Activity Driven Weakly Supervised Object Detection
This work addresses the problem of reducing annotation costs for object detection in videos and images, offering a domain-specific improvement for computer vision applications.
The paper tackles weakly supervised object detection by leveraging action labels to provide spatial cues for object locations, such as a ball being near a leg in kicking actions, and trains a joint model for detection and action classification. It outperforms the state-of-the-art by over 6% in mAP on the Charades video dataset.
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.