Search Results for author: Garrison W. Cottrell

Found 18 papers, 7 papers with code

FIgLib & SmokeyNet: Dataset and Deep Learning Model for Real-Time Wildland Fire Smoke Detection

no code implementations16 Dec 2021 Anshuman Dewangan, Yash Pande, Hans-Werner Braun, Frank Vernon, Ismael Perez, Ilkay Altintas, Garrison W. Cottrell, Mai H. Nguyen

Early detection of fire ignitions from initial smoke can assist the response to such fires before they become difficult to manage.

Learning Representations for Incomplete Time Series Clustering

1 code implementation AAAI 2021 Qianli Ma, Chuxin Chen, Sen Li, Garrison W. Cottrell

Also, to reduce the error propagation from imputation to clustering, we introduce a discriminator to make the distribution of imputation values close to the true one and train CRLI in an alternating train- ing manner.

Imputation Representation Learning +1

Generating Rationales in Visual Question Answering

no code implementations4 Apr 2020 Hammad A. Ayyubi, Md. Mehrab Tanjim, Julian J. McAuley, Garrison W. Cottrell

Despite recent advances in Visual QuestionAnswering (VQA), it remains a challenge todetermine how much success can be attributedto sound reasoning and comprehension ability. We seek to investigate this question by propos-ing a new task ofrationale generation.

Question Answering Visual Question Answering +1

ReZero is All You Need: Fast Convergence at Large Depth

13 code implementations10 Mar 2020 Thomas Bachlechner, Bodhisattwa Prasad Majumder, Huanru Henry Mao, Garrison W. Cottrell, Julian McAuley

Deep networks often suffer from vanishing or exploding gradients due to inefficient signal propagation, leading to long training times or convergence difficulties.

Language Modelling

Using Deep Siamese Neural Networks to Speed up Natural Products Research

no code implementations27 Sep 2018 Nicholas Roberts, Poornav S. Purushothama, Vishal T. Vasudevan, Siddarth Ravichandran, Chen Zhang, William H. Gerwick, Garrison W. Cottrell

Computing a similarity score between 2D NMR spectra for a novel compound and a compound whose structure is known helps determine the structure of the novel compound.

DeepJ: Style-Specific Music Generation

1 code implementation3 Jan 2018 Huanru Henry Mao, Taylor Shin, Garrison W. Cottrell

Recent advances in deep neural networks have enabled algorithms to compose music that is comparable to music composed by humans.

Sound Audio and Speech Processing

Deep-ESN: A Multiple Projection-encoding Hierarchical Reservoir Computing Framework

no code implementations13 Nov 2017 Qianli Ma, Lifeng Shen, Garrison W. Cottrell

As an efficient recurrent neural network (RNN) model, reservoir computing (RC) models, such as Echo State Networks, have attracted widespread attention in the last decade.

Time Series

Belief Tree Search for Active Object Recognition

no code implementations13 Aug 2017 Mohsen Malmir, Garrison W. Cottrell

We show that by optimizing the observation function and retraining the supervised LSTM network, the AOR performance on the test set improves significantly.

Object Recognition Transfer Learning

Recognizing and Curating Photo Albums via Event-Specific Image Importance

1 code implementation19 Jul 2017 Yufei Wang, Zhe Lin, Xiaohui Shen, Radomir Mech, Gavin Miller, Garrison W. Cottrell

Automatic organization of personal photos is a problem with many real world ap- plications, and can be divided into two main tasks: recognizing the event type of the photo collection, and selecting interesting images from the collection.

Hierarchical Cellular Automata for Visual Saliency

1 code implementation26 May 2017 Yao Qin, Mengyang Feng, Huchuan Lu, Garrison W. Cottrell

The CCA can act as an efficient pixel-wise aggregation algorithm that can integrate state-of-the-art methods, resulting in even better results.

Saliency Detection

Skeleton Key: Image Captioning by Skeleton-Attribute Decomposition

no code implementations CVPR 2017 Yufei Wang, Zhe Lin, Xiaohui Shen, Scott Cohen, Garrison W. Cottrell

Furthermore, our algorithm can generate descriptions with varied length, benefiting from the separate control of the skeleton and attributes.

Image Captioning Language Modelling

Event-Specific Image Importance

no code implementations CVPR 2016 Yufei Wang, Zhe Lin, Xiaohui Shen, Radomir Mech, Gavin Miller, Garrison W. Cottrell

In this paper, we show that the selection of important images is consistent among different viewers, and that this selection process is related to the event type of the album.

A Single Model Explains both Visual and Auditory Precortical Coding

no code implementations26 Feb 2016 Honghao Shan, Matthew H. Tong, Garrison W. Cottrell

Precortical neural systems encode information collected by the senses, but the driving principles of the encoding used have remained a subject of debate.

Deep Active Object Recognition by Joint Label and Action Prediction

no code implementations17 Dec 2015 Mohsen Malmir, Karan Sikka, Deborah Forster, Ian Fasel, Javier R. Movellan, Garrison W. Cottrell

The results of experiments suggest that the proposed model equipped with Dirichlet state encoding is superior in performance, and selects images that lead to better training and higher accuracy of label prediction at test time.

Object Recognition

Basic Level Categorization Facilitates Visual Object Recognition

no code implementations12 Nov 2015 Panqu Wang, Garrison W. Cottrell

We instantiate this idea by training a deep CNN to perform basic level object categorization first, and then train it on subordinate level categorization.

Object Categorization Object Recognition +1

Example Selection For Dictionary Learning

no code implementations18 Dec 2014 Tomoki Tsuchida, Garrison W. Cottrell

In unsupervised learning, an unbiased uniform sampling strategy is typically used, in order that the learned features faithfully encode the statistical structure of the training data.

Dictionary Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.