1 citations · 3 across the 17 of their papers we have counts for
23 papers
Rendering-Free Lookahead for Question-Guided Active Vision
Koya Sakamoto, Daichi Azuma, Shuhei Kurita +4
Active robot vision requires controlling the camera to reveal task-relevant information that is hidden from the current viewpoint. For example, determining what is inside a box may…
CapFrame: Text-Instructed Viewpoint Grounding in 3D Gaussian Scenes via Geometric Pseudo Labels
Jirong Li, Satoshi Ikehata, Shuhei Kurita +1
3D Gaussian Splatting (3DGS) enables photorealistic real-time novel view synthesis, yet placing a virtual camera to capture a desired frame remains largely manual. Existing languag…
LongEgoRefer: A Benchmark for Long-Form Egocentric Video Referring Expression Comprehension
Shunya Kato, Taiki Miyanishi, Shuhei Kurita +3
Egocentric videos capture rich and diverse human-object interactions and have emerged as a fundamental resource for understanding human activities related to objects. In this conte…
NavWAM: A Navigation World Action Model for Goal-Conditioned Visual Navigation
Daichi Azuma, Taiki Miyanishi, Koya Sakamoto +6
Goal-conditioned visual navigation requires a robot to act under partial observability by anticipating how its motion will change the future egocentric view and whether that change…
E3VS-Bench: A Benchmark for Viewpoint-Dependent Active Perception in 3D Gaussian Splatting Scenes
Koya Sakamoto, Taiki Miyanishi, Daichi Azuma +6
Visual search in 3D environments requires embodied agents to actively explore their surroundings and acquire task-relevant evidence. However, existing visual search and embodied AI…
PhysQuantAgent: An Inference Pipeline of Mass Estimation for Vision-Language Models
Hisayuki Yokomizo, Taiki Miyanishi, Yan Gang +3
Vision-Language Models (VLMs) are increasingly applied to robotic perception and manipulation, yet their ability to infer physical properties required for manipulation remains limi…
Diagnosing Long-Video Quantitative Reasoning in Multimodal LLMs via Enumeration and Counting
Fumihiko Tsuchiya, Taiki Miyanishi, Shunsuke Yasuki +5
Final-answer video QA can show whether a model predicts the right number, but not which instances it counted, when the supporting evidence occurs, or why it failed. We diagnose lon…
ReMoRa: Multimodal Large Language Model based on Refined Motion Representation for Long-Video Understanding
Daichi Yashima, Shuhei Kurita, Yusuke Oda +1
While multimodal large language models (MLLMs) have shown remarkable success across a wide range of tasks, long-form video understanding remains a significant challenge. In this st…
Evaluating Multimodal Large Language Models on Vertically Written Japanese Text
Keito Sasagawa, Shuhei Kurita, Daisuke Kawahara
Multimodal Large Language Models (MLLMs) have seen rapid advances in recent years and are now being applied to visual document understanding tasks. They are expected to process a w…
STATUS Bench: A Rigorous Benchmark for Evaluating Object State Understanding in Vision-Language Models
Mahiro Ukai, Shuhei Kurita, Nakamasa Inoue
Object state recognition aims to identify the specific condition of objects, such as their positional states (e.g., open or closed) and functional states (e.g., on or off). While r…
Referring Expression Comprehension for Small Objects
Kanoko Goto, Takumi Hirose, Mahiro Ukai +2
Referring expression comprehension (REC) aims to localize the target object described by a natural language expression. Recent advances in vision-language learning have led to sign…
Developing Vision-Language-Action Model from Egocentric Videos
Tomoya Yoshida, Shuhei Kurita, Taichi Nishimura +1
Egocentric videos capture how humans manipulate objects and tools, providing diverse motion cues for learning object manipulation. Unlike the costly, expert-driven manual teleopera…
GeoProg3D: Compositional Visual Reasoning for City-Scale 3D Language Fields
Shunsuke Yasuki, Taiki Miyanishi, Nakamasa Inoue +5
The advancement of 3D language fields has enabled intuitive interactions with 3D scenes via natural language. However, existing approaches are typically limited to small-scale envi…
LegalViz: Legal Text Visualization by Text To Diagram Generation
Eri Onami, Taiki Miyanishi, Koki Maeda +1
Legal documents including judgments and court orders require highly sophisticated legal knowledge for understanding. To disclose expert knowledge for non-experts, we explore the pr…
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…
CityRefer: Geography-aware 3D Visual Grounding Dataset on City-scale Point Cloud Data
Taiki Miyanishi, Fumiya Kitamori, Shuhei Kurita +3
City-scale 3D point cloud is a promising way to express detailed and complicated outdoor structures. It encompasses both the appearance and geometry features of segmented city comp…
Cross3DVG: Cross-Dataset 3D Visual Grounding on Different RGB-D Scans
Taiki Miyanishi, Daichi Azuma, Shuhei Kurita +1
We present a novel task for cross-dataset visual grounding in 3D scenes (Cross3DVG), which overcomes limitations of existing 3D visual grounding models, specifically their restrict…