1 code implementation • 5 Jun 2024 • Yulong Zhang, Yuan YAO, Shuhao Chen, Pengrong Jin, Yu Zhang, Jian Jin, Jiangang Lu
By analyzing the learning objective of ERM, we find that the guidance information for labeled samples in a specific category is the corresponding label encoding.
no code implementations • 17 Mar 2024 • Baiyan Zhang, Qin Chen, Jie zhou, Jian Jin, Liang He
In addition, we generate the rationales to explain why these events have causal relations.
1 code implementation • 13 Dec 2023 • Qi Tang, Yao Zhao, Meiqin Liu, Jian Jin, Chao Yao
As a critical clue of video super-resolution (VSR), inter-frame alignment significantly impacts overall performance.
no code implementations • 25 Sep 2023 • Tongtong Yuan, Xuange Zhang, Kun Liu, Bo Liu, Chen Chen, Jian Jin, Zhenzhen Jiao
Furthermore, we benchmark SOTA models for four multimodal tasks on this newly created dataset, which serve as new baselines for surveillance video-and-language understanding.
no code implementations • 18 Jun 2023 • Fanxin Xia, Jian Jin, Lili Meng, Feng Ding, Huaxiang Zhang
GAN-based image compression schemes have shown remarkable progress lately due to their high perceptual quality at low bit rates.
no code implementations • 5 Mar 2023 • Yaxuan Liu, Jian Jin, Yuan Xue, Weisi Lin
To benefit JND modeling, this work establishes a generalized JND dataset with a coarse-to-fine JND selection, which contains 106 source images and 1, 642 JND maps, covering 25 distortion types.
no code implementations • 25 Feb 2023 • Feng Ding, Jian Jin, Lili Meng, Weisi Lin
After combining them together, we can better assign the distortion in the compressed image with the guidance of JND to preserve the high perceptual quality.
1 code implementation • 16 Aug 2022 • Jian Jin, Yuan Xue, Xingxing Zhang, Lili Meng, Yao Zhao, Weisi Lin
However, they have a major drawback that the generated JND is assessed in the real-world signal domain instead of in the perceptual domain in the human brain.
no code implementations • 17 Jun 2022 • Wen Sun, Jian Jin, Weisi Lin
To achieve this, an adversarial loss is firstly proposed to make the deep learning models attacked by the adversarial images successfully.
1 code implementation • 1 May 2022 • Jiaju Lin, Qin Chen, Jie zhou, Jian Jin, Liang He
Implicit event argument extraction (EAE) aims to identify arguments that could scatter over the document.
no code implementations • 1 Mar 2022 • Jian Jin, Dong Yu, Weisi Lin, Lili Meng, Hao Wang, Huaxiang Zhang
Besides, the JND of the red and blue channels are larger than that of the green one according to the experimental results of the proposed model, which demonstrates that more changes can be tolerated in the red and blue channels, in line with the well-known fact that the human visual system is more sensitive to the green channel in comparison with the red and blue ones.
no code implementations • 7 Jan 2022 • Jian Jin, Xingxing Zhang, Lili Meng, Weisi Lin, Jie Liang, Huaxiang Zhang, Yao Zhao
Experimental results show that the VSD can be accurately estimated with the weights learnt by the nonlinear mapping function once its associated S-VSDs are available.
no code implementations • 19 Dec 2021 • Sien Chen, Jian Jin, Lili Meng, Weisi Lin, Zhuo Chen, Tsui-Shan Chang, Zhengguang Li, Huaxiang Zhang
Meanwhile, an image predictor is designed and trained to achieve the general-quality image reconstruction with the 16-bit gray-scale profile and signal features.
no code implementations • 16 Feb 2021 • Jian Jin, Xingxing Zhang, Xin Fu, huan zhang, Weisi Lin, Jian Lou, Yao Zhao
Experimental results on image classification demonstrate that we successfully find the JND for deep machine vision.
no code implementations • 22 Dec 2015 • Jian Jin
MDL, Multimodal Deep Learning Library, is a deep learning framework that supports multiple models, and this document explains its philosophy and functionality.