = "Ramrakhya, R. and Undersander, E. and Batra, D. and Das, A.",
TITLE = "Habitat-Web: Learning Embodied Object-Search Strategies from Human
Demonstrations at Scale",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "5163-5173",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108145"}
@inproceedings{bb111486,
AUTHOR = "Zhao, H. and Hadji, I. and Dvornik, N. and Derpanis, K.G. and Wildes, R.P. and Jepson, A.D.",
TITLE = "P3IV: Probabilistic Procedure Planning from Instructional Videos with
Weak Supervision",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "2928-2938",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108146"}
@inproceedings{bb111487,
AUTHOR = "Li, M.H. and Chen, L. and Duarr, Y.Q. and Hu, Z.L. and Feng, J.J. and Zhou, J. and Lu, J.W.",
TITLE = "Bridge-Prompt:
Towards Ordinal Action Understanding in Instructional Videos",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "19848-19857",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108147"}
@inproceedings{bb111488,
AUTHOR = "Singh, K.P. and Bhambri, S. and Kim, B. and Mottaghi, R. and Choi, J.H.",
TITLE = "Factorizing Perception and Policy for Interactive Instruction
Following",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "1868-1877",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108148"}
@inproceedings{bb111489,
AUTHOR = "Bi, J. and Luo, J.B. and Xu, C.L.",
TITLE = "Procedure Planning in Instructional Videos via Contextual Modeling
and Model-based Policy Learning",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "15591-15600",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108149"}
@inproceedings{bb111490,
AUTHOR = "Diaz, M. and Fevens, T. and Paull, L.",
TITLE = "Uncertainty-Aware Policy Sampling and Mixing for Safe Interactive
Imitation Learning",
BOOKTITLE = CRV21,
YEAR = "2021",
PAGES = "72-78",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108150"}
@inproceedings{bb111491,
AUTHOR = "Wang, S.J. and Zhao, W.T. and Kou, Z.Y. and Shi, J. and Xu, C.L.",
TITLE = "How to Make a BLT Sandwich? Learning VQA towards Understanding Web
Instructional Videos",
BOOKTITLE = WACV21,
YEAR = "2021",
PAGES = "1129-1138",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108151"}
@inproceedings{bb111492,
AUTHOR = "Shen, Y.H. and Elhamifar, E.",
TITLE = "Semi-Weakly-Supervised Learning of Complex Actions from Instructional
Task Videos",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "3334-3344",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108152"}
@inproceedings{bb111493,
AUTHOR = "Shen, Y.H. and Elhamifar, E.",
TITLE = "Understanding Multi-Task Activities from Single-Task Videos",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "19120-19131",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108153"}
@inproceedings{bb111494,
AUTHOR = "Elhamifar, E. and Huynh, D.",
TITLE = "Self-supervised Multi-task Procedure Learning from Instructional Videos",
BOOKTITLE = ECCV20,
YEAR = "2020",
PAGES = "XVII:557-573",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108154"}
@inproceedings{bb111495,
AUTHOR = "Yao, C. and Lou, L.Z. and Sui, X.K. and Xu, M.",
TITLE = "Research on Quality Evaluation Algorithm of Flight Training for
National Day Parade Air Echelon",
BOOKTITLE = CVIDL20,
YEAR = "2020",
PAGES = "130-134",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108155"}
@inproceedings{bb111496,
AUTHOR = "Chang, C.Y. and Huang, D.A. and Xu, D. and Adeli, E. and Fei Fei, L. and Niebles, J.C.",
TITLE = "Procedure Planning in Instructional Videos",
BOOKTITLE = ECCV20,
YEAR = "2020",
PAGES = "XI:334-350",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108156"}
@inproceedings{bb111497,
AUTHOR = "Elhamifar, E. and Naing, Z.",
TITLE = "Unsupervised Procedure Learning via Joint Dynamic Summarization",
BOOKTITLE = ICCV19,
YEAR = "2019",
PAGES = "6340-6349",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108157"}
@inproceedings{bb111498,
AUTHOR = "Miech, A. and Zhukov, D. and Alayrac, J. and Tapaswi, M. and Laptev, I. and Alayrac, J.B.",
TITLE = "HowTo100M: Learning a Text-Video Embedding by Watching Hundred
Million Narrated Video Clips",
BOOKTITLE = ICCV19,
YEAR = "2019",
PAGES = "2630-2640",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108158"}
@inproceedings{bb111499,
AUTHOR = "Qian, M. and Nicholson, J. and Wang, E.",
TITLE = "Quality of Experience Comparison Between Binocular and Monocular
Augmented Reality Display Under Various Occlusion Conditions for
Manipulation Tasks with Virtual Instructions",
BOOKTITLE = VAMR19,
YEAR = "2019",
PAGES = "I:490-499",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe497how2.html#TT108159"}
Last update:Sep 30, 2026 at 11:45:00