Tatsuya Harada

45

Papers

69

Total Citations

Papers (45)

GPAvatar: Generalizable and Precise Head Avatar from Image(s)

Find n' Propagate: Open-Vocabulary 3D Object Detection in Urban Environments

Luminance-GS: Adapting 3D Gaussian Splatting to Challenging Lighting Conditions with View-Adaptive Curve Adjustment

Symmetric Q-learning: Reducing Skewness of Bellman Error in Online Reinforcement Learning

Gradual Transition from Bellman Optimality Operator to Bellman Operator in Online Reinforcement Learning

Discovering Multiple Solutions from a Single Task in Offline Reinforcement Learning

Recognizing Activities of Daily Living With a Wrist-Mounted Camera

Multi-Label Ranking From Positive and Unlabeled Data

Kernel Approximation via Empirical Orthogonal Decomposition for Unsupervised Feature Learning

Maximum Classifier Discrepancy for Unsupervised Domain Adaptation

Neural 3D Mesh Renderer

Between-Class Learning for Image Classification

Viewpoint-Aware Video Summarization

Customized Image Narrative Generation via Interactive Visual Question Generation and Answering

Label-Noise Robust Generative Adversarial Networks

Strong-Weak Distribution Alignment for Adaptive Object Detection

Multimodal Explanations by Predicting Counterfactuality in Videos

Learning to Explain With Complemental Examples

Learning View Priors for Single-View 3D Reconstruction

Learning to Optimize Non-Rigid Tracking

Noise Robust Generative Adversarial Networks

Blur, Noise, and Compression Robust Generative Adversarial Networks

Goal-Oriented Gaze Estimation for Zero-Shot Learning

Lepard: Learning Partial Point Cloud Matching in Rigid and Deformable Scenes

Revisiting Domain Generalized Stereo Matching Networks From a Feature Consistency Perspective

Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objects

Common Subspace for Model and Similarity: Phrase Learning for Caption Generation From Images

Spatio-Temporal Person Retrieval via Natural Language Queries

Image Generation From Small Datasets via Batch Statistics Adaptation

Generating Easy-to-Understand Referring Expressions for Target Identifications

Multi-Stage Pathological Image Classification Using Semantic Segmentation

Multitask AET With Orthogonal Tangent Regularity for Dark Object Detection

Name Your Colour For the Task: Artificially Discover Colour Naming via Colour Quantisation Transformer

Bounding-box Channels for Visual Relationship Detection

Unsupervised Pose-Aware Part Decomposition for Man-Made Articulated Objects

Exploring Resolution and Degradation Clues As Self-Supervised Signal for Low Quality Object Detection

Unsupervised Learning of Efficient Geometry-Aware Neural Articulated Representations

Deforming Radiance Fields with Cages

Neural Articulated Radiance Field

A Theory of Learning Unified Model via Knowledge Integration from Label Space Varying Domains

Aleth-NeRF: Illumination Adaptive NeRF with Concealing Field Assumption

Neural Star Domain as Primitive Representation

Non-rigid Point Cloud Registration with Neural Deformation Pyramid

Detection Based Part-level Articulated Object Reconstruction from Single RGBD Image

Asymmetric Tri-training for Unsupervised Domain Adaptation