no code implementations • 4 May 2018 • Xin Ma
A short discussion on the priority of this new framework to the existing grey models and LSSVM have also been discussed in this paper.
no code implementations • 25 Jul 2018 • Ling Liang, Lei Deng, Yueling Zeng, Xing Hu, Yu Ji, Xin Ma, Guoqi Li, Yuan Xie
Crossbar architecture based devices have been widely adopted in neural network accelerators by taking advantage of the high efficiency on vector-matrix multiplication (VMM) operations.
no code implementations • 25 Oct 2018 • Zhaodong Chen, Lei Deng, Guoqi Li, Jiawei Sun, Xing Hu, Xin Ma, Yuan Xie
In this paper, we propose alleviating this problem through sampling only a small fraction of data for normalization at each iteration.
1 code implementation • 25 Nov 2019 • Shan An, Guangfu Che, Fangru Zhou, Xianglong Liu, Xin Ma, Yu Chen
Visual loop closure detection, which can be considered as an image retrieval task, is an important problem in SLAM (Simultaneous Localization and Mapping) systems.
no code implementations • 3 Dec 2019 • Xin Ma, Guorong Wu, Won Hwa Kim
As there is significant interest in understanding the altered interactions between different brain regions that lead to neuro-disorders, it is important to develop data-driven methods that work with a population of graph data for traditional prediction tasks.
no code implementations • 21 Dec 2019 • Xin Ma, Yi Li, Huaibo Huang, Mandi Luo, Ran He
Real-world image super-resolution (SR) is a challenging image translation problem.
no code implementations • 29 Oct 2020 • Xin Ma, Xiaoqiang Zhou, Huaibo Huang, Zhenhua Chai, Xiaolin Wei, Ran He
It is difficult for encoders to capture such powerful representations under this complex situation.
no code implementations • 2 Nov 2020 • Xin Ma, Jianchao Wu
In this paper, we introduce two new approximation properties for \'etale groupoids, almost elementariness and (ubiquitous) fiberwise amenability, inspired by Matui's and Kerr's notions of almost finiteness.
Operator Algebras Dynamical Systems 22A22 (primary) 46L35, 51F30, 37A55, 37B05 (Secondary)
no code implementations • 10 Nov 2020 • Yuhe Ding, Xin Ma, Mandi Luo, Aihua Zheng, Ran He
Considering the intuitive artifacts in the existing methods, we propose a contrastive style loss for style rendering to enforce the similarity between the style of rendered photo and the caricature, and simultaneously enhance its discrepancy to the photos.
no code implementations • 8 Dec 2020 • Angelo Ziletti, Christoph Berns, Oliver Treichel, Thomas Weber, Jennifer Liang, Stephanie Kammerath, Marion Schwaerzler, Jagatheswari Virayah, David Ruau, Xin Ma, Andreas Mattern
Millions of unsolicited medical inquiries are received by pharmaceutical companies every year.
no code implementations • 1 Jan 2021 • Xin Ma, Zhicheng Zhang, Danfeng Wang, Yu Luo, Hui Yuan
In deep learning-based local stereo matching methods, larger image patches usually bring better stereo matching accuracy.
no code implementations • 9 Jun 2021 • Xin Ma, Won Hwa Kim
VCC takes advantage of distributions of local relationships of samples near the boundary of clusters, so that they can be properly separated and pulled to cluster centers to form compact clusters.
no code implementations • 20 Dec 2021 • Xin Ma, Xiaoqiang Zhou, Huaibo Huang, Gengyun Jia, Zhenhua Chai, Xiaolin Wei
This multi-scale architecture is beneficial for the decoder to utilize discriminative representations learned from encoders into images.
1 code implementation • CVPR 2022 • Huanyu Wang, Junjie Liu, Xin Ma, Yang Yong, Zhenhua Chai, Jianxin Wu
Hence, previous methods optimize the compressed model layer-by-layer and try to make every layer have the same outputs as the corresponding layer in the teacher model, which is cumbersome.
no code implementations • 28 Mar 2022 • Danfeng Wang, Xin Ma, Xiaodong Yang
Traffic light recognition, as a critical component of the perception module of self-driving vehicles, plays a vital role in the intelligent transportation systems.
no code implementations • 20 Jun 2022 • Xin Ma, Renyi Bao, Jinpeng Jiang, Yang Liu, Arthur Jiang, Jun Yan, Xin Liu, Zhisong Pan
In this work, we propose FedSSO, a server-side second-order optimization method for federated learning (FL).
no code implementations • 26 Oct 2022 • Xin Ma, Suprateek Kundu
Our estimator is designed to minimize the $L_1$ norm among all estimators belonging to suitable feasible sets, without requiring any knowledge of the noise distribution.
1 code implementation • 11 Nov 2022 • Yang Li, Xin Ma, Raj Sunderraman, Shihao Ji, Suprateek Kundu
We compare the prediction performance for different intelligence measures based on static FC, dynamic FC, and region level time series acquired from the Adolescent Brain Cognitive Development (ABCD) study involving close to 7000 individuals.
1 code implementation • 31 Dec 2022 • Xin Ma, Chang Liu, Chunyu Xie, Long Ye, Yafeng Deng, Xiangyang Ji
Masked image modeling (MIM) has shown great promise for self-supervised learning (SSL) yet been criticized for learning inefficiency.
5 code implementations • 6 May 2023 • Yaohui Wang, Xin Ma, Xinyuan Chen, Antitza Dantcheva, Bo Dai, Yu Qiao
Our key idea is to represent motion as a sequence of flow maps in the generation process, which inherently isolate motion from appearance.
1 code implementation • 15 May 2023 • Chuanxin Song, Xin Ma
Despite the remarkable success of convolutional neural networks in various computer vision tasks, recognizing indoor scenes still presents a significant challenge due to their complex composition.
Ranked #1 on Scene Recognition on MIT Indoor Scenes (10-stage average accuracy metric)
no code implementations • 22 May 2023 • Chuanxin Song, Hanbo Wu, Xin Ma, Yibin Li
Exploring the semantic context in scene images is essential for indoor scene recognition.
1 code implementation • 13 Jul 2023 • Yi Wang, Yinan He, Yizhuo Li, Kunchang Li, Jiashuo Yu, Xin Ma, Xinhao Li, Guo Chen, Xinyuan Chen, Yaohui Wang, Conghui He, Ping Luo, Ziwei Liu, Yali Wang, LiMin Wang, Yu Qiao
Specifically, we utilize a multi-scale approach to generate video-related descriptions.
no code implementations • 11 Aug 2023 • Chuanxin Song, Hanbo Wu, Xin Ma, Yibin Li
Due to the high inter-class similarity caused by the complex composition and the co-existing objects across scenes, numerous studies have explored object semantic knowledge within scenes to improve scene recognition.
2 code implementations • 26 Sep 2023 • Yaohui Wang, Xinyuan Chen, Xin Ma, Shangchen Zhou, Ziqi Huang, Yi Wang, Ceyuan Yang, Yinan He, Jiashuo Yu, Peiqing Yang, Yuwei Guo, Tianxing Wu, Chenyang Si, Yuming Jiang, Cunjian Chen, Chen Change Loy, Bo Dai, Dahua Lin, Yu Qiao, Ziwei Liu
To this end, we propose LaVie, an integrated video generation framework that operates on cascaded video latent diffusion models, comprising a base T2V model, a temporal interpolation model, and a video super-resolution model.
Ranked #4 on Text-to-Video Generation on EvalCrafter Text-to-Video (ECTV) Dataset (using extra training data)
no code implementations • 9 Oct 2023 • Xin Liu, Wei Li, Dazhi Zhan, Yu Pan, Xin Ma, Yu Ding, Zhisong Pan
Federated learning (FL) is a widely employed distributed paradigm for collaboratively training machine learning models from multiple clients without sharing local data.
no code implementations • 31 Oct 2023 • Xinyuan Chen, Yaohui Wang, Lingjun Zhang, Shaobin Zhuang, Xin Ma, Jiashuo Yu, Yali Wang, Dahua Lin, Yu Qiao, Ziwei Liu
The goal is to generate high-quality long videos with smooth and creative transitions between scenes and varying lengths of shot-level videos.
no code implementations • 10 Nov 2023 • Chuanxin Song, Hanbo Wu, Xin Ma
Leveraging object information within scenes to enhance the distinguishability of feature representations has emerged as a key approach in this domain.
2 code implementations • 5 Jan 2024 • Xin Ma, Yaohui Wang, Gengyun Jia, Xinyuan Chen, Ziwei Liu, Yuan-Fang Li, Cunjian Chen, Yu Qiao
We propose a novel Latent Diffusion Transformer, namely Latte, for video generation.
1 code implementation • 4 Mar 2024 • Lizhou Fan, Wenyue Hua, Xiang Li, Kaijie Zhu, Mingyu Jin, Lingyao Li, Haoyang Ling, Jinkui Chi, Jindong Wang, Xin Ma, Yongfeng Zhang
Understanding the reasoning capabilities of Multimodal Large Language Models (MLLMs) is an important area of research.
no code implementations • 24 Mar 2024 • Huizi Yu, Lizhou Fan, Lingyao Li, Jiayan Zhou, Zihui Ma, Lu Xian, Wenyue Hua, Sijia He, Mingyu Jin, Yongfeng Zhang, Ashvin Gandhi, Xin Ma
Large Language Models (LLMs) have rapidly become important tools in Biomedical and Health Informatics (BHI), enabling new ways to analyze data, treat patients, and conduct research.