1 citations · 3 across the 17 of their papers we have counts for
7 papers · 1 filter
AdaCoder: Adaptive Prompt Compression for Programmatic Visual Question Answering
Mahiro Ukai, Shuhei Kurita, Atsushi Hashimoto +2
Visual question answering aims to provide responses to natural language questions given visual input. Recently, visual programmatic models (VPMs), which generate executable program…
Answerability Fields: Answerable Location Estimation via Diffusion Models
Daichi Azuma, Taiki Miyanishi, Shuhei Kurita +2
In an era characterized by advancements in artificial intelligence and robotics, enabling machines to interact with and understand their environment is a critical research endeavor…
CityNav: A Large-Scale Dataset for Real-World Aerial Navigation
Jungdae Lee, Taiki Miyanishi, Shuhei Kurita +4
Vision-and-language navigation (VLN) aims to develop agents capable of navigating in realistic environments. While recent cross-modal training approaches have significantly improve…
Map-based Modular Approach for Zero-shot Embodied Question Answering
Koya Sakamoto, Daichi Azuma, Taiki Miyanishi +2
Embodied Question Answering (EQA) serves as a benchmark task to evaluate the capability of robots to navigate within novel environments and identify objects in response to human qu…
Text-driven Affordance Learning from Egocentric Vision
Tomoya Yoshida, Shuhei Kurita, Taichi Nishimura +1
Visual affordance learning is a key component for robots to understand how to interact with objects. Conventional approaches in this field rely on pre-defined objects and actions,…
JDocQA: Japanese Document Question Answering Dataset for Generative Language Models
Eri Onami, Shuhei Kurita, Taiki Miyanishi +1
Document question answering is a task of question answering on given documents such as reports, slides, pamphlets, and websites, and it is a truly demanding task as paper and elect…
Vision Language Model-based Caption Evaluation Method Leveraging Visual Context Extraction
Koki Maeda, Shuhei Kurita, Taiki Miyanishi +1
Given the accelerating progress of vision and language modeling, accurate evaluation of machine-generated image captions remains critical. In order to evaluate captions more closel…