Picture for Takuma Yagi

Takuma Yagi

Learning Object States from Actions via Large Language Models

Add code
May 02, 2024
Viaarxiv icon

FineBio: A Fine-Grained Video Dataset of Biological Experiments with Hierarchical Annotation

Add code
Feb 01, 2024
Viaarxiv icon

Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives

Add code
Nov 30, 2023
Viaarxiv icon

Exo2EgoDVC: Dense Video Captioning of Egocentric Procedural Activities Using Web Instructional Videos

Add code
Nov 29, 2023
Viaarxiv icon

Fine-grained Affordance Annotation for Egocentric Hand-Object Interaction Videos

Add code
Feb 10, 2023
Viaarxiv icon

Precise Affordance Annotation for Egocentric Action Video Datasets

Add code
Jun 11, 2022
Figure 1 for Precise Affordance Annotation for Egocentric Action Video Datasets
Figure 2 for Precise Affordance Annotation for Egocentric Action Video Datasets
Figure 3 for Precise Affordance Annotation for Egocentric Action Video Datasets
Figure 4 for Precise Affordance Annotation for Egocentric Action Video Datasets
Viaarxiv icon

Object Instance Identification in Dynamic Environments

Add code
Jun 10, 2022
Figure 1 for Object Instance Identification in Dynamic Environments
Figure 2 for Object Instance Identification in Dynamic Environments
Figure 3 for Object Instance Identification in Dynamic Environments
Figure 4 for Object Instance Identification in Dynamic Environments
Viaarxiv icon

Hand-Object Contact Prediction via Motion-Based Pseudo-Labeling and Guided Progressive Label Correction

Add code
Oct 19, 2021
Figure 1 for Hand-Object Contact Prediction via Motion-Based Pseudo-Labeling and Guided Progressive Label Correction
Figure 2 for Hand-Object Contact Prediction via Motion-Based Pseudo-Labeling and Guided Progressive Label Correction
Figure 3 for Hand-Object Contact Prediction via Motion-Based Pseudo-Labeling and Guided Progressive Label Correction
Figure 4 for Hand-Object Contact Prediction via Motion-Based Pseudo-Labeling and Guided Progressive Label Correction
Viaarxiv icon

Ego4D: Around the World in 3,000 Hours of Egocentric Video

Add code
Oct 13, 2021
Figure 1 for Ego4D: Around the World in 3,000 Hours of Egocentric Video
Figure 2 for Ego4D: Around the World in 3,000 Hours of Egocentric Video
Figure 3 for Ego4D: Around the World in 3,000 Hours of Egocentric Video
Figure 4 for Ego4D: Around the World in 3,000 Hours of Egocentric Video
Viaarxiv icon

Foreground-Aware Stylization and Consensus Pseudo-Labeling for Domain Adaptation of First-Person Hand Segmentation

Add code
Jul 11, 2021
Figure 1 for Foreground-Aware Stylization and Consensus Pseudo-Labeling for Domain Adaptation of First-Person Hand Segmentation
Figure 2 for Foreground-Aware Stylization and Consensus Pseudo-Labeling for Domain Adaptation of First-Person Hand Segmentation
Figure 3 for Foreground-Aware Stylization and Consensus Pseudo-Labeling for Domain Adaptation of First-Person Hand Segmentation
Figure 4 for Foreground-Aware Stylization and Consensus Pseudo-Labeling for Domain Adaptation of First-Person Hand Segmentation
Viaarxiv icon