Shortened version of the final exam for the Deep Learning course of the University of Trento in 2023.
-
Updated
Jul 31, 2023 - Jupyter Notebook
Shortened version of the final exam for the Deep Learning course of the University of Trento in 2023.
HAIS_2GNN: 3D Visual Grounding with Graph and Attention
Dissertation for "Weakly Supervised Visual-Textual Grounding based on Concept Similarity" (MS thesis at University of Padua, Italy) - PyTorch implementation: https://github.com/lparolari/weakvtg
A collection of resources (work logs, state-of-the-art scores, experiment trace, scripts and proof-of-concepts) for my MS thesis "Weakly Supervised Visual-Textual Grounding based on Concept Similarity" - https://github.com/lparolari/weakvtg
PyTorch implementation of the model described my MS thesis: "Weakly Supervised Visual-Textual Grounding based on Concept Similarity" (https://github.com/lparolari/master-thesis)
A quasi-final short and summary report on my thesis "Weakly Supervised Visual-Textual Grounding based on Concept Similarity". (MS thesis at University of Padua, Italy). - https://github.com/lparolari/weakvtg
This is a deep learning project focused on the visual grounding task
TransformerVG - 3D Visual Grounding with Transformers
Implementation of Master Thesis on "Belief State for Visually Grounded, Task-Oriented Neural Dialogue Model"
[EMNLP 22] Extending Phrase Grounding with Pronouns in Visual Dialogues.
Helper tools for extracting and projecting ENet features to ScanNet pointclouds.
Explore new research topics, visual grounding
Utilizing a transformer-based object detector for the task of 3D visual grounding.
Under review. [IROS 2024] PGA: Personalizing Grasping Agents with Single Human-Robot Interaction
Code used to train probing classifiers in the attribute prediction task
[ICRA 2023] Differentiable parsing and visual grounding of natural language instructions for object placement
Codebase for "Learning to ground medical text in a 3D human atlas (CoNLL 2020)".
A list of research papers on knowledge-enhanced multimodal learning
Toward Explainable and Fine-Grained 3D Grounding through Referring Textual Phrases
[CVPR 2024] Code for "Improved Visual Grounding through Self-Consistent Explanations".
Add a description, image, and links to the visual-grounding topic page so that developers can more easily learn about it.
To associate your repository with the visual-grounding topic, visit your repo's landing page and select "manage topics."