publications
publications by categories in reversed chronological order.
2025
- Mitigating Visual Forgetting via Take-along Visual Conditioning for Multi-modal Long CoT ReasoningarXiv preprint arXiv:2503.13360, 2025
2024
- Transferring vision-language models for visual recognition: A classifier perspectiveInternational Journal of Computer Vision, 2024
- TNGPS: Discovering unknown tensor network structure search algorithms via large language models (LLMs)In Forty-first International Conference on Machine Learning, 2024
- Analyzing the Impact of Learnable Softmax Temperature in Contrastive Visual-Textual Alignment Systems: Benefits, Drawbacks, and Alternative ApproachesTransactions on Machine Learning Research, 2024
2023
- Revisiting classifier: Transferring vision-language models for video recognitionIn Proceedings of the AAAI conference on artificial intelligence, 2023
- Multi-level contrastive learning for self-supervised vision transformersIn Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2023
- Representation disentanglement in generative models with contrastive learningIn Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2023
- What can simple arithmetic operations do for temporal modeling?In Proceedings of the IEEE/CVF international conference on computer vision, 2023
- Rethinking prototypical contrastive learning through alignment, uniformity and correlationIn The 33rd British Machine Vision Conference, 2023
- Exploring Data Augmentations on Self-/Semi-/Fully-Supervised Pre-trained ModelsIn NeurIPS 2023 Workshop: Self-Supervised Learning - Theory and Practice, 2023
- Fractional Tensor Recurrent Unit (fTRU): A Stable Forecasting Model With Long MemoryIEEE Transactions on Neural Networks and Learning Systems, 2023
2022
- Siamese prototypical contrastive learningIn The 32nd British Machine Vision Conference, 2022
- Are we pruning the correct channels in image-to-image translation models?In The 32nd British Machine Vision Conference, 2022
2021
- On the memory mechanism of tensor-power recurrent modelsIn International Conference on Artificial Intelligence and Statistics, 2021
- Hide chopin in the music: efficient information steganography via random shufflingIn ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021
- Focus and retain: Complement the broken pose in human image synthesisIn Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2021
- Piecing and Chipping: An effective solution for the information-erasing view generation in Self-supervised Learning2021
2020
- Evolutionary topology search for tensor network decompositionIn International conference on machine learning, 2020
- Beyond unfolding: Exact recovery of latent convex tensor decomposition under reshufflingIn Proceedings of the AAAI Conference on Artificial Intelligence, 2020
- High-order learning model via fractional tensor network decompositionIn First Workshop on Quantum Tensor Networks in Machine Learning, 34th Conference on Neural Information Processing Systems (NeurIPS 2020), 2020
- Application-oblivious L7 parsing using recurrent neural networksIEEE/ACM Transactions on Networking, 2020
2019
- Dual residual networks leveraging the potential of paired operations for image restorationIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019
- Improving head pose estimation with a combined loss and bounding box margin adjustmentIn 2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019), 2019
- Guaranteed matrix completion under multiple linear transformationsIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019
- Low-rank embedding of kernels in convolutional neural networks under random shufflingIn ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019
2018
- Feature quantization for defending against distortion of imagesIn Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018
2017
- HyperNetworks with statistical filtering for defending adversarial examplesarXiv preprint arXiv:1711.01791, 2017
- Information potential auto-encodersarXiv preprint arXiv:1706.04635, 2017
- Linear discriminant generative adversarial networksarXiv preprint arXiv:1707.07831, 2017
2016
- Design of kernels in convolutional neural networks for image classificationIn Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part VII 14, 2016