Video Object Grounding Using Semantic Roles in Language Description

@article{Sadhu2020VideoOG,
  title={Video Object Grounding Using Semantic Roles in Language Description},
  author={Arka Sadhu and K. Chen and R. Nevatia},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2020},
  pages={10414-10424}
}
  • Arka Sadhu, K. Chen, R. Nevatia
  • Published 2020
  • Computer Science
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
We explore the task of Video Object Grounding (VOG), which grounds objects in videos referred to in natural language descriptions. Previous methods apply image grounding based algorithms to address VOG, fail to explore the object relation information and suffer from limited generalization. Here, we investigate the role of object relations in VOG and propose a novel framework VOGNet to encode multi-modal object relations via self-attention with relative position encoding. To evaluate VOGNet, we… Expand
5 Citations
ClawCraneNet: Leveraging Object-level Relation for Text-based Video Segmentation
  • Chen Liang, Yu Wu, Yawei Luo, Yi Yang
  • Computer Science
  • ArXiv
  • 2021
  • PDF
Video Question Answering with Phrases via Semantic Roles
  • PDF
Refer-it-in-RGBD: A Bottom-up Approach for 3D Visual Grounding in RGBD Images
  • PDF
Grounding-Tracking-Integration
  • 3
  • PDF

References

SHOWING 1-10 OF 89 REFERENCES
Zero-Shot Grounding of Objects From Natural Language Queries
  • 32
  • PDF
Grounding of Textual Phrases in Images by Reconstruction
  • 314
  • PDF
Weakly-Supervised Spatio-Temporally Grounding Natural Sentence in Video
  • 22
  • Highly Influential
  • PDF
Visual7W: Grounded Question Answering in Images
  • 477
  • PDF
Generation and Comprehension of Unambiguous Object Descriptions
  • 421
  • PDF
Grounding Semantic Roles in Images
  • 8
  • PDF
Video Action Transformer Network
  • 189
  • Highly Influential
  • PDF
Video Object Segmentation with Language Referring Expressions
  • 30
  • PDF
...
1
2
3
4
5
...