Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time
Open accessThe DOI matches its Crossref record; 25 of the 25 references it cites were found in a registry or an index.
Abstract
Estimating 3D hand and object pose from a single image is an extremely challenging problem: hands and objects are often self-occluded during interactions, and the 3D annotations are scarce as even humans cannot directly label the ground-truths from a single image perfectly. To tackle these challenges, we propose a unified framework for estimating the 3D hand and object poses with semi-supervised learning. We build a joint learning framework where we perform explicit contextual reasoning between hand and object representations. Going beyond limited 3D annotations in a single image, we leverage the spatial-temporal consistency in large-scale hand-object videos as a constraint for generating pseudo labels in semi-supervised learning. Our method not only improves hand pose estimation in challenging real-world dataset, but also substantially improve the object pose which has fewer ground-truths per instance. By training with large-scale diverse videos, our model also generalizes better across multiple out-of-domain datasets. Project page and code: https://stevenlsw.github.io/Semi-Hand-Object
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
You Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803
Feature Pyramid Networks for Object Detection
Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.106 · Cited by 30,939
Wang, X., Girshick, R., Gupta, A., & He, K. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00813 · Cited by 11,596
Self-citationGreff, K., Srivastava, R. K., Koutnik, J., Steunebrink, B. R., & Schmidhuber, J. (2017) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2016.2582924 · Cited by 6,955 · cited 2×
“[7] proposed to fuse hand-object representations to get interaction-aware features for joint pose estimation using LSTM [15].”
BackgroundStacked Hourglass Networks for Human Pose Estimation
Newell, A., Yang, K., & Deng, J. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46484-8_29 · Cited by 5,634 · cited 1×
“The 2D joints localization network is an hourglass [39] module which takes the hand features after RoIAlign [20] as input and outputs 2D heatmaps for each joint j ∈ J , where J 2D ∈ R ×2 and N = 21 is the number of joints.”
MethodHe, K., Gkioxari, G., Dollar, P., & Girshick, R. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2844175 · Cited by 3,457
Self-Training With Noisy Student Improves ImageNet Classification
Xie, Q., Luong, M.-T., Hovy, E., & Le, Q. V. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01070 · Cited by 2,393
PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes
Xiang, Y., Schmidt, T., Narayanan, V., & Fox, D. (2018) · Robotics: Science and Systems XIV · doi:10.15607/rss.2018.xiv.019 · Cited by 2,139
Relation Networks for Object Detection
Hu, H., Gu, J., Zhang, Z., Dai, J., & Wei, Y. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00378 · Cited by 1,524
The “Something Something” Video Database for Learning and Evaluating Visual Common Sense
Goyal, R., Kahou, S. E., Michalski, V., Materzynska, J., Westphal, S., Kim, H., Haenel, V., Fruend, I., Yianilos, P., Mueller-Freitag, M., et al. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.622 · Cited by 1,471
A simple neural network module for relational reasoning
Santoro, A., Raposo, D., Barrett, D. G. T., Malinowski, M., Pascanu, R., Battaglia, P., & Lillicrap, T. (2017) · arXiv · doi:10.48550/arxiv.1706.01427 · Cited by 1,281 · cited 2×
“[53] inferred relations across all pairs of objects to solve the visual question answering task.”
BackgroundParmar, N., Vaswani, A., Uszkoreit, J., Kaiser, Ł., Shazeer, N., Ku, A., & Tran, D. (2018) · arXiv · doi:10.48550/arxiv.1802.05751 · Cited by 1,085 · cited 1×
“Recent studies show the superiority of the Transformer [74] architecture in learning visual relations and using it to solve different computer vision tasks [51, 57, 71, 38, 13, 7, 10], especially for pose estimation [84, 44, 70, 30, 40, 21].”
BackgroundLearning extraction patterns for subjective expressions
Riloff, E., & Wiebe, J. (2003) · Proceedings of the 2003 conference on Empirical methods in natural language processing - · doi:10.3115/1119355.1119369 · Cited by 1,059
Romero (2017) · doi:10.1145/3130800.3130883 · Cited by 1,056
SSD-6D: Making RGB-Based 3D Detection and 6D Pose Estimation Great Again
Kehl, W., Manhardt, F., Tombari, F., Ilic, S., & Navab, N. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.169 · Cited by 1,047 · cited 1×
“There are also two main paradigms to perform object 6-Dof pose estimation, with one directly regressing the pose as network outputs [28, 67] and another regressing the projected 3D object control points location in the image and recovering the pose with 2D-to-3D correspondence [45, 60, 43, 24].”
MethodInteraction Networks for Learning about Objects, Relations and Physics
Battaglia, P. W., Pascanu, R., Lai, M., Rezende, D., & Kavukcuoglu, K. (2016) · arXiv · doi:10.48550/arxiv.1612.00222 · Cited by 969
Semi-Supervised Self-Training of Object Detection Models
Rosenberg, C., Hebert, M., & Schneiderman, H. (2005) · 2005 Seventh IEEE Workshops on Applications of Computer Vision (WACV/MOTION'05) - Volume 1 · doi:10.1109/acvmot.2005.107 · Cited by 796
End-to-End Human Pose and Mesh Reconstruction with Transformers
Lin, K., Wang, L., & Liu, Z. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00199 · Cited by 740 · cited 1×
“Recent studies show the superiority of the Transformer [74] architecture in learning visual relations and using it to solve different computer vision tasks [51, 57, 71, 38, 13, 7, 10], especially for pose estimation [84, 44, 70, 30, 40, 21].”
BackgroundSet Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks
Lee, J., Lee, Y., Kim, J., Kosiorek, A. R., Choi, S., & Teh, Y. W. (2018) · arXiv · doi:10.48550/arxiv.1810.00825 · Cited by 691
Label Propagation for Deep Semi-Supervised Learning
Iscen, A., Tolias, G., Avrithis, Y., & Chum, O. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00521 · Cited by 686
He, K., Gkioxari, G., Dollár, P., & Girshick, R. (2017) · arXiv · doi:10.48550/arxiv.1703.06870 · Cited by 406
Unifying distillation and privileged information
Lopez-Paz, D., Bottou, L., Schölkopf, B., & Vapnik, V. (2015) · arXiv · doi:10.48550/arxiv.1511.03643 · Cited by 270 · cited 1×
“Semi-supervised learning plays a key role in improving model performance when the labeled data is limited [46, 35, 68, 55, 71, 48, 51, 6].”
BackgroundCategory-Level Articulated Object Pose Estimation
Li, X., Wang, H., Yi, L., Guibas, L. J., Abbott, A. L., & Song, S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00376 · Cited by 196
Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning
Arazo, E., Ortego, D., Albert, P., O'Connor, N. E., & McGuinness, K. (2020) · 2020 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9207304 · Cited by 77
Cited by
AnyTeleop: A General Vision-Based Dexterous Robot Arm-Hand Teleoperation System
Qin, Y., Yang, W., Huang, B., Wyk, K., Su, H., Wang, X., Chao, Y.-W., & Fox, D. (2023) · Robotics: Science and Systems XIX · doi:10.15607/rss.2023.xix.015 · Cited by 109
Self-citation
Metadata
- Authors
- Liu, S., Jiang, H., Xu, J., Liu, S., & Wang, X.
- Venue
- 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2021-06
- Pages
- 14682-14692
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3170924787
- Cited by
- 171
- References
- 25
- FWCI
- 11.18
- 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
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.