Picture for Andrea Burns

Andrea Burns

Tell Me What's Next: Textual Foresight for Generic UI Representations

Add code
Jun 12, 2024
Viaarxiv icon

ImageInWords: Unlocking Hyper-Detailed Image Descriptions

Add code
May 05, 2024
Viaarxiv icon

WikiWeb2M: A Page-Level Multimodal Wikipedia Dataset

Add code
May 09, 2023
Viaarxiv icon

A Suite of Generative Tasks for Multi-Level Multimodal Webpage Understanding

Add code
May 05, 2023
Viaarxiv icon

Language-Guided Audio-Visual Source Separation via Trimodal Consistency

Add code
Mar 28, 2023
Viaarxiv icon

Interactive Mobile App Navigation with Uncertain or Under-specified Natural Language Commands

Add code
Feb 04, 2022
Figure 1 for Interactive Mobile App Navigation with Uncertain or Under-specified Natural Language Commands
Figure 2 for Interactive Mobile App Navigation with Uncertain or Under-specified Natural Language Commands
Figure 3 for Interactive Mobile App Navigation with Uncertain or Under-specified Natural Language Commands
Figure 4 for Interactive Mobile App Navigation with Uncertain or Under-specified Natural Language Commands
Viaarxiv icon

Unsupervised Disentanglement without Autoencoding: Pitfalls and Future Directions

Add code
Aug 14, 2021
Figure 1 for Unsupervised Disentanglement without Autoencoding: Pitfalls and Future Directions
Figure 2 for Unsupervised Disentanglement without Autoencoding: Pitfalls and Future Directions
Figure 3 for Unsupervised Disentanglement without Autoencoding: Pitfalls and Future Directions
Figure 4 for Unsupervised Disentanglement without Autoencoding: Pitfalls and Future Directions
Viaarxiv icon

Mobile App Tasks with Iterative Feedback (MoTIF): Addressing Task Feasibility in Interactive Visual Environments

Add code
Apr 17, 2021
Figure 1 for Mobile App Tasks with Iterative Feedback (MoTIF): Addressing Task Feasibility in Interactive Visual Environments
Figure 2 for Mobile App Tasks with Iterative Feedback (MoTIF): Addressing Task Feasibility in Interactive Visual Environments
Figure 3 for Mobile App Tasks with Iterative Feedback (MoTIF): Addressing Task Feasibility in Interactive Visual Environments
Figure 4 for Mobile App Tasks with Iterative Feedback (MoTIF): Addressing Task Feasibility in Interactive Visual Environments
Viaarxiv icon

Learning to Scale Multilingual Representations for Vision-Language Tasks

Add code
Apr 09, 2020
Figure 1 for Learning to Scale Multilingual Representations for Vision-Language Tasks
Figure 2 for Learning to Scale Multilingual Representations for Vision-Language Tasks
Figure 3 for Learning to Scale Multilingual Representations for Vision-Language Tasks
Figure 4 for Learning to Scale Multilingual Representations for Vision-Language Tasks
Viaarxiv icon

Language Features Matter: Effective Language Representations for Vision-Language Tasks

Add code
Aug 17, 2019
Figure 1 for Language Features Matter: Effective Language Representations for Vision-Language Tasks
Figure 2 for Language Features Matter: Effective Language Representations for Vision-Language Tasks
Figure 3 for Language Features Matter: Effective Language Representations for Vision-Language Tasks
Figure 4 for Language Features Matter: Effective Language Representations for Vision-Language Tasks
Viaarxiv icon