Picture for Matthew Gwilliam

Matthew Gwilliam

Latent-INR: A Flexible Framework for Implicit Representations of Videos with Discriminative Semantics

Add code
Aug 05, 2024
Figure 1 for Latent-INR: A Flexible Framework for Implicit Representations of Videos with Discriminative Semantics
Figure 2 for Latent-INR: A Flexible Framework for Implicit Representations of Videos with Discriminative Semantics
Figure 3 for Latent-INR: A Flexible Framework for Implicit Representations of Videos with Discriminative Semantics
Figure 4 for Latent-INR: A Flexible Framework for Implicit Representations of Videos with Discriminative Semantics
Viaarxiv icon

Explaining the Implicit Neural Canvas: Connecting Pixels to Neurons by Tracing their Contributions

Add code
Jan 18, 2024
Viaarxiv icon

A Video is Worth 10,000 Words: Training and Benchmarking with Diverse Captions for Better Long Video Retrieval

Add code
Nov 30, 2023
Figure 1 for A Video is Worth 10,000 Words: Training and Benchmarking with Diverse Captions for Better Long Video Retrieval
Figure 2 for A Video is Worth 10,000 Words: Training and Benchmarking with Diverse Captions for Better Long Video Retrieval
Figure 3 for A Video is Worth 10,000 Words: Training and Benchmarking with Diverse Captions for Better Long Video Retrieval
Figure 4 for A Video is Worth 10,000 Words: Training and Benchmarking with Diverse Captions for Better Long Video Retrieval
Viaarxiv icon

Do text-free diffusion models learn discriminative visual representations?

Add code
Nov 30, 2023
Viaarxiv icon

Diffusion Models Beat GANs on Image Classification

Add code
Jul 17, 2023
Viaarxiv icon

Beyond Supervised vs. Unsupervised: Representative Benchmarking and Analysis of Image Representation Learning

Add code
Jun 16, 2022
Figure 1 for Beyond Supervised vs. Unsupervised: Representative Benchmarking and Analysis of Image Representation Learning
Figure 2 for Beyond Supervised vs. Unsupervised: Representative Benchmarking and Analysis of Image Representation Learning
Figure 3 for Beyond Supervised vs. Unsupervised: Representative Benchmarking and Analysis of Image Representation Learning
Figure 4 for Beyond Supervised vs. Unsupervised: Representative Benchmarking and Analysis of Image Representation Learning
Viaarxiv icon

Rethinking Common Assumptions to Mitigate Racial Bias in Face Recognition Datasets

Add code
Sep 08, 2021
Figure 1 for Rethinking Common Assumptions to Mitigate Racial Bias in Face Recognition Datasets
Figure 2 for Rethinking Common Assumptions to Mitigate Racial Bias in Face Recognition Datasets
Figure 3 for Rethinking Common Assumptions to Mitigate Racial Bias in Face Recognition Datasets
Figure 4 for Rethinking Common Assumptions to Mitigate Racial Bias in Face Recognition Datasets
Viaarxiv icon

Fair Comparison: Quantifying Variance in Resultsfor Fine-grained Visual Categorization

Add code
Sep 08, 2021
Figure 1 for Fair Comparison: Quantifying Variance in Resultsfor Fine-grained Visual Categorization
Figure 2 for Fair Comparison: Quantifying Variance in Resultsfor Fine-grained Visual Categorization
Figure 3 for Fair Comparison: Quantifying Variance in Resultsfor Fine-grained Visual Categorization
Figure 4 for Fair Comparison: Quantifying Variance in Resultsfor Fine-grained Visual Categorization
Viaarxiv icon

Machine Translationese: Effects of Algorithmic Bias on Linguistic Complexity in Machine Translation

Add code
Jan 30, 2021
Figure 1 for Machine Translationese: Effects of Algorithmic Bias on Linguistic Complexity in Machine Translation
Figure 2 for Machine Translationese: Effects of Algorithmic Bias on Linguistic Complexity in Machine Translation
Figure 3 for Machine Translationese: Effects of Algorithmic Bias on Linguistic Complexity in Machine Translation
Figure 4 for Machine Translationese: Effects of Algorithmic Bias on Linguistic Complexity in Machine Translation
Viaarxiv icon