Skip to Content

Switch language English
- Switch language
- Deutsch
- English
- Español
- Français
- Italiano
- Português do Brasil
- 中文
Login

ScholarsArchive@OSU

Home
About
Help
Contact

Search ScholarsArchive@OSU

Advanced Search

Search Constraints

Start Over

Filtering by: Creator Fino, Antonio Carlos Remove constraint Creator: Fino, Antonio Carlos Advisor Li, Fuxin Remove constraint Advisor: Li, Fuxin

1 - 4 of 4

Relevance
Title [A-Z]
Title [Z-A]
Date Created ▼
Date Created ▲
Date Uploaded ▼
Date Uploaded ▲

Number of results to display per page

10 per page
20 per page
50 per page
100 per page

View results as:

List Gallery Masonry

Search Results

Toward Disentangling the Activations of the Deep Networks via Low-dimensional Embedding and Non-negative Factorization

Creator:

Khorram, Saeed

Abstract:

In this thesis, we introduce a novel Explanation Neural Network (XNN) to explain the predictions made by a deep network. The XNN works by embedding a high-dimensional activation vector of a deep network layer non-linearly into a low-dimensional explanation space while retaining faithfulness i.e., the original deep learning predictions can...

Resource Type:

Masters Thesis
Towards Annotation-Efficient Video Representation Learning

Creator:

Patravali, Jay Sanjay

Abstract:

Labeling videos is costly, time-consuming and tedious. These costs can escalate in applications such as medical diagnosis or autonomous driving where we need domain expertise for annotation. Few-shot action recognition aims to solve this problem by annotation-efficient learning mechanisms. This thesis presents MetaUVFS as the first Unsupervised Meta-learning algorithm for...

Resource Type:

Masters Thesis
Generative Models Meet Explainable AI and Long-Tail Learning: from Attribution Maps to Image Synthesis

Creator:

Khorram, Saeed

Abstract:

The advancement of artificial intelligence (AI) has led to transformative developments across multiple sectors, fostering innovation and redefining our interactions with technology. As AI matures and becomes integrated into society, it offers numerous opportunities to address global challenges and revolutionize a wide array of human endeavors. These advances are driven...

Resource Type:

Dissertation
Deep Convolutional Network on Point Clouds for 3D Scene Understanding

Creator:

Wu, Wenxuan

Abstract:

As one of the most popular data types, the point cloud is widely used in various appli- cations, including computer vision, computer graphics and robotics. The capability to directly measure 3D point clouds is invaluable in those applications as depth information could remove a lot of the segmentation ambiguities in...

Resource Type:

Dissertation

Full Text:

of this work is PointConv, which is a Monte Carlo approximation of the continuous convolution on 3D

Limit your search

Academic Affiliation

Electrical Engineering and Computer Science3

Advisor

Li, Fuxin[remove]4

Commencement Year

Commencement Year range begin – Commencement Year range end

Current results range from 2020 to 2023

View distribution

Committee Member

Fern, Alan3
Todorovic, Sinisa3
Turkan, Yelda2
Wong, Weng-Keen2
Chen, Lizhong1
more Committee Members »

Creator

Khorram, Saeed2
Patravali, Jay Sanjay1
Wu, Wenxuan1

Contributor

Fu, Xiao1
Li, Fuxin1
Qi, Zhongang1

Date

Date range begin – Date range end

Current results range from 2020 to 2023

View distribution

Decade

2020-20294

Degree Field

Computer Science3
Robotics1

Degree Level

Doctoral2
Master's2

Degree Name

Doctor of Philosophy (Ph.D.)2
Master of Science (M.S.)2

Language

English [eng]4

License

All rights reserved4

Non-Academic Affiliation

Oregon State University. Collaborative Robotics and Intelligent Systems (CoRIS) Institute1

Peer Reviewed

No4

Resource Type

Dissertation2
Masters Thesis2

Rights Statement

In Copyright4

Scholars Archive is a service of Oregon State University Libraries & Press

121 The Valley Library
Corvallis, OR 97331-4501

Contact Us
Services for Persons with Disabilities

Powered by Hyrax 3.6.0

Copyright © 2018 Oregon State University
Licensed under the Apache License, Version 2.0

Core Trust application (pdf)