1 code implementation • ECCV 2020 • Yanbo Fan, Baoyuan Wu, Tuanhui Li, Yong Zhang, Mingyang Li, Zhifeng Li, Yujiu Yang
Based on this factorization, we formulate the sparse attack problem as a mixed integer programming (MIP) to jointly optimize the binary selection factors and continuous perturbation magnitudes of all pixels, with a cardinality constraint on selection factors to explicitly control the degree of sparsity.
no code implementations • CCL 2020 • Chun Chen, Mingyang Li, Fang Kong
中文社交媒体命名实体识别由于其领域特殊性, 一直广受关注。非正式且无结构的微博文本存在以下两个问题:一是词语边界模糊;二是语料规模有限。针对问题一, 本文将同维度的字词进行融合, 获得丰富的文本序列表征;针对问题二, 提出了基于Star-Transformer框架的命名实体识别模型, 借助星型拓扑结构更好地捕获动态特征;同时利用高速网络优化Star-Transformer中的信息桥接, 提升模型的鲁棒性。本文提出的轻量级命名实体识别模型取得了目前Weibo语料上最好的效果。
no code implementations • 11 Feb 2025 • Wei Wu, Qiuyi Li, Mingyang Li, Kun fu, Fuli Feng, Jieping Ye, Hui Xiong, Zheng Wang
Recent developments in genomic language models have underscored the potential of LLMs in deciphering DNA sequences.
1 code implementation • 30 Jan 2025 • Mingyang Li, Michelle Kuchera, Raghuram Ramanujan, Adam Anthony, Curtis Hunt, Yassid Ayyad
Modeling detector response is a key challenge in time projection chambers.
1 code implementation • 25 Jan 2025 • Yimeng Fan, Changsong Liu, Mingyang Li, Wei zhang
However, efficiently conducting feature extraction and fusion under the spiking characteristics of SNNs for object detection remains a pressing challenge.
no code implementations • 28 Dec 2024 • Hanjing Zhou, Mingze Yin, Wei Wu, Mingyang Li, Kun fu, Jintai Chen, Jian Wu, Zheng Wang
However, these works were still unable to replicate the extraordinary success of language-supervised visual foundation models due to the ineffective usage of aligned protein-text paired data and the lack of an effective function-informed pre-training paradigm.
no code implementations • 17 Dec 2024 • Zhiyuan Chang, Mingyang Li, Xiaojun Jia, Junjie Wang, Yuekai Huang, Qing Wang, Yihao Huang, Yang Liu
Accordingly, we propose an automated CoE discrimination approach and explore LLMs' preferences from their effectiveness, faithfulness and robustness, as well as CoE's usability in a naive Retrieval-Augmented Generation (RAG) case.
1 code implementation • 13 Dec 2024 • Haowei Wang, Rupeng Zhang, Junjie Wang, Mingyang Li, Yuekai Huang, Dandan Wang, Qing Wang
To fill this gap, we present ToolCommander, a novel framework designed to exploit vulnerabilities in LLM tool-calling systems through adversarial tool injection.
no code implementations • 10 Nov 2024 • Liuyue Xie, Jiancong Guo, Laszlo A. Jeni, Zhiheng Jia, Mingyang Li, Yunwen Zhou, Chao Guo
To motivate further studies on this problem, we provide the benchmarked dataset containing real and synthetic walkable scenes captured with protective cover optical aberrations.
1 code implementation • 4 Nov 2024 • Yiheng Zhu, Jialu Wu, Qiuyi Li, Jiahuan Yan, Mingze Yin, Wei Wu, Mingyang Li, Jieping Ye, Zheng Wang, Jian Wu
To fill these gaps, we propose Bridge-IF, a generative diffusion bridge model for inverse folding, which is designed to learn the probabilistic dependency between the distributions of backbone structures and protein sequences.
no code implementations • 26 Oct 2024 • Fangwen Mu, Junjie Wang, Zhuohao Yu, Lin Shi, Song Wang, Mingyang Li, Qing Wang
In this study, we propose CodePurify, a novel defense against backdoor attacks on code models through entropy-based purification.
no code implementations • 12 Sep 2024 • MengYing Ge, Mingyang Li, Dongkai Tang, Pengbo Li, Kuo Liu, Shuhao Deng, Songbai Pu, Long Liu, Yang song, Tao Zhang
In this paper, we present our solutions for emotion recognition in the sub-challenges of Multimodal Emotion Recognition Challenge (MER2024).
no code implementations • 6 Sep 2024 • Changsong Liu, Wei zhang, Yanyan Liu, Mingyang Li, Wenlin Li, Yimeng Fan, Xiangnan Bai, Liang Zhang
We construct a U-shape encoder-decoder model named CPD-Net that successfully addresses these two issues simultaneously.
no code implementations • 21 Aug 2024 • MengYing Ge, Dongkai Tang, Mingyang Li
Multimodal emotion recognition is a task of great concern.
1 code implementation • 24 Jun 2024 • Zhiyuan Chang, Mingyang Li, Junjie Wang, Yi Liu, Qing Wang, Yang Liu
The most prominent issue among these semantic inconsistencies is catastrophic-neglect, where the images generated by T2I DMs miss key objects mentioned in the prompt.
no code implementations • 9 Jun 2024 • Changsong Liu, Yimeng Fan, Mingyang Li, Wei zhang, Yanyan Liu, Yuming Li, Wenlin Li, Liang Zhang
In the end, we propose a U-shape network named LUS-Net which is based on the SDMCM and BRM for crisp edge detection.
1 code implementation • CVPR 2024 • Yimeng Fan, Wei zhang, Changsong Liu, Mingyang Li, Wenrui Lu
Thereby, we establish state-of-the-art classification results based on SNNs, achieving 93. 7\% accuracy on the NCAR dataset.
1 code implementation • 5 Mar 2024 • Zhiyuan Chang, Mingyang Li, Junjie Wang, Cheng Li, Qing Wang
Visual entailment (VE) is a multimodal reasoning task consisting of image-sentence pairs whereby a promise is defined by an image, and a hypothesis is described by a sentence.
no code implementations • 2 Mar 2024 • Zhiyuan Chang, Mingyang Li, Junjie Wang, Cheng Li, Boyu Wu, Fanjiang Xu, Qing Wang
To this end, we propose PEELING, a text perturbation approach via image-aware property reduction for adversarial testing of the VG model.
no code implementations • 29 Feb 2024 • Mingyang Li, Maoqin Yuan, Luyao Li, Han Pengsihua
This study discusses a new method combining image steganography technology with Natural Language Processing (NLP) large models, aimed at improving the accuracy and robustness of extracting steganographic text.
no code implementations • 14 Feb 2024 • Zhiyuan Chang, Mingyang Li, Yi Liu, Junjie Wang, Qing Wang, Yang Liu
With the development of LLMs, the security threats of LLMs are getting more and more attention.
no code implementations • 13 Feb 2024 • Mingyang Li, Hongyu Liu, Yixuan Li, Zejun Wang, Yuan Yuan, Honglin Dai
Overall, this study successfully overcomes the challenge of missing data and provides valuable insights into early detection of Alzheimer's disease, demonstrating its unique research value and practical significance.
1 code implementation • 23 Jan 2024 • Mingyang Li, Yue Ma, Qinru Qiu
This approach enables the creation of a semantic map of the environment and ensures reliable camera localization.
no code implementations • 3 Jan 2024 • Xingxing Zuo, Pouya Samangouei, Yunwen Zhou, Yan Di, Mingyang Li
This is achieved by distilling feature maps generated from image-based foundation models into those rendered from our 3D model.
1 code implementation • 23 Nov 2023 • Zhenfei Zhang, Mingyang Li, Ming-Ching Chang
Existing Image Manipulation Detection (IMD) methods are mainly based on detecting anomalous features arisen from image editing or double compression artifacts.
no code implementations • 18 Feb 2023 • Xili Dai, Ke Chen, Shengbang Tong, Jingyuan Zhang, Xingjian Gao, Mingyang Li, Druv Pai, Yuexiang Zhai, Xiaojun Yuan, Heung-Yeung Shum, Lionel M. Ni, Yi Ma
Our method is arguably the first to demonstrate that a concatenation of multiple convolution sparse coding/decoding layers leads to an interpretable and effective autoencoder for modeling the distribution of large-scale natural image datasets.
no code implementations • 18 Feb 2023 • Yanci Zhang, Mengjia Xia, Mingyang Li, Haitao Mao, Yutong Lu, Yupeng Lan, Jinlin Ye, Rui Dai
With the segmented Item sections, NLP techniques can directly apply on those Item sections related to downstream tasks.
1 code implementation • 30 Oct 2022 • Shengbang Tong, Xili Dai, Yubei Chen, Mingyang Li, Zengyi Li, Brent Yi, Yann Lecun, Yi Ma
This paper proposes an unsupervised method for learning a unified representation that serves both discriminative and generative purposes.
1 code implementation • 24 Oct 2022 • Xili Dai, Mingyang Li, Pengyuan Zhai, Shengbang Tong, Xingjian Gao, Shao-Lun Huang, Zhihui Zhu, Chong You, Yi Ma
We show that such models have equally strong empirical performance on CIFAR-10, CIFAR-100, and ImageNet datasets when compared to conventional neural networks.
1 code implementation • 3 Aug 2022 • Xiangrui Zhao, Sheng Yang, Tianxin Huang, Jun Chen, Teng Ma, Mingyang Li, Yong liu
To repetitively extract them as features and perform association between discrete LiDAR frames for registration, we propose the first learning-based feature segmentation and description model for 3D lines in LiDAR point cloud.
1 code implementation • 8 Mar 2022 • Jiajun Fei, Ziyu Zhu, Wenlei Liu, Zhidong Deng, Mingyang Li, Huanjun Deng, Shuo Zhang
We strictly prove that any permutation-invariant function implemented by DuMLP-Pin can be decomposed into two or more permutation-equivariant ones in a dot-product way as the cardinality of the given input set is greater than a threshold.
no code implementations • 2 Mar 2022 • Xiaqing Ding, Xuecheng Xu, Sha Lu, Yanmei Jiao, Mengwen Tan, Rong Xiong, Huanjun Deng, Mingyang Li, Yue Wang
Global point cloud registration is an essential module for localization, of which the main difficulty exists in estimating the rotation globally without initial value.
1 code implementation • 11 Feb 2022 • Shengbang Tong, Xili Dai, Ziyang Wu, Mingyang Li, Brent Yi, Yi Ma
Our method is simpler than existing approaches for incremental learning, and more efficient in terms of model size, storage, and computation: it requires only a single, fixed-capacity autoencoding network with a feature space that is used for both discriminative and generative purposes.
1 code implementation • 12 Nov 2021 • Xili Dai, Shengbang Tong, Mingyang Li, Ziyang Wu, Michael Psenka, Kwan Ho Ryan Chan, Pengyuan Zhai, Yaodong Yu, Xiaojun Yuan, Heung Yeung Shum, Yi Ma
In particular, we propose to learn a closed-loop transcription between a multi-class multi-dimensional data distribution and a linear discriminative representation (LDR) in the feature space that consists of multiple independent multi-dimensional linear subspaces.
no code implementations • 21 Oct 2021 • Wenzheng Hu, Zhengping Che, Ning Liu, Mingyang Li, Jian Tang, ChangShui Zhang, Jianqiang Wang
Deep convolutional neural networks are shown to be overkill with high parametric and computational redundancy in many application scenarios, and an increasing number of works have explored model pruning to obtain lightweight and efficient networks.
no code implementations • 26 Mar 2021 • Ming Zhang, Mingming Zhang, Yiming Chen, Mingyang Li
In this work, we propose a novel method for performing inertial aided navigation, by using deep neural networks (DNNs).
no code implementations • IWSLT (ACL) 2022 • Di wu, Liang Ding, Shuo Yang, Mingyang Li
Recently, the performance of the neural word alignment models has exceeded that of statistical models.
1 code implementation • 6 Aug 2020 • Mingyang Li, Louis Hickman, Louis Tay, Lyle Ungar, Sharath Chandra Guntuku
We study the linguistic features associated with politeness across US English and Mandarin Chinese.
Social and Information Networks Computers and Society
no code implementations • 30 Jul 2020 • Xinru Yang, Haozhi Qi, Mingyang Li, Alexander Hauptmann
Facial image retrieval plays a significant role in forensic investigations where an untrained witness tries to identify a suspect from a massive pool of images.
no code implementations • ECCV 2020 • Boren Li, Po-Yu Zhuang, Jian Gu, Mingyang Li, Ping Tan
As for the proposed method, we first train a foreground encoder to learn representations of interchangeable foregrounds.
1 code implementation • 9 Jun 2020 • Yafei Song, Ling Cai, Jia Li, Yonghong Tian, Mingyang Li
Researchers have attempted utilizing deep neural network (DNN) to learn novel local features from images inspired by its recent successes on a variety of vision tasks.
no code implementations • 1 Jun 2020 • Zequn Wang, Mingyang Li
Conventional uncertainty quantification methods usually lacks the capability of dealing with high-dimensional problems due to the curse of dimensionality.
no code implementations • 27 May 2020 • Hongwei Xie, Shuo Zhang, Huanghao Ding, Yafei Song, Baitao Shao, Conggang Hu, Ling Cai, Mingyang Li
The inherent heavy computation of deep neural networks prevents their widespread applications.
1 code implementation • CVPR 2020 • Yongjian Chen, Lei Tai, Kai Sun, Mingyang Li
Monocular 3D object detection is an essential component in autonomous driving while challenging to solve, especially for those occluded samples which are only partially visible.
Ranked #11 on
Vehicle Pose Estimation
on KITTI Cars Hard
no code implementations • 16 Jan 2020 • Hongwei Xie, Jiafang Wang, Baitao Shao, Jian Gu, Mingyang Li
Finally, we provide a variety of experimental results to show that the proposed framework is able to achieve state-of-the-art accuracy with significantly reduced computational cost, which are the key properties for enabling real-time applications in low-cost commercial devices such as mobile devices and AR/VR headsets.
no code implementations • 13 Nov 2019 • Xingxing Zuo, Mingming Zhang, Yiming Chen, Yong liu, Guoquan Huang, Mingyang Li
While visual localization or SLAM has witnessed great progress in past decades, when deploying it on a mobile robot in practice, few works have explicitly considered the kinematic (or dynamic) constraints of the real robotic system when designing state estimators.
1 code implementation • 14 Sep 2019 • Yi Sun, Xushen Han, Kai Sun, Boren Li, Yongjiang Chen, Mingyang Li
Combined with high-level semantics, Sem-LS is more robust under cluttered environment compared with existing line-shaped representations.
no code implementations • 8 Sep 2019 • Mingming Zhang, Xingxing Zuo, Yiming Chen, Yong liu, Mingyang Li
In this paper, we focus on motion estimation dedicated for non-holonomic ground robots, by probabilistically fusing measurements from the wheel odometer and exteroceptive sensors.
no code implementations • ICCV 2019 • Boren Li, Boyu Zhuang, Mingyang Li, Jian Gu
The framework, called Seq-SG2SL, derives sequence proxies for the two modality and a Transformer-based seq-to-seq model learns to transduce one into the other.
no code implementations • 3 Aug 2019 • Yafei Song, Di Zhu, Jia Li, Yonghong Tian, Mingyang Li
For better performance, the features used for open-loop localization are required to be short-term globally static, and the ones used for re-localization or loop closure detection need to be long-term static.
1 code implementation • 4 Apr 2019 • Sharath Chandra Guntuku, Mingyang Li, Louis Tay, Lyle H. Ungar
Global acceptance of Emojis suggests a cross-cultural, normative use of Emojis.
no code implementations • 19 Feb 2019 • Yafei Song, Yonghong Tian, Gang Wang, Mingyang Li
To tackle this problem, we resort to the motion flow between adjacent maps, as motion flow is a powerful tool to process and analyze the dynamic data, which is named optical flow in video processing.