Skip to main content

InstaIndoor and multi-modal deep learning for indoor scene recognition


Indoor scene recognition is a growing field with great potential for behaviour understanding, robot localization, and elderly monitoring, among others. In this study, we approach the task of scene recognition from a novel standpoint, using multi-modal learning and video data gathered from social media. The accessibility and variety of social media videos can provide realistic data for modern scene recognition techniques and applications. We propose a model based on fusion of transcribed speech to text and visual features, which is used for classification on a novel dataset of social media videos of indoor scenes named InstaIndoor. Our model achieves up to 70% accuracy and 0.7 F1-Score. Furthermore, we highlight the potential of our approach by benchmarking on a YouTube-8M subset of indoor scenes as well, where it achieves 74% accuracy and 0.74 F1-Score. We hope the contributions of this work pave the way to novel research in the challenging field of indoor scene recognition.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9


  1. Both datasets and corresponding pipeline code are available at

  2. Both datasets and corresponding pipeline code are available at


  1. Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado G.S, Davis A, Dean J, Devin M, et al (2016) Tensorflow: A system for large-scale machine learning. USENIX Conference on Operating Systems Design and Implementation pp. 265–283

  2. Abu-El-Haija S, Kothari N, Lee J, Natsev P, Toderici G, Varadarajan B, Vijayanarasimhan S (2016) Youtube-8M: A large-scale video classification benchmark. arXiv preprint arXiv:1609.08675

  3. Alayrac JB, Bojanowski P, Agrawal N, Sivic J, Laptev I, Lacoste-Julien S (2016) Unsupervised learning from narrated instruction videos. IEEE Conference on Computer Vision and Pattern Recognition pp. 4575–4583

  4. Arandjelovic R, Gronat P, Torii A, Pajdla T, Sivic J (2016) NetVLAD: CNN architecture for weakly supervised place recognition. IEEE Conference on Computer Vision and Pattern Recognition pp. 5297–5307

  5. Bradski G (2000) The openCV library. Dr. Dobb’s J Softw Tools 120:122–125

    Google Scholar 

  6. Caruana R, Lawrence S, Giles L (2001) Overfitting in neural nets: backpropagation, conjugate gradient, and early stopping. Advances in Neural Information Processing Systems pp. 402–408

  7. Castro FM, Marin-Jimenez MJ, Guil N, de la Blanca NP (2020) Multimodal feature fusion for CNN-based gait recognition: an empirical comparison. Neural Comput Appl 32:14173

    Article  Google Scholar 

  8. Cheng G, Han J, Lu X (2017) Remote sensing image scene classification: benchmark and state of the art. Proceedings of IEEE 105(10):1865–1883

    Article  Google Scholar 

  9. Chollet F, et al (2015) Keras,

  10. Damen D, Doughty H, Farinella GM, Fidler S, Furnari A, Kazakos E, Moltisanti D, Munro J, Perrett T, Price W, et al (2018) Scaling egocentric vision: the epic-kitchens dataset. European Conference on Computer Vision pp. 720–736

  11. Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) ImageNet: a large-scale hierarchical image database. IEEE Conference on Computer Vision and Pattern Recognition pp. 248–255

  12. DeSouza GN, Kak AC (2002) Vision for mobile robot navigation: a survey. Trans Anal Mach Intell 24(2):237–267

    Article  Google Scholar 

  13. DeTone D, Malisiewicz T, Rabinovich A (2018) Superpoint: self-supervised interest point detection and description. IEEE Conference on Computer Vision and Pattern Recognition workshops pp. 224–236

  14. Devlin J, Chang M.W, Lee K, Toutanova K (2019) BERT: Pre-training of deep bidirectional transformers for language understanding. Proceedings of NAACL-HLT pp. 4171–4186

  15. Diwadkar VA, McNamara TP (1997) Viewpoint dependence in scene recognition. Psychol Sci 8(4):302–307

    Article  Google Scholar 

  16. Dusmanu M, Rocco I, Pajdla T, Pollefeys M, Sivic J, Torii A, Sattler T (2019) D2-net: A trainable CNN for joint description and detection of local features. IEEE Conference on Computer Vision and Pattern Recognition pp. 8092–8101

  17. Espinace P, Kollar T, Soto A, Roy N (2010) Indoor scene recognition through object detection. IEEE International Conference on Robotics and Automation pp. 1406–1413

  18. Fouhey DF, Kuo Wc, Efros AA, Malik J (2018) From lifestyle vlogs to everyday interactions. IEEE Conference on Computer Vision and Pattern Recognition pp. 4991–5000

  19. Gelli F, Uricchio T, Bertini M, Del Bimbo A, Chang SF (2015) Image popularity prediction in social media using sentiment and context features. International Conference on Multimedia pp. 907–910

  20. Google C (2021) Google speech to text,

  21. Gwi G Social media trends in 2021: Latest trends & statistics. GWI

  22. Harouni A, Karargyris A, Negahdar M, Beymer D, Syeda-Mahmood T (2018) Universal multi-modal deep network for classification and segmentation of medical images. International Symposium on Biomedical Imaging pp. 872–876

  23. Hassanpour S, Tomita N, DeLise T, Crosier B, Marsch LA (2019) Identifying substance use risk based on deep neural networks and instagram social media data. Neuropsychopharmacology 44(3):487–494

    Article  Google Scholar 

  24. Hausler S, Garg S, Xu M, Milford M, Fischer T (2021) Patch-netvlad: multi-scale fusion of locally-global descriptors for place recognition. IEEE Conference on Computer Vision and Pattern Recognition pp. 14141–14152

  25. Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780

    Article  Google Scholar 

  26. Huang J, Liu Z, Wang Y (2005) Joint scene classification and segmentation based on hidden markov model. IEEE Trans Multimed 7(3):538–550

    Article  Google Scholar 

  27. Huang Q, Xiong Y, Xiong Y, Zhang Y, Lin D (2018) From trailers to storylines: an efficient way to learn from movies. European Conference on Computer Vision

  28. Huang W, Wai AAP, Foo SF, Biswas J, Hsia CC, Liou K (2010) Multimodal sleeping posture classification. International Conference on Pattern Recognition pp. 4336–4339

  29. Khan SH, Hayat M, Bennamoun M, Togneri R, Sohel FA (2016) A discriminative representation of convolutional features for indoor scene recognition. IEEE Trans Image Process 25(7):3372–3383

    Article  MathSciNet  Google Scholar 

  30. Kingma DP, Ba J (2015) Adam: a method for stochastic optimization. CoRR arXiv:1412.6980

  31. Lan T, Chen TC, Savarese S (2014) A hierarchical representation for future action prediction. European Conference on Computer Vision pp. 689–704

  32. Lee J, Reade W, Sukthankar R, Toderici G, et al (2018) The 2nd youtube-8m large-scale video understanding challenge. In: European Conference on Computer Vision Workshops

  33. Leyva-Vallina M, Strisciuglio N, Petkov N (2021) Generalized contrastive optimization of siamese networks for place recognition. arXiv preprint arXiv:2103.06638

  34. Li H, Ma X, Wang F, Liu J, Xu K (2013) On popularity prediction of videos shared in online social networks. ACM International Conference on Information & Knowledge Management pp. 169–178

  35. Liu M, Chen R, Li D, Chen Y, Guo G, Cao Z, Pan Y (2017) Scene recognition for indoor localization using a multi-sensor fusion approach. Sensors 17(12):2847

    Article  Google Scholar 

  36. Liu Y, Yan X, Ca Zhang, Liu W (2019) An ensemble convolutional neural networks for bearing fault diagnosis using multi-sensor data. Sensors 19(23):5300

    Article  Google Scholar 

  37. Liu Y, Ott M, Goyal N, Du J, Joshi M, Chen D, Levy O, Lewis M, Zettlemoyer L, Stoyanov V (2019) Roberta: a robustly optimized BERT pretraining approach. ICLR pp. 1–15

  38. Liu Z, Wang Y, Chen T (1998) Audio feature extraction and analysis for scene segmentation and classification. J VLSI Sig Process Syst 20(1):61–79

    Article  Google Scholar 

  39. Lowry S, Sünderhauf N, Newman P, Leonard JJ, Cox D, Corke P, Milford MJ (2015) Visual place recognition: a survey. IEEE Trans Robot 32(1):1–19

    Article  Google Scholar 

  40. Lu D, Weng Q (2007) A survey of image classification methods and techniques for improving classification performance. J Remote Sens 28(5):823–870

    Article  Google Scholar 

  41. Marszalek M, Laptev I, Schmid C (2009) Actions in context. IEEE Conference on Computer Vision and Pattern Recognition pp. 2929–2936

  42. Martinez ET, Leyva-Vallina M, Sarker MMK, Puig D, Petkov N, Radeva P (2019) Hierarchical approach to classify food scenes in egocentric photo-streams. J Biomed Health Inform 24(3):866–877

    Article  Google Scholar 

  43. Matthews I, Cootes TF, Bangham JA, Cox S, Harvey R (2002) Extraction of visual features for lipreading. Trans Pattern Anal Mach Intell 24(2):198–213

    Article  Google Scholar 

  44. Mikolov T, Chen K, Corrado G, Dean J (2013) Efficient estimation of word representations in vector space

  45. Modiri Assari S, Roshan Zamir A, Shah M (2014) Video classification using semantic concept co-occurrences. IEEE Conference on Computer Vision and Pattern Recognition pp. 2529–2536

  46. Ngiam J, Khosla A, Kim M, Nam J, Lee H, Ng AY (2011) Multimodal deep learning. International Conference on Machine Learning pp. 1–9

  47. Oh J, Guo X, Lee H, Lewis R, Singh S (2015) Action-conditional video prediction using deep networks in Atari games. International Conference on Neural Information Processing Systems pp. 1–9

  48. Patterson E.K, Gurbuz S, Tufekci Z, Gowdy JN (2002) CUAVE: A new audio-visual database for multimodal human-computer interface research. IEEE International Conference on Acoustics, Speech, and Signal Processing 2, II–2017

  49. Perrin A (2015) Pew research center. Soc Med Usage 125:52–68

    Google Scholar 

  50. Quattoni A, Torralba A (2009) Recognizing indoor scenes. IEEE Conference on Computer Vision and Pattern Recognition pp. 413–420

  51. Reimers N, Gurevych I (2019) Sentence-BERT: sentence embeddings using siamese BERT-networks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. pp. 3982–3992. Association for Computational Linguistics

  52. Roach M, Mason JS (2001) Classification of video genre using audio. European Conference on Speech Communication and Technology pp. 1–4

  53. Sanabria R, Caglayan O, Palaskar S, Elliott D, Barrault L, Specia L, Metze F (2018) How2: a large-scale dataset for multimodal language understanding. Advances in Neural Information Processing Systems Workshop on Visually Grounded Interaction and Language

  54. Shah S, Aggarwal JK (1997) Mobile robot navigation and scene modeling using stereo fish-eye lens system. Mach Vis Appl 10(4):159–173

    Article  Google Scholar 

  55. Si C, Chen W, Wang W, Wang L, Tan T (2019) An attention enhanced graph convolutional LSTM network for skeleton-based action recognition. IEEE Conference on Computer Vision and Pattern Recognition pp. 1227–1236

  56. Silberman N, Fergus R (2011) Indoor scene segmentation using a structured light sensor. International Conference on Computer Vision Workshops pp. 601–608

  57. Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. CoRR arXiv:1409.1556

  58. Singh B, Sharma DK (2021) Predicting image credibility in fake news over social media using multi-modal approach. Neural Computing and Applications pp. 1–15

  59. Sureka A, Kumaraguru P, Goyal A, Chhabra S (2010) Mining youtube to discover extremist videos, users and hidden communities. Asia Information Retrieval Symposium pp. 13–24

  60. Taira H, Okutomi M, Sattler T, Cimpoi M, Pollefeys M, Sivic J, Pajdla T, Torii A (2018) Inloc: Indoor visual localization with dense matching and view synthesis. IEEE Conference on Computer Vision and Pattern Recognition pp. 7199–7209

  61. Tan W, Tiwari P, Pandey HM, Moreira C, Jaiswal AK (2020) Multimodal medical image fusion algorithm in the era of big data. Neural Computing and Applications pp. 1–21

  62. Tapaswi M, Zhu Y, Stiefelhagen R, Torralba A, Urtasun R, Fidler S (2016) MovieQA: Understanding stories in movies through question-answering. IEEE Conference on Computer Vision and Pattern Recognition pp. 4631–4640

  63. Toft C, Maddern W, Torii A, Hammarstrand L, Stenborg E, Safari D, Okutomi M, Pollefeys M, Sivic J, Pajdla T, et al (2020) Long-term visual localization revisited. IEEE Transactions on Pattern Analysis and Machine Intelligence pp. 1–14

  64. Tsai G, Xu C, Liu J, Kuipers B (2011) Real-time indoor scene understanding using bayesian filtering with motion cues. International Conference on Computer Vision pp. 121–128

  65. Van Rossum G, Drake FL (2009) Python 3 Reference Manual. Scotts Valley, CA

    Google Scholar 

  66. Warburg F, Hauberg S, Lopez-Antequera M, Gargallo P, Kuang Y, Civera J (2020) Mapillary street-level sequences: A dataset for lifelong place recognition. IEEE Conference on Computer Vision and Pattern Recognition pp. 2626–2635

  67. Xiao J, Hays J, Ehinger K.A, Oliva A, Torralba A (2010) Sun database: Large-scale scene recognition from abbey to zoo. IEEE Conference on Computer Vision and Pattern Recognition pp. 3485–3492

  68. Xingjian S, Chen Z, Wang H, Yeung DY, Wong WK, Woo Wc (2015) Convolutional LSTM network: A machine learning approach for precipitation nowcasting. Advances in neural information processing systems pp. 802–810

  69. Xu Y, Huang J, Wang J, Wang Y, Qin H, Nan K (2021) Esa-vlad: a lightweight network based on second-order attention and netvlad for loop closure detection. IEEE Robot Autom Lett 6(4):6545–6552

    Article  Google Scholar 

  70. Yang X, Luo J (2017) Tracking illicit drug dealing and abuse on instagram using multimodal analysis. Trans Intell Syst Technol 8(4):1–15

    Article  MathSciNet  Google Scholar 

  71. Ye H, Wu Z, Zhao RW, Wang X, Jiang YG, Xue X (2015) Evaluating two-stream CNN for video classification. 5th ACM on International Conference on Multimedia Retrieval pp. 435–442

  72. Yu J, Zhu C, Zhang J, Huang Q, Tao D (2019) Spatial pyramid-enhanced netvlad with weighted triplet loss for place recognition. IEEE Trans Neural Netw Learn Syst 31(2):661–674

    Article  Google Scholar 

  73. Zhang C, Peng Y (2018) Visual data synthesis via GAN for zero-shot video classification. 27th International Joint Conference on Artificial Intelligence pp. 1128–1134

  74. Zhang Y, Jin R, Zhou ZH (2010) Understanding bag-of-words model: a statistical framework. J Mach Learn Cybernet 1(1–4):43–52

    Article  Google Scholar 

  75. Zheng JY, Tsuji S (1992) Panoramic representation for route recognition by a mobile robot. Int J Comput Vis 9(1):55–76

    Article  Google Scholar 

  76. Zhou B, Lapedriza A, Khosla A, Oliva A, Torralba A (2017) Places: a 10 million image database for scene recognition. Transactions on Pattern Analysis and Machine Intelligence pp. 1–23

  77. Zhou B, Lapedriza A, Xiao J, Torralba A, Oliva A (2014) Learning deep features for scene recognition using places database. Neural Information Processing Systems Foundation pp. 1–9

  78. Zhou L, Xu C, Corso J (2018) Towards automatic learning of procedures from web instructional videos. AAAI Conference on Artificial Intelligence pp. 7590–7598

Download references


We would like to thank the Center for Information Technology of the University of Groningen for their support and for providing access to the Peregrine high performance computing cluster.

Author information

Authors and Affiliations


Corresponding author

Correspondence to Andreea Glavan.

Ethics declarations

Conflict of interest

The authors declare that they have no conflicts of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Glavan, A., Talavera, E. InstaIndoor and multi-modal deep learning for indoor scene recognition. Neural Comput & Applic 34, 6861–6877 (2022).

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI:


  • Multi-modal
  • Scene recognition
  • Video classification
  • Behaviour understanding
  • Deep learning