Komei Sugiura
12 papers · 2019–2026 · 7 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (24) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Gold 𧬠Topic Evolution
ποΈ
Keyword Collector
(61)
π
Renaissance Researcher
(5)
π
Century Club Β· Bronze
Top co-authors
Research topics
Artificial Intelligence
(8)
Core AI
(8)
Computer Vision
(6)
Machine Learning
(5)
Core Methods
(5)
Generation Β· Computer Vision
(4)
Deep Learning
(3)
Natural Language Processing
(3)
Generation Β· Natural Language Processing
(3)
Robotics
(2)
Capabilities
(2)
Learning Types
(2)
Data Science & Analytics
(1)
Applications
(1)
Architectures
(1)
Keywords
image captioning
(3)
multimodal large language model
(3)
image captioning evaluation
(2)
metric learning
(2)
automatic evaluation metric
(2)
multimodal learning
(2)
human judgment
(1)
scene graph
(1)
natural language generation
(1)
question generation
(1)
referring expression
(1)
time series forecasting
(1)
attention mechanism
(1)
optical flow
(1)
state space model
(1)
supervised learning
(1)
human feedback
(1)
synthetic data
(1)
viewpoint invariance
(1)
scene understanding
(1)
Papers
LLM-Free Image Captioning Evaluation in Reference-Flexible Settings
AAAI 2026
ReMoRa: Multimodal Large Language Model based on Refined Motion Representation for Long-Video Understanding
CVPR 2026
ZINA: Multimodal Fine-grained Hallucination Detection and Editing
CVPR 2026
Deep Space Weather Model: Long-Range Solar Flare Prediction from Multi-Wavelength Images
ICCV 2025
GENNAV: Polygon Mask Generation for Generalized Referring Navigable Regions
CoRL 2025
VELA: An LLM-Hybrid-as-a-Judge Approach for Evaluating Long Image Captions
EMNLP 2025
Layer-Wise Relevance Propagation with Conservation Property for ResNet
ECCV 2024
Polos: Multimodal Metric Learning from Human Feedback for Image Captioning
CVPR 2024
Task Success Prediction for Open-Vocabulary Manipulation Based on Multi-Level Aligned Representations
CoRL 2024
JaSPICE: Automatic Evaluation Metric Using Predicate-Argument Structures for Image Captioning Models
CoNLL 2023
Unified Questioner Transformer for Descriptive Question Generation in Goal-Oriented Visual Dialogue
ICCV 2021
Multimodal Attention Branch Network for Perspective-Free Sentence Generation
CoRL 2019