Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Yoshihide AoshimaSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works420 from public data
- Maximum Classifier Discrepancy for Unsupervised Domain Adaptation2,161
A new approach that attempts to align distributions of source and target by utilizing the task-specific decision boundaries by maximizing the discrepancy between two classifiers' outputs to detect target samples that are far from the support of the source.
- 1,232
- Neural 3D Mesh Renderer1,184
This work proposes an approximate gradient for rasterization that enables the integration of rendering into neural networks and performs gradient-based 3D mesh editing operations, such as 2D-to-3D style transfer and 3D DeepDream, with 2D supervision for the first time.
- Strong-Weak Distribution Alignment for Adaptive Object Detection788
This work proposes an approach for unsupervised adaptation of object detectors from label-rich to label-poor domains which can significantly reduce annotation costs associated with detection, and designs the strong domain alignment model to only look at local receptive fields of the feature map.
- 725
- Open Set Domain Adaptation by Backpropagation622
This paper proposes a method for an open set domain adaptation scenario, which utilizes adversarial training, and allows to extract features that separate unknown target from known target samples.
- 383
- Domain Generalization Using a Mixture of Multiple Latent Domains369
This paper proposes a method that iteratively divides samples into latent domains via clustering, and which trains the domain-invariant feature extractor shared among the divided latent domains through adversarial learning, which outperforms conventional domain generalization methods, including those that utilize domain labels.
- Frequency-Aware Feature Fusion for Dense Image Prediction325
Comprehensive visualization and quantitative analysis demonstrate that FreqFusion effectively improves feature consistency and sharpens object boundaries, and extensive experiments across various dense prediction tasks confirm its effectiveness.
- Neural Articulated Radiance Field249
Neural Articulated Radiance Field is a novel deformable 3D representation for articulated objects learned from images that is fully differentiable and can be trained from images with pose annotations through the use of an autoencoder.
- Between-Class Learning for Image Classification228
This paper proposes a simple mixing method using internal divisions, which surprisingly proves to significantly improve performance and proposes a mixing method that treats the images as waveforms, which leads to a further improvement in performance.
- Image Generation From Small Datasets via Batch Statistics Adaptation212
This work proposes a new method for transferring prior knowledge of the pre-trained generator, which is trained with a large dataset, to a small dataset in a different domain, and can generate higher quality images compared to previous methods without collapsing.
- 207
- Multispectral Object Detection for Autonomous Vehicles201
The results show that each component in the multispectral image was individually useful for the task of object detection when applied to different types of objects, and the mean average precision (mAP) of mult ispectral object detection is 13% higher than that of RGB-only object detection.
- Lepard: Learning partial point cloud matching in rigid and deformable scenes200
Lepard, a Learning based approach for partial point cloud matching in rigid and deformable scenes with key characteristics are an architecture that disentangles point cloud representation into feature space and 3D position space and a position encoding method that explicitly reveals 3D relative distance information through the dot product of vectors.
- 190
- Multitask AET with Orthogonal Tangent Regularity for Dark Object Detection188
This work proposes a novel multitask auto encoding transformation (MAET) model which is able to explore the intrinsic pattern behind illumination translation and achieves the object detection task by decoding the bounding box coordinates and classes.
- Goal-Oriented Gaze Estimation for Zero-Shot Learning171
This work introduces a novel goal-oriented gaze estimation module (GEM) to improve the discriminative attribute localization based on the class-level attributes for ZSL and implies the promising benefits of collecting human gaze dataset and automatic gaze estimation algorithms on high-level computer vision tasks.
- Online growing neural gas for anomaly detection in changing surveillance scenes118
A neural network based model called online Growing Neural Gas (online GNG) to perform an unsupervised learning to perform anomaly detection and effectively reduces the false alarms and leak detections caused by model aging which frequently happens in changing surveillance scenes.
- 100
- 97
- Revisiting Domain Generalized Stereo Matching Networks from a Feature Consistency Perspective91
A simple pixel-wise contrastive learning across the viewpoints for stereo matching performance to unseen domains is proposed, which achieves superior performance over several state-of-the-art networks.
- GPAvatar: Generalizable and Precise Head Avatar from Image(s)89
A framework named GPAvatar is proposed that reconstructs 3D head avatars from one or several images in a single forward pass and introduces a dynamic point-based expression field driven by a point cloud to precisely and effectively capture expressions.
- Learning View Priors for Single-View 3D Reconstruction88
This work proposes to train a discriminator that learns prior knowledge regarding possible views to reconstruct shapes that look reasonable from any viewpoint and outperforms current state-of-the-art methods on both synthetic and natural image datasets.
- Image Reconstruction from Bag-of-Visual-Words86
This work uses a large-scale image database to estimate the spatial arrangement of local descriptors and proposes a heuristic but efficient method to optimize it, which can reconstruct the original images, although the image features lack spatial information and include quantization errors.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-15. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.