Abstract
In this work we study the problem of using referential language to identify common objects in real-world 3D scenes. We focus on a challenging setup where the referred object belongs to a fine-grained object class and the underlying scene contains multiple object instances of that class. Due to the scarcity and unsuitability of existent 3D-oriented linguistic resources for this task, we first develop two large-scale and complementary visio-linguistic datasets: i) Sr3D, which contains 83.5 K template-based utterances leveraging spatial relations among fine-grained object classes to localize a referred object in a scene, and ii) Nr3D which contains 41.5K natural, free-form, utterances collected by deploying a 2-player object reference game in 3D scenes. Using utterances of either datasets, human listeners can recognize the referred object with high (>86%, 92% resp.) accuracy. By tapping on this data, we develop novel neural listeners that can comprehend object-centric natural language and identify the referred object directly in a 3D scene. Our key technical contribution is designing an approach for combining linguistic and geometric information (in the form of 3D point clouds) and creating multi-modal (3D) neural listeners . We also show that architectures which promote object-to-object communication via graph neural networks outperform less context-aware alternatives, and that fine-grained object classification is a bottleneck for language-assisted 3D object identification.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
The datasets and neural listener code are available at https://referit3d.github.io.
- 2.
Architecture details and hyper-parameters for all the experiments, are provided in the Supplementary Material [2].
- 3.
In all results mean accuracies and standard errors across 5 random seeds are reported, to control for the point cloud scene sampling.
References
Abdelkarim, S., Achlioptas, P., Huang, J., Li, B., Church, K., Elhoseiny, M.: Long-tail visual relationship recognition with a visiolinguistic hubless loss. CoRR abs/2004.00436 (2020)
Achlioptas, P., Abdelreheem, A., Xia, F., Elhoseiny, M., Guibas, L.: Supplementary material for: ReferIt3D: neural listeners for fine-grained 3D object identification in real world 3D scenes (2020)
Achlioptas, P., Diamanti, O., Mitliagkas, I., Guibas, L.: Learning representations and generative models for 3D point clouds. In: International Conference on Machine Learning (ICML) (2018)
Achlioptas, P., Fan, J., Hawkins, R.X., Goodman, N.D., Guibas, L.J.: ShapeGlot: learning language for shape differentiation. In: International Conference on Computer Vision (ICCV) (2019)
Agrawal, A., Batra, D., Parikh, D.: Analyzing the behavior of visual question answering models. In: Empirical Methods in Natural Language Processing (EMNLP) (2016)
Agrawal, H., et al.: nocaps: novel object captioning at scale. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Akata, Z., Reed, S., Walter, D., Lee, H., Schiele, B.: Evaluation of output embeddings for fine-grained image classification. In: CVPR (2015)
Anayurt, H., Ozyegin, S.A., Cetin, U., Aktas, U., Kalkan, S.: Searching for ambiguous objects in videos using relational referring expressions. CoRR abs/1908.01189 (2019)
Anderson, P., et al.: Vision-and-language navigation: interpreting visually-grounded navigation instructions in real environments. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2018)
Andreas, J., Klein, D.: Reasoning about pragmatics with neural listeners and speakers. CoRR abs/1604.00562 (2016)
Andreas, J., Rohrbach, M., Darrell, T., Klein, D.: Neural module networks. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Antol, S., et al.: VQA: visual question answering. In: International Conference on Computer Vision (ICCV) (2015)
Armeni, I., et al.: 3D semantic parsing of large-scale indoor spaces. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Avetisyan, A., Dahnert, M., Dai, A., Savva, M., Chang, A.X., Nießner, M.: Scan2CAD: learning cad model alignment in RGB-D scans. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Kong, C., Lin, D., Bansal, M., Urtasun, R., Fidler, S.: What are you talking about? Text-to-image coreference. In: CVPR (2014)
Chen, K., Choy, C.B., Savva, M., Chang, A.X., Funkhouser, T., Savarese, S.: Text2Shape: generating shapes from natural language by learning joint embeddings. CoRR abs/1803.08495 (2018)
Chen, Z.D., Chang, A.X., Nießner, M.: https://github.com/daveredrum/ScanRefer. Accessed 17 July 2020
Chen, Z.D., Chang, A.X., Nießner, M.: ScanRefer: 3D object localization in RGB-D scans using natural language. CoRR abs/1912.08830 (2019)
Cohn-Gordon, R., Goodman, N., Potts, C.: Pragmatically informative image captioning with character-level inference. CoRR abs/1804.05417 (2018)
Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nießner, M.: ScanNet: richly-annotated 3D reconstructions of indoor scenes. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
Das, A., Datta, S., Gkioxari, G., Lee, S., Parikh, D., Batra, D.: Embodied question answering. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2018)
Devlin, J., Gupta, S., Girshick, R., Mitchell, M., Zitnick, C.L.: Exploring nearest neighbor approaches for image captioning. arXiv preprint arXiv:1505.04467 (2015)
Doğan, F.I., Kalkan, S., Leite, I.: Learning to generate unambiguous spatial referring expressions for real-world environments. CoRR (2019)
Elhoseiny, M., Elfeki, M.: Creativity inspired zero-shot learning. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5784–5793 (2019)
Elhoseiny, M., Saleh, B., Elgammal, A.: Write a classifier: zero-shot learning using purely textual descriptions. In: ICCV (2013)
Elhoseiny, M., Zhu, Y., Zhang, H., Elgammal, A.: Link the head to the “beak”: zero shot learning from noisy text description at part precision. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in visual question answering. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
Karpathy, A., Joulin, A., Li, F.F.F.: Deep fragment embeddings for bidirectional image sentence mapping. In: Advances in Neural Information Processing Systems (NeurIPS) (2014)
Kazemzadeh, S., Ordonez, V., Matten, M., Berg, T.: ReferitGame: referring to objects in photographs of natural scenes. In: Empirical Methods in Natural Language Processing (EMNLP) (2014)
Kim, J.H., Jun, J., Zhang, B.T.: Bilinear attention networks. In: Advances in Neural Information Processing Systems (NeurIPS) (2018)
Kiros, R., Salakhutdinov, R., Zemel, R.S., et al.: Unifying visual-semantic embeddings with multimodal neural language models. Trans. Assoc. Comput. Linguist. (TACL) (2015)
Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. 123(1), 32–73 (2017). https://doi.org/10.1007/S11263-016-0981-7
Kulkarni, N., Misra, I., Tulsiani, S., Gupta, A.: 3D-RelNet: joint object and relational network for 3D prediction. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Lazaridou, A., Hermann, K.M., Tuyls, K., Clark, S.: Emergence of linguistic communication from referential games with symbolic and pixel input. arXiv preprint arXiv:1804.03984 (2018)
Ba, J.L., Swersky, K., Fidler, S., et al.: Predicting deep zero-shot convolutional neural networks using textual descriptions. In: ICCV (2015)
Lewis, D.: Convention: A Philosophical Study. Wiley, Hoboken (2008)
Li, C., Xia, F., Martín-Martín, R., Savarese, S.: HRL4IN: hierarchical reinforcement learning for interactive navigation with mobile manipulators. In: Conference on Robot Learning (2020)
Long, Y., Shao, L.: Describing unseen classes by exemplars: zero-shot learning using grouped simile ensemble. In: Winter Conference on Applications of Computer Vision (WACV) (2017)
Long, Y., Shao, L.: Learning to recognise unseen classes by a few similes. In: Proceedings of the 25th ACM International Conference on Multimedia, pp. 636–644. ACM (2017)
Lu, C., Krishna, R., Bernstein, M., Fei-Fei, L.: Visual relationship detection with language priors. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 852–869. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_51
Mao, J., Xu, W., Yang, Y., Wang, J., Yuille, A.: Deep captioning with multimodal recurrent neural networks (m-RNN). In: International Conference on Learning Representations (ICLR) (2015)
Mauceri, C., Palmer, M., Heckman, C.: SUN-Spot: an RGB-D dataset with spatial referring expressions. In: International Conference on Computer Vision Workshop on Closing the Loop Between Vision and Language (2019)
Mitchell, M., van Deemter, K., Reiter, E.: Generating expressions that refer to visible objects. In: North American Chapter of the Association for Computational Linguistics (NAACL) (2013)
Mo, K., et al.: A large-scale benchmark for fine-grained and hierarchical part-level 3D object understanding. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Monroe, W., Hawkins, R.X., Goodman, N.D., Potts, C.: Colors in context: a pragmatic neural model for grounded language understanding. Trans. Assoc. Comput. Linguist. (TACL) (2017)
Paetzel, M., Racca, D.N., DeVault, D.: A multimodal corpus of rapid dialogue games. In: LREC, pp. 4189–4195 (2014)
Plummer, B.A., et al.: Revisiting image-language networks for open-ended phrase detection. CoRR abs/1811.07212 (2018)
Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2015)
Prabhudesai, M., Tung, H.Y.F., Javed, S.A., Sieb, M., Harley, A.W., Fragkiadaki, K.: Embodied language grounding with implicit 3D visual feature representations. CoRR abs/1910.01210 (2019)
Qi, C.R., Litany, O., He, K., Guibas, L.: Deep hough voting for 3D object detection in point clouds. In: International Conference on Computer Vision (ICCV) (2019)
Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space. In: Advances in Neural Information Processing Systems (NeurIPS) (2017)
Ramanathan, V., Joulin, A., Liang, P., Fei-Fei, L.: Linking people with “their” names using coreference resolution. In: European Conference on Computer Vision (ECCV) (2014)
Ren, M., Kiros, R., Zemel, R.: Exploring models and data for image question answering. In: Advances in Neural Information Processing Systems (NeurIPS) (2015)
Romera-Paredes, B., Torr, P.: An embarrassingly simple approach to zero-shot learning. In: ICML, pp. 2152–2161 (2015)
Rosman, B., Ramamoorthy, S.: Learning spatial relationships between objects. Int. J. Rob. Res. 30(11), 1328–1342 (2011)
Savva, M., et al.: Habitat: a platform for embodied AI research. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Shridhar, M., et al.: ALFRED: a benchmark for interpreting grounded instructions for everyday tasks. CoRR abs/1912.01734 (2019)
Socher, R., Ganjoo, M., Manning, C.D., Ng, A.: Zero-shot learning through cross-modal transfer. In: NeurIPS, pp. 935–943 (2013)
Su, J.C., Wu, C., Jiang, H., Maji, S.: Reasoning about fine-grained attribute phrases using reference games. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 418–427 (2017)
Tsai, Y.H.H., Huang, L.K., Salakhutdinov, R.: Learning robust visual-semantic embeddings. In: ICCV (2017)
Vedantam, R., Bengio, S., Murphy, K., Parikh, D., Chechik, G.: Context-aware captions from context-agnostic supervision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 251–260 (2017)
Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2015)
Wang, Y., Sun, Y., Liu, Z., Sarma, S.E., Bronstein, M.M., Solomon, J.M.: Dynamic graph CNN for learning on point clouds. ACM Trans. Graph. (TOG) 38(5), 1–12 (2019)
Wittgenstein., L.: Philosophical Investigations: the English text of the third edition. Wiley, Hoboken (1953)
Xia, F., Zamir, A.R., He, Z., Sax, A., Malik, J., Savarese, S.: Gibson Env: real-world perception for embodied agents. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2018)
Xiang, F., et al.: SAPIEN: a simulated part-based interactive environment. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11097–11107 (2020)
Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning (ICML) (2015)
Yang, J., et al.: Embodied visual recognition. CoRR abs/1904.04404 (2019)
Yang, Y., Hospedales, T.M.: A unified perspective on multi-domain and multi-task learning. In: ICLR (2015)
Yu, Z., Yu, J., Cui, Y., Tao, D., Tian, Q.: Deep modular co-attention networks for visual question answering. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Zhang, J., Kalantidis, Y., Rohrbach, M., Paluri, M., Elgammal, A., Elhoseiny, M.: Large-scale visual relationship understanding. In: AAAI Conference on Artificial Intelligence (2019)
Zhou, L., Kalantidis, Y., Chen, X., Corso, J.J., Rohrbach, M.: Grounded video description. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Zhu, Y., Elhoseiny, M., Liu, B., Peng, X., Elgammal, A.: A generative adversarial approach for zero-shot learning from noisy texts. In: CVPR (2018)
Acknowledgment
The authors wish to acknowledge the support of a Vannevar Bush Faculty Fellowship, a grant from the Samsung GRO program and the Stanford SAIL Toyota Research Center, NSF grant IIS-1763268, KAUST grant BAS/1/1685-01-01, and a research gift from Amazon Web Services. Also, they wish to thank Prof. Angel X. Chang for the inspiring discussions regarding the creation of synthetic 3D spatial data, and Iro Armeni and Antonia Saravanou for their help in writing.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Achlioptas, P., Abdelreheem, A., Xia, F., Elhoseiny, M., Guibas, L. (2020). ReferIt3D: Neural Listeners for Fine-Grained 3D Object Identification in Real-World Scenes. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12346. Springer, Cham. https://doi.org/10.1007/978-3-030-58452-8_25
Download citation
DOI: https://doi.org/10.1007/978-3-030-58452-8_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58451-1
Online ISBN: 978-3-030-58452-8
eBook Packages: Computer ScienceComputer Science (R0)