Doubling down: sparse grounding with an additional, almost-matching caption for detection-oriented multimodal pretraining

التفاصيل البيبلوغرافية
العنوان: Doubling down: sparse grounding with an additional, almost-matching caption for detection-oriented multimodal pretraining
المؤلفون: Nebbia, Giacomo, Kovashka, Adriana
المصدر: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) CVPRW Computer Vision and Pattern Recognition Workshops (CVPRW), 2022 IEEE/CVF Conference on. :4641-4650 Jun, 2022
Relation: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
قاعدة البيانات: IEEE Xplore Digital Library