Skip to content

Presentation for "Weakly Supervised Visual-Textual Grounding based on Concept Similarity" (MS thesis at University of Padua, Italy) - PyTorch implementation: https://github.com/lparolari/weakvtg

Notifications You must be signed in to change notification settings

lparolari/master-thesis-presentation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

37 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Weakly Supervised Visual-Textual Grounding based on Concept Similarity

You may want to browse the code for my thesis model implementation.

Abastract

We address the problem of phrase grounding, i.e. the task of locating the content of the image referenced by the sentence, by using weak supervision. Phrase grounding is a challenging problem that requires joint understanding of both visual and textual modalities, while being an important application in many field of study such as visual question answering, image retrieval and robotic navigation. We propose a simple model that leverages on concept similarity, i.e. the similarity between a concept in phrases and the proposal bounding boxes label. We apply such measure as a prior on our model prediction. Then the model is trained to maximize multimodal similarity between an image and a sentence describing that image, while minimizing instead the multimodal similarity between the image and a sentence not describing the image. Our experiments shows comparable performance with respect to State-of-the-Art works.

Example

presentation-1 presentation-2 presentation-3

Usage

pdflatex presentation.tex

Related Works

Acknowledgements

Author

Luca Parolari

License

MIT

About

Presentation for "Weakly Supervised Visual-Textual Grounding based on Concept Similarity" (MS thesis at University of Padua, Italy) - PyTorch implementation: https://github.com/lparolari/weakvtg

Topics

Resources

Stars

Watchers

Forks

Packages

No packages published

Languages