Learning Models for Actions and Person-Object Interactions with Transfer to Question Answering
Open accessThe DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.
Abstract
This paper proposes deep convolutional network models that utilize local and global context to make human activity label predictions in still images, achieving state-of-the-art performance on two recent datasets with hundreds of labels each. We use multiple instance learning to handle the lack of supervision on the level of individual person instances, and weighted loss to handle unbalanced training data. Further, we show how specialized features trained on these datasets can be used to improve accuracy on the Visual Question Answering (VQA) task, in the form of multiple choice fill-in-the-blank questions (Visual Madlibs). Specifically, we tackle two types of questions on person activity and person-object relationship and show improvements over generic features trained on the ImageNet classification task
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 classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2389824 · Cited by 11,971
VQA: Visual Question Answering
Antol, S., Agrawal, A., Lu, J., Mitchell, M., Batra, D., Zitnick, C. L., & Parikh, D. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.279 · Cited by 4,487
Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding
Fukui, A., Park, D. H., Yang, D., Rohrbach, A., Darrell, T., & Rohrbach, M. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1044 · Cited by 1,582
The Role of Context for Object Detection and Semantic Segmentation in the Wild
Mottaghi, R., Chen, X., Liu, X., Cho, N.-G., Lee, S.-W., Fidler, S., Urtasun, R., & Yuille, A. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.119 · Cited by 1,438 · cited 1×
“Contextual information outside the tight box around an object has shown to be useful in tasks such as object detection & classification [25,26,27] and segmentation [28].”
MethodVQA: Visual Question Answering: www.visualqa.org
Agrawal, A., Lu, J., Antol, S., Mitchell, M., Zitnick, C. L., Parikh, D., & Batra, D. (2017) · International Journal of Computer Vision · doi:10.1007/s11263-016-0966-6 · Cited by 570 · cited 9×
“Motivated by the recent availability of large activity recognition and VQA datasets centered around humans, in this paper, we show that transferring expert knowledge from a network trained on human activity prediction to the task of answering questions of the Madlibs dataset can not only improve performance, but also…”
BackgroundInfluentialAnalyzing the Performance of Multilayer Neural Networks for Object Recognition
Agrawal, P., Girshick, R., & Malik, J. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10584-0_22 · Cited by 427 · cited 1×
“In order to achieve good performance on smaller datasets, previous work [34,35,30] has emphasized the importance of re-using weights from the network trained on the large-scale ImageNet classification task [9].”
MethodEmotion Recognition in the Wild via Convolutional Neural Networks and Mapped Binary Patterns
Levi, G., & Hassner, T. (2015) · Proceedings of the 2015 ACM on International Conference on Multimodal Interaction · doi:10.1145/2818346.2830587 · Cited by 336 · cited 1×
“Over the last few years, a number of valuable datasets and models targeting specific tasks such as scene recognition [10], age, gender, and emotion classifi-cation [11,12], human action recognition [13,14,15], etc. have been released.”
Background
Cited by
Detecting and Recognizing Human-Object Interactions
Gkioxari, G., Girshick, R., Dollar, P., & He, K. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00872 · Cited by 602
Visual Translation Embedding Network for Visual Relation Detection
Zhang, H., Kyaw, Z., Chang, S.-F., & Chua, T.-S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.331 · Cited by 586
Learning Human-Object Interactions by Graph Parsing Neural Networks
Qi, S., Wang, W., Jia, B., Shen, J., & Zhu, S.-C. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01240-3_25 · Cited by 572
Learning to Detect Human-Object Interactions
Chao, Y.-W., Liu, Y., Liu, X., Zeng, H., & Deng, J. (2018) · 2018 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv.2018.00048 · Cited by 520
A Comprehensive Survey of Vision-Based Human Action Recognition Methods
Zhang, H.-B., Zhang, Y.-X., Zhong, B., Lei, Q., Yang, L., Du, J.-X., & Chen, D.-S. (2019) · Sensors · doi:10.3390/s19051005 · Cited by 503
“[120] calculated human and object features from pretrained CNNs, and merged them with pretrained human and object relationship models learned from the HIOC dataset to detect interactions.”
Method
Metadata
- Authors
- Mallya, A., & Lazebnik, S.
- Venue
- Lecture Notes in Computer Science
- Publisher
- Springer International Publishing
- Published
- 2016
- Pages
- 414-428
- ISSN
- 0302-9743 (ISSN-L)
- 1611-3349
- OpenAlex
- W2339712187
- Cited by
- 109
- References
- 8
- FWCI
- 6.11
- 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: Learning Models for Actions and Person-Object Interactions with Transfer to Question Answering. https://app.cochat.ai/papers/10.1007/978-3-319-46448-0_25
- The paper
- Mallya, A., & Lazebnik, S. (2016). Learning Models for Actions and Person-Object Interactions with Transfer to Question Answering. Lecture Notes in Computer Science. https://doi.org/10.1007/978-3-319-46448-0_25
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.