preprint · arXiv (Cornell University) · 2019

Activity Driven Weakly Supervised Object Detection

Zhenheng Yang, Dhruv Mahajan, Deepti Ghadiyaram, Ram Nevatia, Vignesh Ramanathan

Cited by 4Open access

Abstract

Weakly supervised object detection aims at reducing the amount of supervision required to train detection models. Such models are traditionally learned from images/videos labelled only with the object class and not the object bounding box. In our work, we try to leverage not only the object class labels but also the action labels associated with the data. We show that the action depicted in the image/video can provide strong cues about the location of the associated object. We learn a spatial prior for the object dependent on the action (e.g. "ball" is closer to "leg of the person" in "kicking ball"), and incorporate this prior to simultaneously train a joint object detection and action classification model. We conducted experiments on both video datasets and image datasets to evaluate the performance of our weakly supervised object detection model. Our approach outperformed the current state-of-the-art (SOTA) method by more than 6% in mAP on the Charades video dataset.

Cite this paper

APA 7

Yang, Z., Mahajan, D., Ghadiyaram, D., Nevatia, R., & Ramanathan, V. (2019). Activity Driven Weakly Supervised Object Detection. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1904.01665

MLA 9

Yang, Zhenheng, et al. “Activity Driven Weakly Supervised Object Detection.” arXiv (Cornell University), 2019, https://doi.org/10.48550/arxiv.1904.01665.

Chicago

Yang, Zhenheng, Dhruv Mahajan, Deepti Ghadiyaram, Ram Nevatia, and Vignesh Ramanathan. 2019. “Activity Driven Weakly Supervised Object Detection.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.1904.01665.

Harvard

Yang, Z. et al. (2019) ‘Activity Driven Weakly Supervised Object Detection’, arXiv (Cornell University). Available at: https://doi.org/10.48550/arxiv.1904.01665.

BibTeX

@misc{yang2019activity,
  title = {{Activity Driven Weakly Supervised Object Detection}},
  author = {Yang, Zhenheng and Mahajan, Dhruv and Ghadiyaram, Deepti and Nevatia, Ram and Ramanathan, Vignesh},
  journal = {arXiv (Cornell University)},
  year = {2019},
  doi = {10.48550/arxiv.1904.01665}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.