riken-grp

dataloader_reflective_stretch

Dataloader for Dataset Consists User Situations and Reflective Robot Actions

GazeVQA

Dataset for the LREC-COLING 2024 paper "A Gaze-grounded Visual Question Answering Dataset for Clarifying Ambiguous Japanese Questions"

J-CRe3

A Japanese Conversation Dataset for Real-world Reference Resolution (Ueda et al., LREC-COLING, 2024)

langrobo-tutorial

This is the place to note langrobo-tutorial materials.

multimodal-reference

Code for J-CRe3 experiments (Ueda et al., LREC-COLING, 2024)

operative_action_captioning

PersonaSelection

riken-grp/GazeVQA

Dataset for the LREC-COLING 2024 paper "A Gaze-grounded Visual Question Answering Dataset for Clarifying Ambiguous Japanese Questions"

riken-grp/J-CRe3

A Japanese Conversation Dataset for Real-world Reference Resolution (Ueda et al., LREC-COLING, 2024)

riken-grp/dataloader_reflective_stretch

Dataloader for Dataset Consists User Situations and Reflective Robot Actions

riken-grp/multimodal-reference

Code for J-CRe3 experiments (Ueda et al., LREC-COLING, 2024)

riken-grp/langrobo-tutorial

This is the place to note langrobo-tutorial materials.

riken-grp/operative_action_captioning

riken-grp/PersonaSelection