Corpus ID: 222066863

Learning Object Detection from Captions via Textual Scene Attributes

@article{Jerbi2020LearningOD,
  title={Learning Object Detection from Captions via Textual Scene Attributes},
  author={Achiya Jerbi and Roei Herzig and Jonathan Berant and Gal Chechik and A. Globerson},
  journal={ArXiv},
  year={2020},
  volume={abs/2009.14558}
}
  • Achiya Jerbi, Roei Herzig, +2 authors A. Globerson
  • Published 2020
  • Computer Science
  • ArXiv
  • Object detection is a fundamental task in computer vision, requiring large annotated datasets that are difficult to collect, as annotators need to label objects and their bounding boxes. Thus, it is a significant challenge to use cheaper forms of supervision effectively. Recent work has begun to explore image captions as a source for weak supervision, but to date, in the context of object detection, captions have only been used to infer the categories of the objects in the image. In this work… CONTINUE READING

    Figures and Tables from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 51 REFERENCES
    Cap2Det: Learning to Amplify Weak Caption Supervision for Object Detection
    • 3
    • Highly Influential
    • Open Access
    Is object localization for free? - Weakly-supervised learning with convolutional neural networks
    • 609
    • Open Access
    On Support Relations and Semantic Scene Graphs
    • 30
    • Open Access
    Instance-Aware, Context-Focused, and Memory-Efficient Weakly Supervised Object Detection
    • 3
    • Open Access
    The Pascal Visual Object Classes (VOC) Challenge
    • 8,141
    • Open Access
    Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations
    • 1,435
    • Open Access
    Scene graph captioner: Image captioning based on structural visual representation
    • 17
    • Open Access
    Segmentation as selective search for object recognition
    • 615
    • Open Access
    Generating Semantically Precise Scene Graphs from Textual Descriptions for Improved Image Retrieval
    • 133
    • Highly Influential
    • Open Access
    Precise Detection in Densely Packed Scenes
    • 34
    • Open Access