• 研究課題をさがす
  • 研究者をさがす
  • KAKENの使い方
  1. 課題ページに戻る

2023 年度 実績報告書

Vision and language cross-modal for training conditional GANs with long-tail data.

研究課題

研究課題/領域番号 22K17947
研究機関東京大学

研究代表者

ヴォ ミンデュク  東京大学, 大学院情報理工学系研究科, 特任助教 (40939906)

研究期間 (年度) 2022-04-01 – 2024-03-31
キーワードVision and language / Novel object captioning / GANs / External knowledge / Bias mitigation
研究実績の概要

We expand our knowledge of the cross-modality between vision and language spaces. We obtained four achievements:
1. By using commonsense knowledge, we can anticipate the future, given a set of sparsely temporally-ordered set of images. It was published at CVPR 2023.
2. We explore training GANs under limited and open-set dataset as well as GAN inversion. The three papers were published at WACV 2024.
3. We build a new knowledge containing image features and corresponding object names. Using it, we propose a method for novel object captioning that outperforms other methods while being comparable to LLMs. It will be published at CVPR 2024.
4. We also gain knowledge about bias mitigation in image classification using a mixture of biases-specific experts. It was published at ICCV 2023.

  • 研究成果

    (13件)

すべて 2024 2023

すべて 雑誌論文 (7件) (うち国際共著 7件、 査読あり 7件) 学会発表 (6件) (うち国際学会 6件)

  • [雑誌論文] Soft Curriculum for Learning Conditional GANs with Noisy-Labeled and Uncurated Unlabeled Data2024

    • 著者名/発表者名
      Katsumata Kai、Vo Duc Minh、Harada Tatsuya、Nakayama Hideki
    • 雑誌名

      2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

      巻: 1 ページ: 5311-5320

    • DOI

      10.1109/WACV57701.2024.00524

    • 査読あり / 国際共著
  • [雑誌論文] Revisiting Latent Space of GAN Inversion for Robust Real Image Editing2024

    • 著者名/発表者名
      Katsumata Kai、Vo Duc Minh、Liu Bei、Nakayama Hideki
    • 雑誌名

      2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

      巻: 1 ページ: 5301-5310

    • DOI

      10.1109/WACV57701.2024.00523

    • 査読あり / 国際共著
  • [雑誌論文] Label Augmentation as Inter-class Data Augmentation for Conditional Image Synthesis with Imbalanced Data2024

    • 著者名/発表者名
      Katsumata Kai、Vo Duc Minh、Nakayama Hideki
    • 雑誌名

      2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

      巻: 1 ページ: 4932-4941

    • DOI

      10.1109/WACV57701.2024.00487

    • 査読あり / 国際共著
  • [雑誌論文] EVCap: Retrieval-Augmented Image Captioning with External Visual--Name Memory for Open-World Comprehension2024

    • 著者名/発表者名
      Li Jiaxuan、Vo Duc Minh、Sugimoto Akihiro, Nakayama Hideki
    • 雑誌名

      2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

      巻: 1 ページ: -

    • 査読あり / 国際共著
  • [雑誌論文] Partition-and-Debias: Agnostic Biases Mitigation via A Mixture of Biases-Specific Experts2023

    • 著者名/発表者名
      Li Jiaxuan、Vo Duc Minh、Nakayama Hideki
    • 雑誌名

      2023 IEEE/CVF International Conference on Computer Vision (ICCV)

      巻: 1 ページ: 4901-4911

    • DOI

      10.1109/ICCV51070.2023.00454

    • 査読あり / 国際共著
  • [雑誌論文] A-CAP: Anticipation Captioning with Commonsense Knowledge2023

    • 著者名/発表者名
      Vo Duc Minh、Luong Quoc-An、Sugimoto Akihiro、Nakayama Hideki
    • 雑誌名

      2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

      巻: 1 ページ: 10824-10833

    • DOI

      10.1109/CVPR52729.2023.01042

    • 査読あり / 国際共著
  • [雑誌論文] Indirect Adversarial Losses via an Intermediate Distribution for Training GANs2023

    • 著者名/発表者名
      Yang Rui、Vo Duc Minh、Nakayama Hideki
    • 雑誌名

      2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

      巻: 1 ページ: 4641-4650

    • DOI

      10.1109/WACV56688.2023.00463

    • 査読あり / 国際共著
  • [学会発表] Soft Curriculum for Learning Conditional GANs with Noisy-Labeled and Uncurated Unlabeled Data2024

    • 著者名/発表者名
      Katsumata Kai、Vo Duc Minh、Harada Tatsuya、Nakayama Hideki
    • 学会等名
      2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
    • 国際学会
  • [学会発表] Revisiting Latent Space of GAN Inversion for Robust Real Image Editing2024

    • 著者名/発表者名
      Katsumata Kai、Vo Duc Minh、Liu Bei、Nakayama Hideki
    • 学会等名
      2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
    • 国際学会
  • [学会発表] Label Augmentation as Inter-class Data Augmentation for Conditional Image Synthesis with Imbalanced Data2024

    • 著者名/発表者名
      Katsumata Kai、Vo Duc Minh、Nakayama Hideki
    • 学会等名
      2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
    • 国際学会
  • [学会発表] Partition-and-Debias: Agnostic Biases Mitigation via A Mixture of Biases-Specific Experts2023

    • 著者名/発表者名
      Li Jiaxuan、Vo Duc Minh、Nakayama Hideki
    • 学会等名
      2023 IEEE/CVF International Conference on Computer Vision (ICCV)
    • 国際学会
  • [学会発表] A-CAP: Anticipation Captioning with Commonsense Knowledge2023

    • 著者名/発表者名
      Vo Duc Minh、Luong Quoc-An、Sugimoto Akihiro、Nakayama Hideki
    • 学会等名
      2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
    • 国際学会
  • [学会発表] Indirect Adversarial Losses via an Intermediate Distribution for Training GANs2023

    • 著者名/発表者名
      Yang Rui、Vo Duc Minh、Nakayama Hideki
    • 学会等名
      2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
    • 国際学会

URL: 

公開日: 2024-12-25  

サービス概要 検索マニュアル よくある質問 お知らせ 利用規程 科研費による研究の帰属

Powered by NII kakenhi