Picture for Vlad I. Morariu

Vlad I. Morariu

DocSynthv2: A Practical Autoregressive Modeling for Document Generation

Jun 12, 2024
Viaarxiv icon

TutoAI: A Cross-domain Framework for AI-assisted Mixed-media Tutorial Creation on Physical Tasks

Mar 12, 2024
Figure 1 for TutoAI: A Cross-domain Framework for AI-assisted Mixed-media Tutorial Creation on Physical Tasks
Figure 2 for TutoAI: A Cross-domain Framework for AI-assisted Mixed-media Tutorial Creation on Physical Tasks
Figure 3 for TutoAI: A Cross-domain Framework for AI-assisted Mixed-media Tutorial Creation on Physical Tasks
Figure 4 for TutoAI: A Cross-domain Framework for AI-assisted Mixed-media Tutorial Creation on Physical Tasks
Viaarxiv icon

MGDoc: Pre-training with Multi-granular Hierarchy for Document Image Understanding

Add code
Nov 27, 2022
Figure 1 for MGDoc: Pre-training with Multi-granular Hierarchy for Document Image Understanding
Figure 2 for MGDoc: Pre-training with Multi-granular Hierarchy for Document Image Understanding
Figure 3 for MGDoc: Pre-training with Multi-granular Hierarchy for Document Image Understanding
Figure 4 for MGDoc: Pre-training with Multi-granular Hierarchy for Document Image Understanding
Viaarxiv icon

Unified Pretraining Framework for Document Understanding

Apr 28, 2022
Figure 1 for Unified Pretraining Framework for Document Understanding
Figure 2 for Unified Pretraining Framework for Document Understanding
Figure 3 for Unified Pretraining Framework for Document Understanding
Figure 4 for Unified Pretraining Framework for Document Understanding
Viaarxiv icon

SelfDoc: Self-Supervised Document Representation Learning

Add code
Jun 07, 2021
Figure 1 for SelfDoc: Self-Supervised Document Representation Learning
Figure 2 for SelfDoc: Self-Supervised Document Representation Learning
Figure 3 for SelfDoc: Self-Supervised Document Representation Learning
Figure 4 for SelfDoc: Self-Supervised Document Representation Learning
Viaarxiv icon

RPCL: A Framework for Improving Cross-Domain Detection with Auxiliary Tasks

Add code
Apr 18, 2021
Figure 1 for RPCL: A Framework for Improving Cross-Domain Detection with Auxiliary Tasks
Figure 2 for RPCL: A Framework for Improving Cross-Domain Detection with Auxiliary Tasks
Figure 3 for RPCL: A Framework for Improving Cross-Domain Detection with Auxiliary Tasks
Figure 4 for RPCL: A Framework for Improving Cross-Domain Detection with Auxiliary Tasks
Viaarxiv icon

Black-box Explanation of Object Detectors via Saliency Maps

Add code
Jun 05, 2020
Figure 1 for Black-box Explanation of Object Detectors via Saliency Maps
Figure 2 for Black-box Explanation of Object Detectors via Saliency Maps
Figure 3 for Black-box Explanation of Object Detectors via Saliency Maps
Figure 4 for Black-box Explanation of Object Detectors via Saliency Maps
Viaarxiv icon

Cross-Domain Document Object Detection: Benchmark Suite and Method

Add code
Mar 30, 2020
Figure 1 for Cross-Domain Document Object Detection: Benchmark Suite and Method
Figure 2 for Cross-Domain Document Object Detection: Benchmark Suite and Method
Figure 3 for Cross-Domain Document Object Detection: Benchmark Suite and Method
Figure 4 for Cross-Domain Document Object Detection: Benchmark Suite and Method
Viaarxiv icon

Referring to Objects in Videos using Spatio-Temporal Identifying Descriptions

Apr 08, 2019
Figure 1 for Referring to Objects in Videos using Spatio-Temporal Identifying Descriptions
Figure 2 for Referring to Objects in Videos using Spatio-Temporal Identifying Descriptions
Figure 3 for Referring to Objects in Videos using Spatio-Temporal Identifying Descriptions
Figure 4 for Referring to Objects in Videos using Spatio-Temporal Identifying Descriptions
Viaarxiv icon

C-WSL: Count-guided Weakly Supervised Localization

Jul 25, 2018
Figure 1 for C-WSL: Count-guided Weakly Supervised Localization
Figure 2 for C-WSL: Count-guided Weakly Supervised Localization
Figure 3 for C-WSL: Count-guided Weakly Supervised Localization
Figure 4 for C-WSL: Count-guided Weakly Supervised Localization
Viaarxiv icon