A Metaverse: Taxonomy, Components, Applications, and Open Challenges

IEEE Access - Tập 10 - Trang 4209-4251 - 2022
Sangmin Park1, Young‐Gab Kim2
1Department of Computer Science and Engineering, Korea University, Seoul 02841, South Korea
2Department of Computer and Information Security, and Convergence Engineering for Intelligent Drone, Sejong University, Seoul 05006, South Korea

Tóm tắt

Từ khóa


Tài liệu tham khảo

10.1109/CVPR46437.2021.01472

10.1109/CVPR46437.2021.00739

10.18653/v1/2021.eacl-main.36

10.18653/v1/2021.naacl-main.324

10.1109/CVPR46437.2021.00873

10.1145/3450626.3459761

10.1007/978-3-662-47909-4

10.1109/CVPR46437.2021.01169

10.1109/CVPR46437.2021.01294

10.1109/CVPR.2019.00684

shekhar, 2018, To reduce the multidimensionality of feature set for anaphora resolution algorithm, Ambient communications and computer systems, 437

10.1109/CVPR.2017.447

10.1016/j.inffus.2020.01.010

heinrich, 2018, Embodied multimodal interaction in language learning: The emil data collection, Proc ICDL-EpiRob Workshop Active Vis Attention Learn (ICDL-Epirob AVAL)(Tokyo), 2, 1

10.18653/v1/W18-0701

zhang, 2018, An interpretable model for scene graph generation, Proc Adv Neural Inf Process Syst, 1

10.1016/j.inffus.2019.06.019

10.1109/ASRU.2017.8268987

das, 2018, Embodied question answering, Proc IEEE Conf Comput Vis and Pattern Recog, 1

kipper, 2012, Augmented Reality An Emerging Technologies Guide to AR

10.1016/j.procs.2013.09.165

müller, 2012, Remembering in the metaverse: Preservation, evaluation, and perception

resmini, 2011, Pervasive Information Architecture - Designing Cross-Channel User Experiences, 4

10.1016/j.compedu.2011.01.009

10.1016/j.elerap.2010.10.003

2021, Detectron2 Github

10.1109/CVPR46437.2021.00149

10.1016/j.chb.2012.04.004

10.21437/Interspeech.2021-1655

10.1016/j.comnet.2012.09.016

sinha, 2021, Multi-armed bandits with cost subsidy, Proc Int Conf Artif Intell Statist, 3016

richard, 2021, Neural synthesis of binaural speech from mono audio, Proc Int Conf Learn Represent, 1

10.1016/j.geoforum.2011.12.008

10.1109/LRA.2021.3062303

10.1016/j.techfore.2012.03.006

10.24963/ijcai.2021/22

10.1109/SLT48900.2021.9383560

10.1145/3411763.3451734

dagan, 2020, Co-evolution of language and agents in referential games, arXiv 2001 03361

10.1145/3442381.3450074

2021, BlenderBot 2 0 GitHub

de lima alcantara, 2021, Diverse and inclusive representation in online advertising: An exploration of the current landscape and people’s expectations

10.1145/3463274.3463275

10.18653/v1/2020.acl-main.195

huang, 2020, Combining label propagation and simple models out-performs graph neural networks, arXiv 2010 13993

10.18653/v1/D19-1006

10.1109/CVPR46437.2021.01279

10.1016/j.jue.2020.103264

j liang, 2020, MixKD: Towards efficient distillation of large-scale language models, arXiv 2011 00593

10.1109/CVPR46437.2021.01220

10.18653/v1/P19-1564

10.1109/CVPR46437.2021.00111

2021, T5 Text-to-Text Transfer Transformer GitHub

10.18653/v1/2020.emnlp-main.162

brown, 2020, Language models are few-shot learners, arXiv 2005 14165

wang, 2020, Abstract diagrammatic reasoning with multiplex graph networks, Proc ICRL, 1

gordon, 2011, Commonsense causal reasoning using millions of personal stories, Proc 35th AAAI Conf Artif Intell, 1

10.1109/CVPR.2019.00683

lu, 2019, Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks, Adv Neural Inf Process Syst, 1

10.1145/1952712.1952717

10.21236/ADA522953

10.1145/3242969.3243019

10.4101/jvwr.v4i1.1901

conitzer, 2017, Multiplicative pacing equilibria in auction markets, arXiv 1706 07151

10.1016/j.arcontrol.2009.05.002

onaolapo, 2021, SocialHEISTing: Understanding stolen Facebook accounts, Proc 30th USENIX Secur Symp (USENIX Security), 1

rymaszewski, 2007, Second Life The Official Guide

10.1016/j.futures.2009.04.013

giraudy, 2021, Measuring long-term displacement using Facebook data

hazan, 2010, Musing the metaverse, Heritage in the Digital Era

gray, 2020, Human-level performance in no-press diplomacy via equilibrium search, arXiv 2010 02923

10.1016/j.dss.2009.02.014

10.1145/3404835.3464924

de cao, 2020, Autoregressive entity retrieval, arXiv 2010 00904

forte, 2010, Metaverse communities and archaeology: The case of Teramo, Proc EuroMed, 79

10.1007/978-3-662-63958-0_34

10.1109/CVPR46437.2021.00094

10.4101/jvwr.v2i5.808

schwenk, 2019, WikiMatrix: Mining 135M parallel sentences in 1620 language pairs from Wikipedia, arXiv 1907 05791

kwanya, 2014, Library 3 0 Intelligent Libraries and Apomediation

min, 2021, NeurIPS 2020 EfficientQA competition: Systems, analyses and lessons learned, arXiv 2101 00133

10.1016/j.procs.2015.08.181

10.18653/v1/2021.eacl-main.50

10.18653/v1/2021.acl-long.328

10.1109/CVPR46437.2021.01249

patrick, 2020, Support-set bottlenecks for video-text representation learning, arXiv 2010 02824

10.1109/CVPR46437.2021.01229

10.1109/CVPR46437.2021.01274

mendez, 2019, Reinforcement learning of multi-domain dialog policies via action embeddings, Proc 3rd Workshop Conversational AI Today’s Practice Tomorrow’s Potential (NIPS), 1

10.1109/ICCV.2017.321

10.1109/CVPR.2018.00872

10.1609/aaai.v34i07.6924

subaši?, 2010, Experience STORIES: A visual news search and summarization system, Proc Eur Conf Mach Learn Knowl Discovery Databases, 619

10.18653/v1/D17-2014

xiong, 2020, Answering complex open-domain questions with multi-hop dense retrieval, arXiv 2009 12756

10.1177/1473871613493996

lewis, 2019, MLQA: Evaluating cross-lingual extractive question answering, arXiv 1910 07475

10.1080/21670811.2016.1186497

10.18653/v1/N16-1008

10.1016/j.eswa.2012.02.087

10.1007/978-3-540-89454-4_37

10.18653/v1/2021.eacl-main.176

10.3390/s21062066

de decker, 2020, Beyond virtual or physical environments: Building a research metaverse a white paper for NDRIO’s Canadian digital research needs assessment

10.14434/sdh.v4i1.26218

10.1002/cav.1752

10.1016/j.procs.2017.08.200

10.1016/j.futures.2015.11.002

10.1016/j.compedu.2016.08.004

10.4101/jvwr.v8i2.7149

10.1016/j.image.2012.10.006

10.21437/Interspeech.2019-1951

10.1609/aaai.v33i01.33013796

10.1609/aaai.v34i07.7005

palaskar, 2018, Multimodal abstractive summarization for How2 videos, Proc Annual Meeting of the Assoc Computational Linguistics, 1

10.18653/v1/D19-1469

10.1016/j.inffus.2020.05.009

10.18653/v1/D17-1158

ammanabrolu, 2020, Graph constrained reinforcement learning for natural language action spaces, Proc ICRL, 1

kemp, 2006, Putting a second life ‘metaverse’ skin on learning management systems, Proc 2nd Life Educ Workshop Second Life Community Conv, 20, 22

long, 2019, Roblox and effect on education

cagnina, 2007, How to compete in the metaverse: The business models in second life

10.1016/j.bushor.2009.07.002

lee, 2019, Large-scale answerer in questioner’s mind for visual dialog question generation, Proc ICLR, 1

10.1016/j.ijinfomgt.2016.04.017

10.1145/3474085.3479238

10.1109/ICSTCC.2014.6982472

10.18653/v1/D19-1063

jiang, 2019, Language as an abstraction for hierarchical deep reinforcement learning, Proc Advances Neural Inf Process Syst, 1

10.1016/j.procs.2020.09.249

10.1016/j.procs.2013.11.039

10.1109/ICSTCC.2014.6982498

yoon, 2015, MPEG-V Bridging the Virtual and Real World

10.1016/j.procs.2014.05.128

10.1016/j.chb.2012.10.004

10.1016/j.image.2012.12.002

ko, 2014, The virtual device managing module of the metaverse assisted living support system, Proc Int Conf Modeling Simulation Vis Methods (MSV) Steering Committee World Congr Comput Eng Appl Comput (WorldComp), 125

10.1145/2480741.2480751

ebrahimi, 2020, Remembering for the right reasons: Explanations reduce catastrophic forgetting, arXiv 2010 01528

sodhani, 2021, Multi-task reinforcement learning with context-based representations, arXiv 2102 06177

10.1145/3450522.3451323

10.1145/3411764.3445064

10.1117/12.541645

10.1109/TASLP.2021.3061939

10.1007/978-3-030-01246-5_21

10.1109/CVPR46437.2021.01365

chen, 2019, Unsupervised object segmentation by redrawing, Proc Adv Neural Inf Process Syst, 1

10.1109/CVPR46437.2021.01089

10.1145/3411764.3445671

sukhbaatar, 2021, Not all memories are created equal: Learning to forget by expiring, arXiv 2105 06548

10.1109/CVPR46437.2021.01300

amos, 2021, On the model-based stochastic value gradient for continuous reinforcement learning, Learning for Dynamics and Control

cui, 2020, Control-aware representations for model-based reinforcement learning, arXiv 2006 13408

modhe, 2019, IR-VIC: Unsupervised discovery of sub-goals for transfer in RL, arXiv 1907 10580

skerry-ryan, 2018, Towards end-to-end prosody transfer for expressive speech synthesis with tacotron, Proc Int Conf Mach Learn, 4693

jiang, 2021, Prioritized level replay, Proc Int Conf Mach Learn, 4940

fazel-zarandi, 2019, Towards personalized dialog policies for conversational skill discovery, Proc 33rd Conf Neural Inf Process Syst (NIPS)

10.1109/TAFFC.2021.3062406

mehta, 2021, Continual learning using a Bayesian nonparametric dictionary of weight factors, Proc Int Conf Artif Intell Statist, 100

10.1109/CVPR46437.2021.00013

10.2139/ssrn.3813522

stephenson, 1992, Snow Crash

2021, Metaverse Wikipedia

10.1007/s11628-011-0108-8

lombardi, 2021, Mixture of volumetric primitives for efficient neural rendering, arXiv 2103 01954

10.1093/oxfordhb/9780199826162.001.0001

bagautdinov, 2021, Driving-signal aware full-body avatars, arXiv 2105 10441

2021, Digital twin wikipedia

10.1145/3478513.3480545

oddone, 2019, Even better than the real thing?, 1

sun, 2021, Human hair inverse rendering using multi-view photometric data, Proc Eurograph Symp Rendering (EGSR), 179

townsdin, 2017, Implementing augmented reality in academic libraries, Public Service, 13, 190, 10.1080/15228959.2017.1338541

chen, 2020, Learning to set waypoints for audio-visual navigation, arXiv 2008 09622

10.3389/fpsyg.2019.01530

szot, 2021, Habitat 2.0: Training home assistants to rearrange their habitat, arXiv 2106 14405

10.3389/fpsyg.2019.01530

ye, 2021, Auxiliary tasks and exploration enable ObjectNav, arXiv 2104 04112

10.1109/CVPR46437.2021.01526

10.1145/3450626.3459829

10.1109/CVPR46437.2021.00790

puig, 2021, Watch- and-help: A challenge for social perception and human-AI collaboration, Proc ICLR, 1

hamrick, 2018, Relational inductive bias for physical construction in humans and machines, Proc Annu Meeting Cogn Sci Soc (CogSci), 1

10.1016/j.cobeha.2018.12.011

zeng, 2020, Graphsaint: Graph sampling based inductive learning method, Proc ICRL, 1

10.18653/v1/P19-1431

eysenbach, 2019, Diversity is all you need: Learning skills without a reward function, Proc ICLR, 1

laskin, 2020, CURL: Contrastive unsupervised representations for reinforcement learning, Proc Int Conf Mach Learn (ICML), 1

zheng, 2019, Persona-aware dialogue generation with enriched profile, Proc 33rd Conf Neural Inf Process Syst (NIPS), 1

asai, 2020, Learning to retrieve reasoning paths over wikipedia graph for question answering, Proc ICLR, 1

10.1016/j.inffus.2020.06.011

10.18653/v1/D17-1060

10.1109/ACCESS.2019.2923057

10.18653/v1/P19-1128

fu, 2019, Paraphrase generation with latent bag of words, Proc Adv Neural Inf Process Syst, 13623

10.1007/s10791-018-9342-1

10.1109/LRA.2021.3057046

10.1145/2736277.2741112

10.1109/IROS45743.2020.9341606

10.1109/HPCA51647.2021.00013

10.1145/3453483.3454050

10.1109/DSN-S52858.2021.00027

maeng, 2021, Understanding and improving failure tolerant training for deep learning recommendation with partial recovery, Proc Mach Learn Syst, 3, 1

li, 2021, Ditto: Fair and robust federated learning through personalization, Proc Int Conf Mach Learn, 6357

li, 2020, Tilted empirical risk minimization, arXiv 2007 01162

2021, CTRL—A Conditional Transformer Language Model for Controllable Generation GitHub

10.1145/3132847.3133095

10.1109/ICASSP39728.2021.9413595

lubis, 2019, Dialogue model and response generation for emotion improvement elicitation, Proc 33rd Conf Neural Inf Process Syst (NIPS), 1

10.1016/j.telpol.2021.102127

10.18653/v1/W19-3402

xia, 2021, A social network under social distancing: Risk-driven backbone management during COVID-19 and beyond, Proc NSDI, 217

10.1007/s41095-020-0162-z

10.1145/3386569.3392410

10.1109/CVPR.2017.128

10.1016/j.inffus.2017.02.003

zhang, 2021, On the importance of hyperparameter optimization for model-based reinforcement learning, Proc Int Conf Artif Intell Statist, 4015

10.1109/CVPR.2018.00611

zhang, 2020, Learning invariant representations for reinforcement learning without reconstruction, arXiv 2006 10742

10.1145/3446804.3446843

10.1109/CVPR.2017.120

zhang, 2020, Learning robust state abstractions for hidden-parameter block MDPs, arXiv 2007 07206

fu, 2021, Learn-to-share: A hardware-friendly transfer learning framework exploiting computation and parameter sharing, Proc Int Conf Mach Learn, 3469

ruiz, 2021, Anytime inference with distilled hierarchical neural ensembles, Proc AAAI Conf Artif Intell, 35, 1

10.1109/CVPR46437.2021.00098

10.1109/CVPR.2017.345

dixit, 2021, Silent data corruptions at scale, arXiv 2102 11245

10.1109/CVPR.2017.681

10.1109/HPCA51647.2021.00072

10.1109/CVPR.2015.7298932

10.1109/CVPR46437.2021.00635

10.1109/CVPR.2017.214

zhao, 2021, Few-shot neural architecture search, Proc Int Conf Mach Learn, 12707

davis, 2018, Modelling visual properties and visual context in multimodal semantics, Proc Adv Neural Inf Process Syst, 1

10.18653/v1/D17-1182

10.18653/v1/D17-1049

vuorio, 2019, Multimodal model-agnostic meta-learning via task-aware modulation, Proc Adv Neural Inf Process Syst, 1

lopez-paz, 2017, Gradient episodic memory for continual learning, Proc Adv Neural Inf Process Syst, 6467

10.1016/bs.pbr.2016.05.005

10.1038/s41586-019-1924-6

10.1146/annurev-psych-113011-143733

10.1109/CVPR46437.2021.00372

liu, 2019, Learning to propagate for graph meta-learning, Proc Adv Neural Inf Process Syst, 1

rabinowitz, 2018, Machine theory of mind, Proc 35th Int Conf Mach Learn, 80, 4218

10.1007/s13218-020-00641-2

10.3389/frvir.2021.647997

racanière, 2017, Imagination-augmented agents for deep reinforcement learning, Proc Adv Neural Inf Process Syst, 5694

maharg, 2007, Simulations, learning and the metaverse: Changing cultures in legal education, J Inform Law Technol, 1, 1

10.3390/su12072875

10.1109/CVPR.2018.00430

qiu, 2020, Target driven visual navigation exploiting object relationships

10.1145/3343031.3351017

10.18653/v1/2020.acl-main.559

baker, 2019, Emergent tool use from multi-agent autocurricula, Proc Int Conf Learn Represent, 1

ilinykh, 2019, Meetup! A corpus of joint activity dialogues in a visual environment, Proc 23rd Workshop Semantics Pragmatics Dialogue (Semdial/LondonLogue), 1

10.1162/isal_a_00269

10.1016/j.techfore.2007.04.007

10.3390/s20216045

barry, 2009, International comparison for problem based learning in metaverse, Proc ICEE ICEER, 6066, 1

templeton, 2020, Getting real: Learning with (and about) augmented reality, Scan J Educators, 39, 6

10.1111/bjet.13003

10.1016/j.procs.2014.08.224

noghabaei, 2020, A survey study to understand industry vision for virtual and augmented reality applications in design and construction, arXiv 2005 02795

10.1016/j.acalib.2020.102294

smart, 2007, A cross-industry public foresight project, Proc Metaverse Roadmap Pathways 3DWeb, 1

newell, 2017, Pixels to graphs by associative embedding, Proc Adv Neural Inf Process Syst, 2168

10.1145/2808797.2809306

paulus, 2018, A deep reinforced model for abstractive summarization, Proc Int Conf Learn Represent (ICLR), 1

gulcehre, 2017, Plan, attend, generate: Planning for sequence-to-sequence models, Proc Adv Neural Inf Process Syst, 5474

10.18653/v1/D15-1289

10.1109/CVPR.2016.323

10.18653/v1/D17-1047

10.1109/THMS.2016.2616296

10.1109/CVPR.2019.00649

niculae, 2017, A regularized framework for sparse and structured neural attention, Proc Adv Neural Inf Process Syst, 3338

10.1109/TMM.2016.2644872

10.3390/app11115277

10.1109/CVPR46437.2021.00687

kanematsu, 2009, Practice and evaluation of problem based learning in metaverse, Proc EdMediaC Innovate Learn Assoc Advancement Comput Educ (AACE), 2862

10.3390/s21113661

10.1145/3411763.3451742

10.1109/WHC49131.2021.9517208

bonatti, 2020, Batteries, camera, action! Learning a semantic control space for expressive robot cinematography, arXiv 2011 10118

10.1109/CVPR46437.2021.00930

rognon, 2021, An online survey on the perception of mediated social touch interaction and device design, arXiv 2104 00086

10.1145/3450626.3459783

10.18653/v1/D17-1101

10.1109/CVPR.2017.331

10.1109/CVPR.2017.470

10.1109/CVPR.2017.763

10.1109/CVPR.2018.00443

10.1145/3291925

10.18653/v1/D17-1238

10.18653/v1/D17-1227

10.18653/v1/D17-1287

swayamdipta, 2018, Multi-mention learning for reading comprehension with neural cascades, Proc Int Conf Learn Represent (ICLR), 1

10.3991/ijet.v15i20.16535

10.1109/TG.2018.2806190

2022, Roblox Blog

10.1109/CVPR46437.2021.00047

lucas, 2021, Chromatic-luminance and true-texture analysis for image mining in the social sciences, 10.31235/osf.io/edb35

d’ascoli, 2021, ConViT: Improving vision transformers with soft convolutional inductive biases, arXiv 2103 10697

10.1109/CVPR46437.2021.00722

10.1109/CVPR46437.2021.00708

10.1109/CVPR46437.2021.00452

xiong, 2021, Multiview pseudo-labeling for semi-supervised learning from video, arXiv 2104 00682

10.1109/PCS50896.2021.9477465

10.1109/CVPR46437.2021.01508

10.1109/CVPR46437.2021.00869

woo, 2018, LinkNet: Relational embedding for scene graph, Proc Adv Neural Inf Process Syst, 1

10.18653/v1/D17-1190

10.1109/CVPR.2017.664

ciliberto, 2017, Consistent multitask learning with nonlinear output relations, Proc Adv Neural Inf Process Syst, 1986

10.1007/978-3-319-26561-2_3

10.1609/aaai.v33i01.33018465

10.18653/v1/D17-1108

10.1007/978-3-319-25207-0_11

10.1145/3343031.3351034

10.1109/ACCESS.2020.2975244

10.3390/app10030957

sodhani, 2021, Multi-task reinforcement learning with context-based representations, arXiv 2102 06177

10.1109/CVPR46437.2021.00467

tian, 2021, Understanding self-supervised learning dynamics without contrastive pairs, arXiv 2102 06810

10.23919/EUSIPCO54536.2021.9616016

liu, 2021, Unbiased teacher for semi-supervised object detection, arXiv 2102 09480

10.1109/CVPR46437.2021.01549

10.1109/ICASSP40776.2020.9054434

10.1109/ICASSP39728.2021.9413955

10.1109/ICASSP39728.2021.9413873

10.1145/3174910.3174952

10.1109/ICASSP39728.2021.9413627

10.1016/j.infsof.2008.09.009

stephenson, 1992, Snowcrash

10.1016/S0016-3287(01)00002-7

10.1145/769953.769967

ondrejka, 2004, Escaping the gilded cage: User created content and building the metaverse, NYL Sch L Rev, 49, 81

10.18653/v1/D17-1216

10.1016/j.artint.2007.10.011

yang, 2017, Differentiable learning of logical rules for knowledge base reasoning, Proc Adv Neural Inf Process Syst, 2319

collins, 2008, Looking to the future: Higher education in the Metaverse, EDUCAUSE Rev, 43, 51

10.1145/1501750.1501812

10.1145/3292500.3330925

schlemmer, 2009, The metaverse: Telepresence in 3D avatar-driven digital-virtual worlds, Tic Revista D’Innovacio Educativa, 2, 26

10.1109/CVPR.2017.232

kocaoglu, 2018, CausalGAN: Learning causal implicit generative models with adversarial training, Proc Int Conf Learn Represent (ICLR), 1

10.18653/v1/D17-1167

10.1145/2647868.2654950

10.18653/v1/P19-1131

10.24963/ijcai.2019/829

10.18653/v1/D17-1223

yu, 2012, A sequential recommendation approach for interactive personalized story generation, Proc 11th Int Conf Auto Agents Multiagent Syst, 1, 71

10.1109/TSP.2021.3057495

10.1109/ICASSP39728.2021.9414042

10.1109/TASLP.2021.3055038

10.17743/jaes.2021.0004

10.17743/jaes.2020.0063

ge, 2020, Creative sketch generation, arXiv 2011 10039

10.1109/ICPR48806.2021.9413318