1 code implementation • 14 Jun 2023 • Ren Wang, Haoliang Sun, Qi Wei, Xiushan Nie, Yuling Ma, Yilong Yin
The key idea is to first break the rote memories by network pruning to address memorization overfitting in the inner loop, and then the gradients of pruned sub-networks naturally form the high-quality augmentation of the meta-gradient to alleviate learner overfitting in the outer loop.
no code implementations • 22 Mar 2022 • Tiantian He, Zhibin Li, Yongshun Gong, Yazhou Yao, Xiushan Nie, Yilong Yin
Non-linear activation functions, e. g., Sigmoid, ReLU, and Tanh, have achieved great success in neural networks (NNs).
no code implementations • 18 Mar 2022 • Jin Huang, Lu Zhang, Yongshun Gong, Jian Zhang, Xiushan Nie, Yilong Yin
Series photo selection (SPS) is an important branch of the image aesthetics quality assessment, which focuses on finding the best one from a series of nearly identical photos.
no code implementations • CVPR 2022 • Zheyun Qin, Xiankai Lu, Xiushan Nie, Yilong Yin, Jianbing Shen
Video Instance Segmentation (VIS) needs to automatically track and segment multiple objects in videos that rely on modeling the spatial-temporal interactions of the instances.
1 code implementation • 22 Jul 2021 • Chaoran Cui, Xiaojie Li, Juan Du, Chunyun Zhang, Xiushan Nie, Meng Wang, Yilong Yin
Extensive experiments on real-world data demonstrate the effectiveness of our approach.
no code implementations • 1 Apr 2021 • Xinfang Liu, Xiushan Nie, Zhifang Tan, Jie Guo, Yilong Yin
Natural language video localization (NLVL), which aims to locate a target moment from a video that semantically corresponds to a text query, is a novel and challenging task.
no code implementations • 7 Oct 2020 • Xiao Kang, Xingbo Liu, Xiushan Nie, Xiaoming Xi, Yilong Yin
In this study, we propose a novel method named Attention Model Enhanced Network (AMEN), which is formulated in a multi-branch fashion with pixel-wised attention model and classification submodular.
1 code implementation • 7 Oct 2020 • Xiao Kang, Xingbo Liu, Xiushan Nie, Yilong Yin
With the development of medical imaging technology and machine learning, computer-assisted diagnosis which can provide impressive reference to pathologists, attracts extensive research interests.
no code implementations • 24 Apr 2020 • Xingbo Liu, Xiushan Nie, Qi Dai, Yupan Huang, Yilong Yin
Due to the compelling efficiency in retrieval and storage, similarity-preserving hashing has been widely applied to approximate nearest neighbor search in large-scale image retrieval.
no code implementations • 15 Mar 2019 • Xingbo Liu, Xiushan Nie, Yilong Yin
Label information is widely used in hashing methods because of its effectiveness of improving the precision.
1 code implementation • 1 Oct 2018 • Xingbo Liu, Xiushan Nie, Yilong Yin
In this paper, in contrast to existing hashing methods, we propose a novel generalized framework called fusion hashing (FH) to improve the precision of existing hashing methods without adding new constraints or penalty terms.
Data Structures and Algorithms Multimedia
no code implementations • 27 Jan 2016 • Xiushan Nie, Yilong Yin, Jiande Sun
Therefore, in the present study, we mine the assistance and consensus among different features based on tensor model, and present a new comprehensive feature to fully use them in the proposed video fingerprinting framework.