Publications
Highlights
Persistent Test-time Adaptation in Recurring Testing Scenarios
A Compact Dynamic 3D Gaussian Representation for Real-Time Dynamic View Synthesis
EVCap: Retrieval-Augmented Image Captioning with External Visual-Name Memory for Open-World Comprehension
Partition-and-Debias: Agnostic Biases Mitigation via A Mixture of Biases-Specific Experts
A-CAP: Anticipation Captioning with Commonsense Knowledge
StoryER: Automatic Story Evaluation via Ranking, Rating and Reasoning
NOC-REK: Novel Object Captioning with Retrieved Vocabulary from External Knowledge
OSSGAN: Open-Set Semi-Supervised Image Generation
Visual-Relation Conscious Image Generation from Structured-Text
Paired-D GAN for Semantic Image Synthesis
Balancing Content and Style with Two-Stream FCNs for Style Transfer
Paired-D++ GAN for Image Manipulation with Text
Two-stream FCNs to Balance Content and Style for Style Transfer
Full List
International Conference & Workshop
1
J-Shuwa: A Large-Scale Web-Collected Japanese Sign Language-Japanese Parallel Corpus
ACL, Findings 2026 ·
ACL, Findings 2026 ·
2
Improving Sign Language Understanding with a Multi-Stream Masked Autoencoder Trained on ASL Videos
AACL 2025 ·
AACL 2025 ·
3
4
5
Uncovering the Risk of Model Collapsing in Self-Supervised Continual Test-time Adaptation
Workshop on Self-Supervised Learning - Theory and Practice, NeurIPS 2024
Workshop on Self-Supervised Learning - Theory and Practice, NeurIPS 2024
6
Questioning, Answering, and Captioning for Zero-Shot Detailed Image Caption
Workshop on Large Vision - Language Model Learning and Applications, ACCV 2024
Workshop on Large Vision - Language Model Learning and Applications, ACCV 2024
7
Persistent Test-time Adaptation in Recurring Testing Scenarios
The Thirty-eighth Annual Conference on Neural Information Processing Systems, NeurIPS 2024 · See Project page
The Thirty-eighth Annual Conference on Neural Information Processing Systems, NeurIPS 2024 · See Project page
8
A Compact Dynamic 3D Gaussian Representation for Real-Time Dynamic View Synthesis
2024 European Conference on Computer Vision · See Project page
2024 European Conference on Computer Vision · See Project page
9
EVCap: Retrieval-Augmented Image Captioning with External Visual-Name Memory for Open-World Comprehension
IEEE Computer Vision and Pattern Recognition (CVPR), 2024 · Invited talk at MIRU, 2024
IEEE Computer Vision and Pattern Recognition (CVPR), 2024 · Invited talk at MIRU, 2024
10
Persistent Test-time Adaptation in Episodic Testing Scenarios
First Workshop on Test-Time Adaptation Model, Adapt Thyself (MAT), Community Track, CVPR 2024
First Workshop on Test-Time Adaptation Model, Adapt Thyself (MAT), Community Track, CVPR 2024
11
Improving the Robustness of 3D Human Pose Estimation: A Benchmark Dataset and Learning from Noisy Input
IEEE CVPR workshop on fair, data-efficient, and trusted computer vision, 2024
IEEE CVPR workshop on fair, data-efficient, and trusted computer vision, 2024
12
Balancing Reconstruction and Editing Quality of GAN Inversion for Real Image Editing with StyleGAN Prior Latent Space
IEEE Winter Conference on Applications of Computer Vision (WACV), 2024 · See Code
IEEE Winter Conference on Applications of Computer Vision (WACV), 2024 · See Code
13
Soft Curriculum for Learning Conditional GANs with Noisy-Labeled and Uncurated Unlabeled Data
IEEE Winter Conference on Applications of Computer Vision (WACV), 2024 · See Code
IEEE Winter Conference on Applications of Computer Vision (WACV), 2024 · See Code
14
Label Augmentation as Inter-class Data Augmentation for Conditional Image Synthesis with Imbalanced Data
IEEE Winter Conference on Applications of Computer Vision (WACV), 2024 · See Code
IEEE Winter Conference on Applications of Computer Vision (WACV), 2024 · See Code
15
Partition-and-Debias: Agnostic Biases Mitigation via A Mixture of Biases-Specific Experts
International Conference on Computer Vision (ICCV), 2023 · See Code
International Conference on Computer Vision (ICCV), 2023 · See Code
16
Revisiting Latent Space of GAN Inversion for Robust Real Image Editing
AI for Content Creation Workshop @CVPR, 2023
AI for Content Creation Workshop @CVPR, 2023
17
A-CAP: Anticipation Captioning with Commonsense Knowledge
IEEE Computer Vision and Pattern Recognition (CVPR), 2023 · See Video
IEEE Computer Vision and Pattern Recognition (CVPR), 2023 · See Video
18
Indirect Adversarial Losses via an Intermediate Distribution for Training GANs
IEEE Winter Conference on Applications of Computer Vision (WACV), 2023
IEEE Winter Conference on Applications of Computer Vision (WACV), 2023
19
StoryER: Automatic Story Evaluation via Ranking, Rating and Reasoning
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2022 · Oral
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2022 · Oral
20
NOC-REK: Novel Object Captioning with Retrieved Vocabulary from External Knowledge
IEEE Computer Vision and Pattern Recognition (CVPR), 2022
IEEE Computer Vision and Pattern Recognition (CVPR), 2022
21
OSSGAN: Open-Set Semi-Supervised Image Generation
IEEE Computer Vision and Pattern Recognition (CVPR), 2022 · Invited talk at MIRU, 2022
IEEE Computer Vision and Pattern Recognition (CVPR), 2022 · Invited talk at MIRU, 2022
22
PPCD-GAN: Progressive Pruning and Class-Aware Distillation for Large-Scale Conditional GANs Compression
IEEE Winter Conference on Applications of Computer Vision (WACV), 2022 · See Poster
IEEE Winter Conference on Applications of Computer Vision (WACV), 2022 · See Poster
23
Saliency based Subject Selection for Diverse Image Captioning
17th International Conference on Machine Vision Applications, 2021
17th International Conference on Machine Vision Applications, 2021
24
Visual-Relation Conscious Image Generation from Structured-Text
European Conference on Computer Vision (ECCV), 2020
European Conference on Computer Vision (ECCV), 2020
25
Stylized-Colorization for Line Arts
25th International Conference on Pattern Recognition (ICPR), 2020
25th International Conference on Pattern Recognition (ICPR), 2020
26
Paired-D GAN for Semantic Image Synthesis
Asian Conference on Computer Vision (ACCV), 2018 · See Poster and Code
Asian Conference on Computer Vision (ACCV), 2018 · See Poster and Code
27
Balancing Content and Style with Two-Stream FCNs for Style Transfer
IEEE Winter Conference on Applications of Computer Vision (WACV), 2018 · See Poster, Code, Demo
IEEE Winter Conference on Applications of Computer Vision (WACV), 2018 · See Poster, Code, Demo
28
Facial Expression Recognition by Re-ranking with Global and Local Generic Features
23rd International Conference on Pattern Recognition (ICPR), 2016 · See Poster
23rd International Conference on Pattern Recognition (ICPR), 2016 · See Poster
Domestic Conference & Workshop
1
2
3
Robust Novel Object Captioning by Retrieving Objects from External Knowledge
First International Workshop on Embodied Semiotics (EmSemi2023) (Idea presentation)
First International Workshop on Embodied Semiotics (EmSemi2023) (Idea presentation)
4
Biases mitigation in medical images via knowledge guidance
First International Workshop on Embodied Semiotics (EmSemi2023) (Idea presentation)
First International Workshop on Embodied Semiotics (EmSemi2023) (Idea presentation)
5
Enhancing Sign Language Translation with Quantized Video Encoding
First International Workshop on Embodied Semiotics (EmSemi2023) (Idea presentation)
First International Workshop on Embodied Semiotics (EmSemi2023) (Idea presentation)
Journal
1
Anticipation Captioning with Commonsense Knowledge
Journal of the Imaging Society of Japan, 2023 (Invited commentorary paper)
Journal of the Imaging Society of Japan, 2023 (Invited commentorary paper)
2
Stochastically Flipping Labels of Discriminator’s Outputs for Training Generative Adversarial Networks
IEEE Access, 2022
IEEE Access, 2022
3
4
Two-stream FCNs to Balance Content and Style for Style Transfer
Machine Vision and Applications (MVAP), 2020
Machine Vision and Applications (MVAP), 2020