publications

publications by categories in reversed chronological order.

2025

  1. Mitigating Visual Forgetting via Take-along Visual Conditioning for Multi-modal Long CoT Reasoning
    Hai-Long Sun, Zhun Sun, Houwen Peng, and 1 more author
    arXiv preprint arXiv:2503.13360, 2025

2024

  1. Transferring vision-language models for visual recognition: A classifier perspective
    Wenhao Wu, Zhun Sun, Yuxin Song, and 2 more authors
    International Journal of Computer Vision, 2024
  2. TNGPS: Discovering unknown tensor network structure search algorithms via large language models (LLMs)
    Junhua Zeng, Chao Li, Zhun Sun, and 2 more authors
    In Forty-first International Conference on Machine Learning, 2024
  3. Analyzing the Impact of Learnable Softmax Temperature in Contrastive Visual-Textual Alignment Systems: Benefits, Drawbacks, and Alternative Approaches
    Zhun Sun, and Chao Li
    Transactions on Machine Learning Research, 2024

2023

  1. Revisiting classifier: Transferring vision-language models for video recognition
    Wenhao Wu, Zhun Sun, and Wanli Ouyang
    In Proceedings of the AAAI conference on artificial intelligence, 2023
  2. Multi-level contrastive learning for self-supervised vision transformers
    Shentong Mo, Zhun Sun, and Chao Li
    In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2023
  3. Representation disentanglement in generative models with contrastive learning
    Shentong Mo, Zhun Sun, and Chao Li
    In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2023
  4. What can simple arithmetic operations do for temporal modeling?
    Wenhao Wu, Yuxin Song, Zhun Sun, and 3 more authors
    In Proceedings of the IEEE/CVF international conference on computer vision, 2023
  5. Rethinking prototypical contrastive learning through alignment, uniformity and correlation
    Shentong Mo, Zhun Sun, and Chao Li
    In The 33rd British Machine Vision Conference, 2023
  6. Exploring Data Augmentations on Self-/Semi-/Fully-Supervised Pre-trained Models
    Shentong Mo, Zhun Sun, and Chao Li
    In NeurIPS 2023 Workshop: Self-Supervised Learning - Theory and Practice, 2023
  7. Fractional Tensor Recurrent Unit (fTRU): A Stable Forecasting Model With Long Memory
    Hejia Qiu, Chao Li, Ying Weng, and 2 more authors
    IEEE Transactions on Neural Networks and Learning Systems, 2023

2022

  1. Siamese prototypical contrastive learning
    Shentong Mo, Zhun Sun, and Chao Li
    In The 32nd British Machine Vision Conference, 2022
  2. Are we pruning the correct channels in image-to-image translation models?
    Yiyong Li, Zhun Sun, and Chao Li
    In The 32nd British Machine Vision Conference, 2022

2021

  1. On the memory mechanism of tensor-power recurrent models
    Hejia Qiu, Chao Li, Ying Weng, and 3 more authors
    In International Conference on Artificial Intelligence and Statistics, 2021
  2. Hide chopin in the music: efficient information steganography via random shuffling
    Zhun Sun, Chao Li, and Qibin Zhao
    In ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021
  3. Focus and retain: Complement the broken pose in human image synthesis
    Pu Ge, Qiushi Huang, Wei Xiang, and 4 more authors
    In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2021
  4. Piecing and Chipping: An effective solution for the information-erasing view generation in Self-supervised Learning
    Jingwei Liu, Yi Gu, Shentong Mo, and 4 more authors
    2021

2020

  1. Evolutionary topology search for tensor network decomposition
    Chao Li, and Zhun Sun
    In International conference on machine learning, 2020
  2. Beyond unfolding: Exact recovery of latent convex tensor decomposition under reshuffling
    Chao Li, Mohammad Emtiyaz Khan, Zhun Sun, and 4 more authors
    In Proceedings of the AAAI Conference on Artificial Intelligence, 2020
  3. High-order learning model via fractional tensor network decomposition
    Chao Li, Zhun Sun, and Qibin Zhao
    In First Workshop on Quantum Tensor Networks in Machine Learning, 34th Conference on Neural Information Processing Systems (NeurIPS 2020), 2020
  4. Application-oblivious L7 parsing using recurrent neural networks
    Hao Li, Zhengda Bian, Peng Zhang, and 5 more authors
    IEEE/ACM Transactions on Networking, 2020

2019

  1. Dual residual networks leveraging the potential of paired operations for image restoration
    Xing Liu, Masanori Suganuma, Zhun Sun, and 1 more author
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019
  2. Improving head pose estimation with a combined loss and bounding box margin adjustment
    Mingzhen Shao, Zhun Sun, Mete Ozay, and 1 more author
    In 2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019), 2019
  3. Guaranteed matrix completion under multiple linear transformations
    Chao Li, Wei He, Longhao Yuan, and 2 more authors
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019
  4. Low-rank embedding of kernels in convolutional neural networks under random shuffling
    Chao Li, Zhun Sun, Jinshi Yu, and 2 more authors
    In ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019

2018

  1. Feature quantization for defending against distortion of images
    Zhun Sun, Mete Ozay, Yan Zhang, and 2 more authors
    In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018

2017

  1. HyperNetworks with statistical filtering for defending adversarial examples
    Zhun Sun, Mete Ozay, and Takayuki Okatani
    arXiv preprint arXiv:1711.01791, 2017
  2. Information potential auto-encoders
    Yan Zhang, Mete Ozay, Zhun Sun, and 1 more author
    arXiv preprint arXiv:1706.04635, 2017
  3. Linear discriminant generative adversarial networks
    Zhun Sun, Mete Ozay, and Takayuki Okatani
    arXiv preprint arXiv:1707.07831, 2017

2016

  1. Design of kernels in convolutional neural networks for image classification
    Zhun Sun, Mete Ozay, and Takayuki Okatani
    In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part VII 14, 2016