There is More than Meets the Eye: Self-Supervised Multi-Object Detection and Tracking with Sound by Distilling Multimodal Knowledge
Open accessThe DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Abstract
Attributes of sound inherent to objects can provide valuable cues to learn rich representations for object detection and tracking. Furthermore, the co-occurrence of audiovisual events in videos can be exploited to localize objects over the image field by solely monitoring the sound in the environment. Thus far, this has only been feasible in scenarios where the camera is static and for single object detection. Moreover, the robustness of these methods has been limited as they primarily rely on RGB images which are highly susceptible to illumination and weather changes. In this work, we present the novel self-supervised MM-DistillNet framework consisting of multiple teachers that leverage diverse modalities including RGB, depth and thermal images, to simultaneously exploit complementary cues and distill knowledge into a single audio student network. We propose the new MTA loss function that facilitates the distillation of information from multimodal teachers in a self-supervised manner. Additionally, we propose a novel self-supervised pretext task for the audio student that enables us to not rely on labor-intensive manual annotations. We introduce a large-scale multimodal dataset with over 113,000 time-synchronized frames of RGB, depth, thermal, and audio modalities. Extensive experiments demonstrate that our approach outperforms state-of-the-art methods while being able to detect multiple objects using only sound during inference and even while moving.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
EfficientDet: Scalable and Efficient Object Detection
Tan, M., Pang, R., & Le, Q. V. (2019) · arXiv · Cited by 9,841 · cited 2×
“We build upon the EfficientDet [42] architecture for the modality-specific teacher networks.”
MethodEvaluating Multiple Object Tracking Performance: The CLEAR MOT Metrics
Bernardin, K., & Stiefelhagen, R. (2008) · EURASIP Journal on Image and Video Processing · doi:10.1155/2008/246309 · Cited by 2,918
FitNets: Hints for Thin Deep Nets
Romero, A., Ballas, N., Kahou, S. E., Chassang, A., Gatta, C., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1412.6550 · Cited by 2,859
Searching for activation functions
Ramachandran, P., Zoph, B., & Le, Q. V. (2017) · arXiv · doi:10.48550/arxiv.1710.05941 · Cited by 2,335 · cited 1×
“The last stage of the network is a classifier and regressor branch that consist of a sequence of separable convolutions, batch normalization, and a memory-efficient swish [36].”
BackgroundArgoverse: 3D Tracking and Forecasting With Rich Maps
Chang, M.-F., Lambert, J., Sangkloy, P., Singh, J., Bak, S., Hartnett, A., Wang, D., Carr, P., Lucey, S., Ramanan, D., et al. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00895 · Cited by 1,474 · cited 2×
“• Depth teacher that we train on the Argoverse [12] dataset using 3D vehicle bounding boxes mapped to 2D. Note that Argoverse does not provide direct depth/disparity data.”
MethodAudio-Visual Scene Analysis with Self-Supervised Multisensory Features
Owens, A., & Efros, A. A. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01231-1_39 · Cited by 704
Learning to Localize Sound Source in Visual Scenes
Senocak, A., Oh, T.-H., Kim, J., Yang, M.-H., & Kweon, I. S. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00458 · Cited by 328
Learnable PINs: cross-modal embeddings for person identity
Nagrani, A., Albanie, S., & Zisserman, A. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01261-8_5 · Cited by 151
Cited by
COCOA: Cross Modality Contrastive Learning for Sensor Data
Deldari, S., Xue, H., Saeed, A., Smith, D. V., & Salim, F. D. (2022) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3550316 · Cited by 92
Yi (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.11.056 · Cited by 49
Honerkamp, D., Welschehold, T., & Valada, A. (2023) · IEEE Transactions on Robotics · doi:10.1109/tro.2023.3284346 · Cited by 30
Self-citation
Metadata
- Authors
- Valverde, F. R., Valeria Hurtado, J., & Valada, A.
- Venue
- 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2021-06
- Pages
- 11607-11616
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3135163157
- Cited by
- 76
- References
- 9
- FWCI
- 10.20
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: There is More than Meets the Eye: Self-Supervised Multi-Object Detection and Tracking with Sound by Distilling Multimodal Knowledge. https://app.cochat.ai/papers/10.1109/cvpr46437.2021.01144
- The paper
- Valverde, F. R., Valeria Hurtado, J., & Valada, A. (2021). There is More than Meets the Eye: Self-Supervised Multi-Object Detection and Tracking with Sound by Distilling Multimodal Knowledge. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/cvpr46437.2021.01144
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.