Corpus ID: 214743355

Long-tail Visual Relationship Recognition with a Visiolinguistic Hubless Loss

@article{Abdelkarim2020LongtailVR,
  title={Long-tail Visual Relationship Recognition with a Visiolinguistic Hubless Loss},
  author={Sherif Abdelkarim and Panos Achlioptas and Jiaji Huang and Boyang Li and Kenneth Ward Church and Mohamed Elhoseiny},
  journal={ArXiv},
  year={2020},
  volume={abs/2004.00436}
}
Scaling up the vocabulary and complexity of current visual understanding systems is necessary in order to bridge the gap between human and machine visual intelligence. However, a crucial impediment to this end lies in the difficulty of generalizing to data distributions that come from real-world scenarios. Typically such distributions follow Zipf's law which states that only a small portion of the collected object classes will have abundant examples (head); while most classes will contain just… Expand
5 Citations

References

SHOWING 1-10 OF 77 REFERENCES
Large-Scale Visual Relationship Understanding
  • 88
  • PDF
DeViSE: A Deep Visual-Semantic Embedding Model
  • 1,584
  • PDF
Visual Relationship Detection with Internal and External Linguistic Knowledge Distillation
  • 174
  • PDF
Dynamic Few-Shot Visual Learning Without Forgetting
  • 422
  • PDF
Visual Translation Embedding Network for Visual Relation Detection
  • 316
  • PDF
Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations
  • 1,826
  • Highly Influential
  • PDF
Visual Relationship Detection with Language Priors
  • 537
  • PDF
Decoupling Representation and Classifier for Long-Tailed Recognition
  • 93
  • Highly Influential
  • PDF
Factors in Finetuning Deep Model for Object Detection with Long-Tail Distribution
  • 92
  • PDF
Relationship Proposal Networks
  • 60
  • PDF
...
1
2
3
4
5
...