Interaction part mining: A mid-level approach for fine-grained action recognition
The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
Modeling human-object interactions and manipulating motions lies in the heart of fine-grained action recognition. Previous methods heavily rely on explicit detection of the object being interacted, which requires intensive human labour on object annotation. To bypass this constraint and achieve better classification performance, in this work, we propose a novel fine-grained action recognition pipeline by interaction part proposal and discriminative mid-level part mining. Firstly, we generate a large number of candidate object regions using off-the-shelf object proposal tool, e.g., BING. Secondly, these object regions are matched and tracked across frames to form a large spatio-temporal graph based on the appearance matching and the dense motion trajectories through them. We then propose an efficient approximate graph segmentation algorithm to partition and filter the graph into consistent local dense sub-graphs. These sub-graphs, which are spatio-temporal sub-volumes, represent our candidate interaction parts. Finally, we mine discriminative mid-level part detectors from the features computed over the candidate interaction parts. Bag-of-detection scores based on a novel Max-N pooling scheme are computed as the action representation for a video sample. We conduct extensive experiments on human-object interaction datasets including MPII Cooking and MSR Daily Activity 3D. The experimental results demonstrate that the proposed framework achieves consistent improvements over the state-of-the-art action recognition accuracies on the benchmarks, without using any object annotation.
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
Improving the Fisher Kernel for Large-Scale Image Classification
Perronnin, F., Sánchez, J., & Mensink, T. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15561-1_11 · Cited by 2,588 · cited 1×
“Following [23], we also apply square-rooting and normalization for the computed Fisher vectors.”
MethodDense Trajectories and Motion Boundary Descriptors for Action Recognition
Wang, H., Kläser, A., Schmid, C., & Liu, C.-L. (2013) · International Journal of Computer Vision · doi:10.1007/s11263-012-0594-8 · Cited by 1,669 · cited 5×
“, to form mid-level feature descriptor), we adopt the method of Fisher vector coding of dense trajectories [29].”
BackgroundMethodInfluentialEnsemble of exemplar-SVMs for object detection and beyond
Malisiewicz, T., Gupta, A., & Efros, A. A. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126229 · Cited by 865 · cited 1×
“Secondly, recent image mid-level patch mining approaches [9, 28, 3, 15] show success in image recognition tasks.”
BackgroundA database for fine grained activity detection of cooking activities
Rohrbach, M., Amin, S., Andriluka, M., & Schiele, B. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6247801 · Cited by 521
Fine-Grained Activity Recognition by Aggregating Abstract Object Usage
Patterson, D. J., Fox, D., Kautz, H., & Philipose, M. (2005) · Ninth IEEE International Symposium on Wearable Computers (ISWC'05) · doi:10.1109/iswc.2005.22 · Cited by 452
Research works printed but not linked: 34
- 10.1109/ICPR.2004.1333992 · DOI · Paper page
- zhou, 2014, Pipelining localized semantic features for fine-grained action recognition, ECCV
- 10.1109/ICCV.2007.4408865 · DOI · Paper page
- 10.1109/TPAMI.2010.214 · DOI · Paper page
- 10.1109/ICCV.2013.333 · DOI
- 10.1109/CVPR.2012.6247813 · DOI · Paper page
- 10.1109/ICCV.2013.342 · DOI · Paper page
- yao, 2011, Classifying actions and measuring action similarity by modeling the mutual context of objects and human poses, ICML
- 10.1109/ICCV.2011.6126386 · DOI · Paper page
- 10.1109/CVPR.2013.331 · DOI
- kjellström, 2008, Simultaneous visual recognition of manipulation actions and manipulated objects, ECCV
- koppula, 2012, Learning human activities and object affordances from rgb-d videos, CoRR
- 10.1109/CVPR.2008.4587756 · DOI · Paper page
- 10.1145/2370216.2370248 · DOI · Paper page
- 10.1109/CVPR.2014.104 · DOI
- 10.1109/CVPR.2009.5206557 · DOI · Paper page
- 10.1109/ICCV.1999.791201 · DOI · Paper page
- müller, 2006, Motion templates for automatic classification and retrieval of motion capture data, SCA
- 10.1109/ICCV.2013.228 · DOI · Paper page
- singh, 2012, Unsupervised discovery of mid-level discriminative patches, ECCV
- 10.1109/ICCVW.2013.72 · DOI
- 10.1109/CVPR.2012.6247806 · DOI · Paper page
- doersch, 2013, Mid-level visual element discovery as discriminative mode seeking, NIPS
- 10.1109/CVPR.2005.16 · DOI · Paper page
- fan, 2008, Liblinear: A library for large linear classification, IMLR, 9, 1871
- 10.1109/CVPR.2013.332 · DOI
- 10.1109/CVPR.2007.383331 · DOI · Paper page
- 10.1109/CVPR.2014.414 · DOI · Paper page
- 10.1109/CVPR.2013.124 · DOI · Paper page
- 10.1007/s00224-006-1350-7 · doi:10.1007/s00224-006-1350-7
- 10.1109/CVPR.2012.6247824 · DOI · Paper page
- peng, 2014, Action recognition with stacked fisher vectors, ECCV
- 10.1109/TPAMI.2012.175 · DOI
- 10.1109/CVPR.2012.6247807 · DOI · Paper page
Cited by
Temporal Convolutional Networks for Action Segmentation and Detection
Lea, C., Flynn, M. D., Vidal, R., Reiter, A., & Hager, G. D. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.113 · Cited by 2,238
“, [3, 39]), however, this task assumes the boundaries of each segment are known.”
BackgroundP-CNN: Pose-Based CNN Features for Action Recognition
Cheron, G., Laptev, I., & Schmid, C. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.368 · Cited by 633
“this dataset and is on par with the recently published work of [44].”
ResultDeep Sequential Context Networks for Action Prediction
Kong, Y., Tao, Z., & Fu, Y. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.390 · Cited by 169
“Existing approaches can be roughly categorized into low-level feature-based approaches [15, 33, 30, 22, 31, 20] and midlevel feature-based approaches [12, 26, 34, 36, 18].”
BackgroundProgressively Parsing Interactional Objects for Fine Grained Action Detection
Ni, B., Yang, X., & Gao, S. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.116 · Cited by 69
Self-citationDTR-HAR: deep temporal residual representation for human activity recognition
Basly, H., Ouarda, W., Sayadi, F. E., Ouni, B., & Alimi, A. M. (2022) · The Visual Computer · doi:10.1007/s00371-021-02064-y · Cited by 36
Metadata
- Authors
- Zhou, Y., Ni, B., Hong, R., Wang, M., & Tian, Q.
- Venue
- 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2015-06
- Pages
- 3323-3331
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W1923026787
- Cited by
- 77
- References
- 5
- FWCI
- 6.65
- Type
- conference paper
- Language
- en
- Open access
- closed
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: Interaction part mining: A mid-level approach for fine-grained action recognition. https://app.cochat.ai/papers/10.1109/cvpr.2015.7298953
- The paper
- Zhou, Y., Ni, B., Hong, R., Wang, M., & Tian, Q. (2015). Interaction part mining: A mid-level approach for fine-grained action recognition. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/cvpr.2015.7298953
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.