no code implementations • ECCV 2020 • Zhipeng Fan, Jun Liu, Yao Wang
A novel model, called Adaptive Computationally Efficient (ACE) network, is proposed, which takes advantage of a Gaussian kernel based Gate Module to dynamically switch the computation between a light model and a heavy network for feature extraction.
no code implementations • ECCV 2020 • Liang Chen, Faming Fang, Jiawei Zhang, Jun Liu, Guixu Zhang
Even a small amount of outliers can dramatically degrade the quality of the estimated blur kernel, because the outliers are not conforming to the linear formation of the blurring process.
no code implementations • ECCV 2020 • Tianjiao Li, Jun Liu, Wei zhang, Ling-Yu Duan
In this paper, we propose a novel Hardness-AwaRe Discrimination Network (HARD-Net) to specifically investigate the relationships between the similar activity pairs that are hard to be discriminated.
Ranked #6 on Skeleton Based Action Recognition on UAV-Human
no code implementations • ECCV 2020 • Yujun Cai, Lin Huang, Yiwei Wang, Tat-Jen Cham, Jianfei Cai, Junsong Yuan, Jun Liu, Xu Yang, Yiheng Zhu, Xiaohui Shen, Ding Liu, Jing Liu, Nadia Magnenat Thalmann
Last, in order to incorporate a general motion space for high-quality prediction, we build a memory-based dictionary, which aims to preserve the global motion patterns in training data to guide the predictions.
no code implementations • ECCV 2020 • Siyuan Yang, Jun Liu, Shijian Lu, Meng Hwa Er, Alex C. Kot
The proposed network exploits joint-aware features that are crucial for both tasks, with which gesture recognition and 3D hand pose estimation boost each other to learn highly discriminative features and models.
no code implementations • 29 May 2024 • Fangzhi Xu, Qika Lin, Tianzhe Zhao, Jiawei Han, Jun Liu
In particular, we propose a path-attention module to joint model in-atom and cross-atom relations with the high-order diffusion strategy.
no code implementations • 24 May 2024 • Haoxuan Qu, Zhaoyang He, Zeyu Hu, Yujun Cai, Jun Liu
Extensive experiments demonstrate the efficacy of our proposed framework.
no code implementations • 24 May 2024 • Jun Liu, Chaoyun Zhang, Jiaxu Qian, Minghua Ma, Si Qin, Chetan Bansal, QIngwei Lin, Saravan Rajmohan, Dongmei Zhang
Time series anomaly detection (TSAD) plays a crucial role in various industries by identifying atypical patterns that deviate from standard trends, thereby maintaining system integrity and enabling prompt response measures.
no code implementations • 24 May 2024 • Haoxuan Qu, Zhuoling Li, Hossein Rahmani, Yujun Cai, Jun Liu
Recently, Gaussian Splatting, a method that represents a 3D scene as a collection of Gaussian distributions, has gained significant attention in addressing the task of novel view synthesis.
no code implementations • 21 May 2024 • Jia Gong, Shenyu Ji, Lin Geng Foo, Kang Chen, Hossein Rahmani, Jun Liu
To generate high-quality garments for each layer, we introduce a coarse-to-fine strategy for diverse garment generation and a novel dual-SDS loss function to maintain coherence between the generated garments and avatar components, including the human body and other garments.
no code implementations • 18 May 2024 • Duo Peng, Qiuhong Ke, Jun Liu
Text-to-Image (T2I) models have raised security concerns due to their potential to generate inappropriate or harmful images.
no code implementations • 8 May 2024 • Tianzhe Zhao, Jiaoyan Chen, Yanchi Ru, Qika Lin, Yuxia Geng, Jun Liu
In this work, we explore untargeted attacks with the aim of reducing the global performances of KGE methods over a set of unknown test triples and conducting systematic analyses on KGE robustness.
1 code implementation • 24 Apr 2024 • Junfeng Tian, Rui Wang, Cong Li, Yudong Zhou, Jun Liu, Jun Wang
This report details the development and key achievements of our latest language model designed for custom large language models.
1 code implementation • 18 Apr 2024 • Jie Ma, Min Hu, Pinghui Wang, Wangchun Sun, Lingyun Song, Hongbin Pei, Jun Liu, Youtian Du
The former leads to a large, diverse test space, while the latter results in a comprehensive robustness evaluation on rare, frequent, and overall questions.
Audio-visual Question Answering Audio-Visual Question Answering (AVQA) +3
no code implementations • 3 Apr 2024 • Hanxuan Wang, Na Lu, Zixuan Wang, Jiacheng Liu, Jun Liu
TSA-ENRT utilizes an expert guiding nonlinear regression tree to approximate the neural network prediction and the neural network can be explained by the interpretive rules generated by the tree model.
no code implementations • 1 Apr 2024 • Lin Geng Foo, Tianjiao Li, Hossein Rahmani, Jun Liu
Action detection aims to localize the starting and ending points of action instances in untrimmed videos, and predict the classes of those instances.
no code implementations • 1 Apr 2024 • Jia Gong, Lin Geng Foo, Yixuan He, Hossein Rahmani, Jun Liu
Sign Language Translation (SLT) is a challenging task that aims to translate sign videos into spoken language.
Ranked #1 on Gloss-free Sign Language Translation on PHOENIX14T
Gloss-free Sign Language Translation Sign Language Translation +1
no code implementations • 31 Mar 2024 • Haoxuan Qu, Yujun Cai, Jun Liu
Motivated by this, we propose a novel LLM-AR framework, in which we investigate treating the Large Language Model as an Action Recognizer.
1 code implementation • 26 Mar 2024 • Amartya Mukherjee, Thanin Quartz, Jun Liu
This paper presents a novel approach to generating stabilizing controllers for a large class of dynamical systems using diffusion models.
no code implementations • 26 Mar 2024 • Mohammad Aali, Jun Liu
This uncertainty results in piecewise residuals for each switching surface, impacting the CLF and CBF constraints.
no code implementations • 22 Mar 2024 • Haoxuan Qu, Ziyan Guo, Jun Liu
Recently, while text-driven human motion generation has received massive research attention, most existing text-driven motion generators are generally only designed to generate motion sequences in a blank background.
1 code implementation • NeurIPS 2022 • Xi Jiang, Ying Chen, Qiang Nie, Yong liu, Jianlin Liu, Bin-Bin Gao, Jun Liu, Chengjie Wang, Feng Zheng
Noise discriminators are utilized to generate outlier scores for patch-level noise elimination before coreset construction.
no code implementations • 16 Mar 2024 • Jun Liu, Chao Wu, Changdi Yang, Hao Tang, Zhenglun Kong, Geng Yuan, Wei Niu, Dong Huang, Yanzhi Wang
Large language models (LLMs) have become crucial for many generative downstream tasks, leading to an inevitable trend and significant challenge to deploy them efficiently on resource-constrained devices.
1 code implementation • 15 Mar 2024 • Jun Liu, Yiming Meng, Maxwell Fitzsimmons, Ruikun Zhou
While there has been increasing interest in using neural networks to compute Lyapunov functions, verifying that these functions satisfy the Lyapunov conditions and certifying stability regions remain challenging due to the curse of dimensionality.
no code implementations • 15 Mar 2024 • Hang Zhang, Wenxiao Zhang, Haoxuan Qu, Jun Liu
Human-centered dynamic scene understanding plays a pivotal role in enhancing the capability of robotic and autonomous systems, in which Video-based Human-Object Interaction (V-HOI) detection is a crucial task in semantic scene understanding, aimed at comprehensively understanding HOI relationships within a video to benefit the behavioral decisions of mobile robots and autonomous driving systems.
no code implementations • 15 Mar 2024 • Jun Liu, Yiming Meng, Maxwell Fitzsimmons, Ruikun Zhou
In this paper, we describe a lightweight Python framework that provides integrated learning and verification of neural Lyapunov functions for stability analysis.
no code implementations • 14 Mar 2024 • Xinnan Zhang, Yuanbo Cheng, Xiaolei Shang, Jun Liu
The Cram{\'e}r-Rao bound (CRB) with the antenna-varying threshold is obtained.
no code implementations • 14 Mar 2024 • Mohammad Aali, Jun Liu
However, the effectiveness of CBFs is closely tied to the system model.
no code implementations • 9 Mar 2024 • QiHao Zhao, Yalun Dai, Hao Li, Wei Hu, Fan Zhang, Jun Liu
Long-tail recognition is challenging because it requires the model to learn good representations from tail categories and address imbalances across all categories.
no code implementations • 8 Mar 2024 • Zichong Meng, Changdi Yang, Jun Liu, Hao Tang, Pu Zhao, Yanzhi Wang
In response to this challenge, our study introduces a novel image editing framework with enhanced generalization robustness by boosting in-context learning capability and unifying language instruction.
no code implementations • 28 Feb 2024 • Lanyun Zhu, Deyi Ji, Tianrun Chen, Peng Xu, Jieping Ye, Jun Liu
Despite achieving rapid developments and with widespread applications, Large Vision-Language Models (LVLMs) confront a serious challenge of being prone to generating hallucinations.
no code implementations • 26 Feb 2024 • Xiang Chen, Faqiang Wang, Jun Liu, Li Cui
The algorithm (1) converges to the true solution of UOT, (2) has theoretical guarantees and robust regularization parameter selection, (3) mitigates numerical stability issues, and (4) can achieve comparable computational complexity to the Scaling algorithm in specific practice.
no code implementations • 15 Feb 2024 • Yiming Meng, Ruikun Zhou, Amartya Mukherjee, Maxwell Fitzsimmons, Christopher Song, Jun Liu
We provide a theoretical analysis of both algorithms in terms of convergence of neural approximations towards the true optimal solutions in a general setting.
no code implementations • 13 Feb 2024 • Amartya Mukherjee, Melissa M. Stadt, Lena Podina, Mohammad Kohandel, Jun Liu
Equivalently, we present an approach to restore the solution and the parameters in the Poisson equation by exploiting the eigenvalues and the eigenfunctions of the Laplacian operator.
no code implementations • 7 Feb 2024 • Lei Wang, Jun Liu, Liang Zheng, Tom Gedeon, Piotr Koniusz
For a support sequence, we match it with view-simulated query sequences, as in the popular Dynamic Time Warping (DTW).
1 code implementation • 6 Feb 2024 • Yuxu Lu, Dong Yang, Yuan Gao, Ryan Wen Liu, Jun Liu, Yu Guo
Additionally, we suggest a multi-receptive field extraction module (MEM) to attenuate the loss of image texture details caused by GC nonlinear and OLS linear transformations.
no code implementations • 31 Jan 2024 • Weixing Liu, Jun Liu, Xin Su, Han Nie, Bin Luo
To address this challenge, we propose a practical source-free object detection (SFOD) setting for RS images, which aims to perform target domain adaptation using only the source pre-trained model.
no code implementations • 14 Jan 2024 • Pengfei Wang, Xiaofei Hui, Beijia Lu, Nimrod Lilith, Jun Liu, Sameer Alam
Stereo matching neural networks often involve a Siamese structure to extract intermediate features from left and right images.
no code implementations • 12 Jan 2024 • Jiaxin Wang, Lingling Zhang, Jun Liu, Tianlin Guo, Wenjun Wu
The key challenges of GRD are how to mitigate the serious model biases caused by labeled pre-defined relations to learn effective relational representations and how to determine the specific semantics of novel relations during classifying or clustering unlabeled instances.
no code implementations • 8 Jan 2024 • Shulin Zeng, Jun Liu, Guohao Dai, Xinhao Yang, Tianyu Fu, Hongyi Wang, Wenheng Ma, Hanbo Sun, Shiyao Li, Zixiao Huang, Yadong Dai, Jintao Li, Zehao Wang, Ruoyu Zhang, Kairui Wen, Xuefei Ning, Yu Wang
However, existing GPU and transformer-based accelerators cannot efficiently process compressed LLMs, due to the following unresolved challenges: low computational efficiency, underutilized memory bandwidth, and large compilation overheads.
1 code implementation • 3 Jan 2024 • Haopeng Li, Andong Deng, Qiuhong Ke, Jun Liu, Hossein Rahmani, Yulan Guo, Bernt Schiele, Chen Chen
Reasoning over sports videos for question answering is an important task with numerous applications, such as player training and information retrieval.
no code implementations • 31 Dec 2023 • Hao liu, Jun Liu, Raymond Chan, Xue-Cheng Tai
In this study, our goal is to integrate classical mathematical models with deep neural networks by introducing two novel deep neural network models for image segmentation known as Double-well Nets.
no code implementations • 29 Dec 2023 • Li Xu, Haoxuan Qu, Yujun Cai, Jun Liu
Estimating the 6D object pose from a single RGB image often involves noise and indeterminacy due to challenges such as occlusions and cluttered backgrounds.
no code implementations • 20 Dec 2023 • Chuanzheng Wang, Yiming Meng, Jun Liu, Stephen Smith
Control barrier functions are widely used to synthesize safety-critical controls.
no code implementations • 18 Dec 2023 • Jinxiang Lai, Wenlong Wu, Bin-Bin Gao, Jun Liu, Jiawei Zhan, Congchong Nie, Yi Zeng, Chengjie Wang
Image matching and object detection are two fundamental and challenging tasks, while many related applications consider them two individual tasks (i. e. task-individual).
1 code implementation • 14 Dec 2023 • Kian Eng Ong, Sivaji Retta, Ramarajulu Srinivasan, Shawn Tan, Jun Liu
Cattle farming is one of the important and profitable agricultural industries.
no code implementations • 14 Dec 2023 • Jun Liu, Yiming Meng, Maxwell Fitzsimmons, Ruikun Zhou
We provide a systematic investigation of using physics-informed neural networks to compute Lyapunov functions.
1 code implementation • 12 Dec 2023 • Guangfeng Jiang, Jun Liu, Yuzhi Wu, Wenlong Liao, Tao He, Pai Peng
Instance segmentation is a fundamental research in computer vision, especially in autonomous driving.
no code implementations • 28 Nov 2023 • Lanyun Zhu, Tianrun Chen, Deyi Ji, Jieping Ye, Jun Liu
This paper proposes LLaFS, the first attempt to leverage large language models (LLMs) in few-shot segmentation.
no code implementations • 28 Nov 2023 • Jinhao Li, Shiyao Li, Jiaming Xu, Shan Huang, Yaoxiu Lian, Jun Liu, Yu Wang, Guohao Dai
Weights are quantized by groups, while the ranges of weights are large in some groups, resulting in large quantization errors and nonnegligible accuracy loss (e. g. >3% for Llama2-7b with 2-bit quantization in GPTQ and Greenbit).
no code implementations • 24 Nov 2023 • Yuheng Xue, Nenglun Chen, Jun Liu, Wenyun Sun
The main idea of our approach is to explore the natural relationship between multi-view correspondences and the prompt mechanism of foundational models and build bridges on it.
no code implementations • 16 Nov 2023 • Ziyan Guo, Li Xu, Jun Liu
The rapid progress of Large Models (LMs) has recently revolutionized various fields of deep learning with remarkable grades, ranging from Natural Language Processing (NLP) to Computer Vision (CV).
no code implementations • 15 Nov 2023 • Fangzhi Xu, Zhiyong Wu, Qiushi Sun, Siyu Ren, Fei Yuan, Shuai Yuan, Qika Lin, Yu Qiao, Jun Liu
Although Large Language Models (LLMs) demonstrate remarkable ability in processing and generating human-like text, they do have limitations when it comes to comprehending and expressing world knowledge that extends beyond the boundaries of natural language(e. g., chemical molecular formula).
no code implementations • 10 Nov 2023 • Zhengliang Liu, Hanqi Jiang, Tianyang Zhong, Zihao Wu, Chong Ma, Yiwei Li, Xiaowei Yu, Yutong Zhang, Yi Pan, Peng Shu, Yanjun Lyu, Lu Zhang, Junjie Yao, Peixin Dong, Chao Cao, Zhenxiang Xiao, Jiaqi Wang, Huan Zhao, Shaochen Xu, Yaonai Wei, Jingyuan Chen, Haixing Dai, Peilong Wang, Hao He, Zewei Wang, Xinyu Wang, Xu Zhang, Lin Zhao, Yiheng Liu, Kai Zhang, Liheng Yan, Lichao Sun, Jun Liu, Ning Qiang, Bao Ge, Xiaoyan Cai, Shijie Zhao, Xintao Hu, Yixuan Yuan, Gang Li, Shu Zhang, Xin Zhang, Xi Jiang, Tuo Zhang, Dinggang Shen, Quanzheng Li, Wei Liu, Xiang Li, Dajiang Zhu, Tianming Liu
GPT-4V represents a breakthrough in artificial general intelligence (AGI) for computer vision, with applications in the biomedical domain.
no code implementations • 2 Nov 2023 • Ke Hong, Guohao Dai, Jiaming Xu, Qiuli Mao, Xiuhong Li, Jun Liu, Kangdi Chen, Yuhan Dong, Yu Wang
A single and static dataflow may lead to a 50. 25% performance loss for GEMMs of different shapes in LLM inference.
no code implementations • 25 Oct 2023 • Xiaohui Zhong, Lei Chen, Jun Liu, Chensen Lin, Yuan Qi, Hao Li
State-of-the-art ML-based weather forecast models, such as FuXi, have demonstrated superior statistical forecast performance in comparison to the high-resolution forecasts (HRES) of the European Centre for Medium-Range Weather Forecasts (ECMWF).
1 code implementation • 19 Oct 2023 • Jun Liu, Jiantao Zhou, Jinyu Tian, Weiwei Sun
Extensive experiments demonstrate that 1) the classification accuracy of the classifier trained in the plaintext domain remains the same in both the ciphertext and plaintext domains; 2) the encrypted images can be recovered into their original form with an average PSNR of up to 51+ dB for the SVHN dataset and 48+ dB for the VGGFace2 dataset; 3) our system exhibits satisfactory generalization capability on the encryption, decryption and classification tasks across datasets that are different from the training one; and 4) a high-level of security is achieved against three potential threat models.
1 code implementation • 19 Oct 2023 • Jun Liu, Jiantao Zhou, Haiwei Wu, Weiwei Sun, Jinyu Tian
In this work, we aim to design a new framework for generating robust AEs that can survive the OSN transmission; namely, the AEs before and after the OSN transmission both possess strong attack capabilities.
no code implementations • 17 Oct 2023 • Shuanglin Yan, Neng Dong, Jun Liu, Liyan Zhang, Jinhui Tang
Since the support set is unavailable during inference, we propose to distill the knowledge learned by the "richer" model into a lightweight model for inference with a single image/text as input.
no code implementations • 14 Oct 2023 • Yutian Lei, Jun Liu, Dong Huang
The flourishing success of Deep Neural Networks(DNNs) on RGB-input perception tasks has opened unbounded possibilities for non-RGB-input perception tasks, such as object detection from wireless signals, lidar scans, and infrared images.
no code implementations • 8 Oct 2023 • Tianyang Zhong, Wei Zhao, Yutong Zhang, Yi Pan, Peixin Dong, Zuowei Jiang, Xiaoyan Kui, Youlan Shang, Li Yang, Yaonai Wei, Longtao Yang, Hao Chen, Huan Zhao, Yuxiao Liu, Ning Zhu, Yiwei Li, Yisong Wang, Jiaqi Yao, Jiaqi Wang, Ying Zeng, Lei He, Chao Zheng, Zhixue Zhang, Ming Li, Zhengliang Liu, Haixing Dai, Zihao Wu, Lu Zhang, Shu Zhang, Xiaoyan Cai, Xintao Hu, Shijie Zhao, Xi Jiang, Xin Zhang, Xiang Li, Dajiang Zhu, Lei Guo, Dinggang Shen, Junwei Han, Tianming Liu, Jun Liu, Tuo Zhang
Radiology report generation, as a key step in medical image analysis, is critical to the quantitative analysis of clinically informed decision-making levels.
no code implementations • 4 Oct 2023 • Amartya Mukherjee, Ruikun Zhou, Haocheng Chang, Jun Liu
This paper introduces harmonic control Lyapunov barrier functions (harmonic CLBF) that aid in constrained control problems such as reach-avoid problems.
1 code implementation • 29 Sep 2023 • Qian Wu, Si Yong Yeo, Yufei Chen, Jun Liu
Accurate localization of cephalometric landmarks holds great importance in the fields of orthodontics and orthognathics due to its potential for automating key point labeling.
1 code implementation • NeurIPS 2023 • Haoxuan Qu, Xiaofei Hui, Yujun Cai, Jun Liu
Open-set object recognition aims to identify if an object is from a class that has been encountered during training or not.
no code implementations • 12 Sep 2023 • Di Guo, Sijin Li, Jun Liu, Zhangren Tu, Tianyu Qiu, Jingjing Xu, Liubin Feng, Donghai Lin, Qing Hong, Meijin Lin, Yanqin Lin, Xiaobo Qu
Particularly, the emerging deep learning tools is hard to be widely used in NMR due to the sophisticated setup of computation.
no code implementations • 4 Sep 2023 • Yuqin Li, Jun Liu, Shengliang Zhong, Licheng Zhou, Shoubin Dong, Zejia Liu, Liqun Tang
In this paper, a deep learning based overloaded vehicle identification approach (DOVI) is proposed, with the purpose of overloaded vehicle identification for long-span bridges by the use of structural health monitoring data.
no code implementations • 29 Aug 2023 • Zhengliang Liu, Yiwei Li, Peng Shu, Aoxiao Zhong, Longtao Yang, Chao Ju, Zihao Wu, Chong Ma, Jie Luo, Cheng Chen, Sekeun Kim, Jiang Hu, Haixing Dai, Lin Zhao, Dajiang Zhu, Jun Liu, Wei Liu, Dinggang Shen, Tianming Liu, Quanzheng Li, Xiang Li
This paper introduces Radiology-Llama2, a large language model specialized for radiology through a process known as instruction tuning.
no code implementations • 27 Aug 2023 • Lin Geng Foo, Hossein Rahmani, Jun Liu
Due to its wide range of applications and the demonstrated potential of recent works, AIGC developments have been attracting lots of attention recently, and AIGC methods have been developed for various data modalities, such as image, video, text, 3D shape (as voxels, point clouds, meshes, and neural implicit fields), 3D scene, 3D human avatar (body and head), 3D motion, and audio -- each presenting different characteristics and challenges.
no code implementations • 26 Aug 2023 • Duo Peng, Qiuhong Ke, Yinjie Lei, Jun Liu
Unsupervised Domain Adaptation (UDA) is quite challenging due to the large distribution discrepancy between the source domain and the target domain.
no code implementations • 25 Aug 2023 • Mei-Yuh Hwang, Yangyang Shi, Ankit Ramchandani, Guan Pang, Praveen Krishnan, Lucas Kabela, Frank Seide, Samyak Datta, Jun Liu
This paper discusses the challenges of optical character recognition (OCR) on natural scenes, which is harder than OCR on documents due to the wild content and various image backgrounds.
no code implementations • ICCV 2023 • Lin Geng Foo, Jia Gong, Hossein Rahmani, Jun Liu
Inspired by their capability, we explore a diffusion-based approach for human mesh recovery, and propose a Human Mesh Diffusion (HMDiff) framework which frames mesh recovery as a reverse diffusion process.
no code implementations • ICCV 2023 • Duo Peng, Ping Hu, Qiuhong Ke, Jun Liu
Translating images from a source domain to a target domain for learning target models is one of the most common strategies in domain adaptive semantic segmentation (DASS).
1 code implementation • ICCV 2023 • QiHao Zhao, Chen Jiang, Wei Hu, Fan Zhang, Jun Liu
In the analysis and ablation study, we demonstrate that our method compared with previous work can effectively increase the diversity of experts, significantly reduce the variance of the model, and improve recognition accuracy.
Ranked #5 on Long-tail Learning on CIFAR-10-LT (ρ=50)
no code implementations • ICCV 2023 • Lanyun Zhu, Tianrun Chen, Jianxiong Yin, Simon See, Jun Liu
We innovatively utilize Gabor filters as a powerful extractor to exploit texture features, motivated by the capability of Gabor filters in effectively capturing multi-frequency features and detailed local information.
no code implementations • 6 Aug 2023 • Hao Tang, Jun Liu, Shuanglin Yan, Rui Yan, Zechao Li, Jinhui Tang
Due to the scarcity of manually annotated data required for fine-grained video understanding, few-shot fine-grained (FS-FG) action recognition has gained significant attention, with the aim of classifying novel fine-grained action categories with only a few labeled instances.
1 code implementation • 25 Jul 2023 • Zhengliang Liu, Tianyang Zhong, Yiwei Li, Yutong Zhang, Yi Pan, Zihao Zhao, Peixin Dong, Chao Cao, Yuxiao Liu, Peng Shu, Yaonai Wei, Zihao Wu, Chong Ma, Jiaqi Wang, Sheng Wang, Mengyue Zhou, Zuowei Jiang, Chunlin Li, Jason Holmes, Shaochen Xu, Lu Zhang, Haixing Dai, Kai Zhang, Lin Zhao, Yuanhao Chen, Xu Liu, Peilong Wang, Pingkun Yan, Jun Liu, Bao Ge, Lichao Sun, Dajiang Zhu, Xiang Li, Wei Liu, Xiaoyan Cai, Xintao Hu, Xi Jiang, Shu Zhang, Xin Zhang, Tuo Zhang, Shijie Zhao, Quanzheng Li, Hongtu Zhu, Dinggang Shen, Tianming Liu
The rise of large language models (LLMs) has marked a pivotal shift in the field of natural language processing (NLP).
1 code implementation • 24 Jul 2023 • Qing-Hua Zhang, Liang-Tian He, Yi-Lun Wang, Liang-Jian Deng, Jun Liu
Very recently, a quaternion-based WNNM approach (QWNNM) has been developed to mitigate this issue, which is capable of representing the color image as a whole in the quaternion domain and preserving the inherent correlation among the three color channels.
no code implementations • 21 Jul 2023 • Jie Ma, Pinghui Wang, Dechen Kong, Zewei Wang, Jun Liu, Hongbin Pei, Junzhou Zhao
Specifically, we first provide an overview of the development process of datasets from in-distribution and out-of-distribution perspectives.
no code implementations • 14 Jul 2023 • Siyuan Yang, Jun Liu, Shijian Lu, Er Meng Hwa, Alex C. Kot
The first is multi-scale matching which captures the scale-wise semantic relevance of skeleton data at multiple spatial and temporal scales simultaneously.
no code implementations • 25 Jun 2023 • Junying Meng, Weihong Guo, Jun Liu, Mingrui Yang
The main objective of image segmentation is to divide an image into homogeneous regions for further analysis.
1 code implementation • 16 Jun 2023 • Fangzhi Xu, Qika Lin, Jiawei Han, Tianzhe Zhao, Jun Liu, Erik Cambria
Firstly, to offer systematic evaluations, we select fifteen typical logical reasoning datasets and organize them into deductive, inductive, abductive and mixed-form reasoning settings.
no code implementations • 14 Jun 2023 • Zhengliang Liu, Aoxiao Zhong, Yiwei Li, Longtao Yang, Chao Ju, Zihao Wu, Chong Ma, Peng Shu, Cheng Chen, Sekeun Kim, Haixing Dai, Lin Zhao, Lichao Sun, Dajiang Zhu, Jun Liu, Wei Liu, Dinggang Shen, Xiang Li, Quanzheng Li, Tianming Liu
We introduce Radiology-GPT, a large language model for radiology.
no code implementations • 8 Jun 2023 • Xiang Li, Lu Zhang, Zihao Wu, Zhengliang Liu, Lin Zhao, Yixuan Yuan, Jun Liu, Gang Li, Dajiang Zhu, Pingkun Yan, Quanzheng Li, Wei Liu, Tianming Liu, Dinggang Shen
In this review, we explore the potential applications of Artificial General Intelligence (AGI) models in healthcare, focusing on foundational Large Language Models (LLMs), Large Vision Models, and Large Multimodal Models.
1 code implementation • 18 May 2023 • Amartya Mukherjee, Jun Liu
The Hamilton-Jacobi-Bellman (HJB) equation is a PDE that evaluates the optimality of the value function and determines an optimal controller.
1 code implementation • 6 May 2023 • Jie Ma, Pinghui Wang, Zewei Wang, Dechen Kong, Min Hu, Ting Han, Jun Liu
Question answering methods are well-known for leveraging data bias, such as the language prior in visual question answering and the position bias in machine reading comprehension (extractive question answering).
Extractive Question-Answering Machine Reading Comprehension +2
1 code implementation • 24 Apr 2023 • QiHao Zhao, Yangyu Huang, Wei Hu, Fan Zhang, Jun Liu
TransMix uses unreliable attention maps to compute mixed attention labels that can affect the model.
Ranked #1 on Data Augmentation on ImageNet
no code implementations • 20 Apr 2023 • Jinxiang Lai, Siqian Yang, JunHong Zhou, Wenlong Wu, Xiaochen Chen, Jun Liu, Bin-Bin Gao, Chengjie Wang
According to this, we propose a novel Clustered-patch Element Connection (CEC) layer to correct the mismatch problem.
Ranked #48 on Few-Shot Semantic Segmentation on COCO-20i (5-shot)
no code implementations • 18 Apr 2023 • Siyuan Yang, Jun Liu, Shijian Lu, Er Meng Hwa, Yongjian Hu, Alex C. Kot
We investigate self-supervised representation learning and design a novel skeleton cloud colorization technique that is capable of learning spatial and temporal skeleton representations from unlabeled skeleton sequence data.
no code implementations • CVPR 2023 • Lanyun Zhu, Tianrun Chen, Jianxiong Yin, Simon See, Jun Liu
Continual Semantic Segmentation (CSS) extends static semantic segmentation by incrementally introducing new classes for training.
no code implementations • CVPR 2023 • Li Xu, Mark He Huang, Xindi Shang, Zehuan Yuan, Ying Sun, Jun Liu
Then, following a novel meta optimization scheme to optimize the model to obtain good testing performance on the virtual testing sets after training on the virtual training set, our framework can effectively drive the model to better capture semantics and visual representations of individual concepts, and thus obtain robust generalization performance even when handling novel compositions.
no code implementations • CVPR 2023 • Tianjiao Li, Lin Geng Foo, Ping Hu, Xindi Shang, Hossein Rahmani, Zehuan Yuan, Jun Liu
Pre-training VTs on such corrupted data can be challenging, especially when we pre-train via the masked autoencoding approach, where both the inputs and masked ``ground truth" targets can potentially be unreliable in this case.
no code implementations • 7 Apr 2023 • Gongning Luo, Kuanquan Wang, Jun Liu, Shuo Li, Xinjie Liang, Xiangyu Li, Shaowei Gan, Wei Wang, Suyu Dong, Wenyi Wang, Pengxin Yu, Enyou Liu, Hongrong Wei, Na Wang, Jia Guo, Huiqi Li, Zhao Zhang, Ziwei Zhao, Na Gao, Nan An, Ashkan Pakzad, Bojidar Rangelov, Jiaqi Dou, Song Tian, Zeyu Liu, Yi Wang, Ampatishan Sivalingam, Kumaradevan Punithakumar, Zhaowen Qiu, Xin Gao
Efficient automatic segmentation of multi-level (i. e. main and branch) pulmonary arteries (PA) in CTPA images plays a significant role in clinical applications.
no code implementations • 1 Apr 2023 • Jianhong Pan, Lin Geng Foo, Qichen Zheng, Zhipeng Fan, Hossein Rahmani, Qiuhong Ke, Jun Liu
Dynamic neural networks can greatly reduce computation redundancy without compromising accuracy by adapting their structures based on the input.
no code implementations • 1 Apr 2023 • Jianhong Pan, Siyuan Yang, Lin Geng Foo, Qiuhong Ke, Hossein Rahmani, Zhipeng Fan, Jun Liu
Currently, salience-based channel pruning makes continuous breakthroughs in network compression.
no code implementations • CVPR 2023 • Lin Geng Foo, Jia Gong, Zhipeng Fan, Jun Liu
Recent years have witnessed great progress in deep neural networks for real-time applications.
no code implementations • 27 Mar 2023 • Xinnan Zhang, Yuanbo Cheng, Xiaolei Shang, Jun Liu
Simulation results show the validity of the asymptotic CRB and better performance under the optimal mixed-precision arrangement.
1 code implementation • 15 Mar 2023 • Jinxiang Lai, Siqian Yang, Wenlong Wu, Tao Wu, Guannan Jiang, Xi Wang, Jun Liu, Bin-Bin Gao, Wei zhang, Yuan Xie, Chengjie Wang
Then we derive two specific attention modules, named SpatialFormer Semantic Attention (SFSA) and SpatialFormer Target Attention (SFTA), to enhance the target object regions while reduce the background distraction.
no code implementations • 14 Mar 2023 • Jun Wan, Jun Liu, Jie zhou, Zhihui Lai, Linlin Shen, Hang Sun, Ping Xiong, Wenwen Min
Most facial landmark detection methods predict landmarks by mapping the input facial appearance features to landmark heatmaps and have achieved promising results.
no code implementations • 8 Mar 2023 • Yiming Meng, Jun Liu
The essential step of abstraction-based control synthesis for nonlinear systems to satisfy a given specification is to obtain a finite-state abstraction of the original systems.
no code implementations • 15 Feb 2023 • Jun Liu, Ye Yuan
We prove that various stochastic gradient descent methods, including the stochastic gradient descent (SGD), stochastic heavy-ball (SHB), and stochastic Nesterov's accelerated gradient (SNAG) methods, almost surely avoid any strict saddle manifold.
1 code implementation • 10 Feb 2023 • Yang Liu, Dingkang Yang, Yan Wang, Jing Liu, Jun Liu, Azzedine Boukerche, Peng Sun, Liang Song
Video Anomaly Detection (VAD) serves as a pivotal technology in the intelligent surveillance systems, enabling the temporal or spatial identification of anomalous events within videos.
no code implementations • 1 Feb 2023 • Amartya Mukherjee, Jun Liu
The Proximal Policy Optimization (PPO)-Clipped algorithm is improvised with this implementation as it uses a value network to compute the objective function for its policy network.
1 code implementation • 16 Jan 2023 • Xiaotong Li, Zixuan Hu, Jun Liu, Yixiao Ge, Yongxing Dai, Ling-Yu Duan
In this paper, we improve the network generalization ability by modeling domain shifts with uncertainty (DSU), i. e., characterizing the feature statistics as uncertain distributions during training.
no code implementations • 9 Jan 2023 • Xiangyu Li, Gongning Luo, Kuanquan Wang, Hongyu Wang, Jun Liu, Xinjie Liang, Jie Jiang, Zhenghao Song, Chunyue Zheng, Haokai Chi, Mingwang Xu, Yingte He, Xinghua Ma, Jingwen Guo, Yifan Liu, Chuanpu Li, Zeli Chen, Md Mahfuzur Rahman Siddiquee, Andriy Myronenko, Antoine P. Sanner, Anirban Mukhopadhyay, Ahmed E. Othman, Xingyu Zhao, Weiping Liu, Jinhuang Zhang, Xiangyuan Ma, Qinghui Liu, Bradley J. MacIntosh, Wei Liang, Moona Mazher, Abdul Qayyum, Valeriia Abramova, Xavier Lladó, Shuo Li
It is intended to resolve the above-mentioned problems and promote the development of both intracranial hemorrhage segmentation and anisotropic data processing.
no code implementations • ICCV 2023 • Ming Li, Xiangyu Xu, Hehe Fan, Pan Zhou, Jun Liu, Jia-Wei Liu, Jiahe Li, Jussi Keppo, Mike Zheng Shou, Shuicheng Yan
For the first time, we introduce vision Transformers into PPAR by treating a video as a tubelet sequence, and accordingly design two complementary mechanisms, i. e., sparsification and anonymization, to remove privacy from a spatio-temporal perspective.
1 code implementation • 8 Jan 2023 • Fangzhi Xu, Jun Liu, Qika Lin, Tianzhe Zhao, Jian Zhang, Lingling Zhang
(2) How to enhance the perception of reasoning types for the models?
no code implementations • CVPR 2023 • Haoxuan Qu, Yujun Cai, Lin Geng Foo, Ajay Kumar, Jun Liu
Therefore, via minimizing the distance between the two characteristic functions, we can optimize the model to provide a more accurate localization result for the body joints in different sub-regions of the predicted heatmap.
no code implementations • ICCV 2023 • Xudong Tian, Zhizhong Zhang, Xin Tan, Jun Liu, Chengjie Wang, Yanyun Qu, Guannan Jiang, Yuan Xie
Continual Learning (CL) is the constant development of complex behaviors by building upon previously acquired skills.
1 code implementation • ICCV 2023 • Kian Eng Ong, Xun Long Ng, Yanchao Li, Wenjie Ai, Kuangyi Zhao, Si Yong Yeo, Jun Liu
Understanding and analyzing human behaviors (actions and interactions of people), voices, and sounds in chaotic events is crucial in many applications, e. g., crowd management, emergency response services.
no code implementations • CVPR 2023 • Lin Geng Foo, Tianjiao Li, Hossein Rahmani, Qiuhong Ke, Jun Liu
We propose a Unified Pose Sequence Modeling approach to unify heterogeneous human behavior understanding tasks based on pose data, e. g., action recognition, 3D pose estimation and 3D early action prediction.
no code implementations • CVPR 2023 • Zhen Zhao, Zhizhong Zhang, Xin Tan, Jun Liu, Yanyun Qu, Yuan Xie, Lizhuang Ma
In this paper, we propose a space decoupling (SD) algorithm to decouple the feature space into a pair of complementary subspaces, i. e., the stability space I, and the plasticity space R. I is established by conducting space intersection between the historic and current feature space, and thus I contains more task-shared bases.
no code implementations • ICCV 2023 • Rui Li, Baopeng Zhang, Jun Liu, Wei Liu, Jian Zhao, Zhu Teng
HD-AMOT defines the diversified informative representation by encoding the geometric and semantic information, and formulates the frame inference strategy as a Markov decision process to learn an optimal sampling policy based on the designed informative representation.
no code implementations • CVPR 2023 • Kexin Sun, Zhineng Chen, Gongwei Wang, Jun Liu, Xiongjun Ye, Yu-Gang Jiang
In order to eliminate the square effect, we design a bi-directional feature fusion generative adversarial network (BFF-GAN) with a global branch and a local branch.
no code implementations • 29 Dec 2022 • Xin Hu, Lingling Zhang, Jun Liu, Jinfu Fan, Yang You, Yaqiang Wu
These lead to the fact that traditional data-driven detection model is not suitable for diagrams.
no code implementations • 12 Dec 2022 • Chenliang Gu, Changan Wang, Bin-Bin Gao, Jun Liu, Tianliang Zhang
Recently, density map regression-based methods have dominated in crowd counting owing to their excellent fitting ability on density distribution.
1 code implementation • CVPR 2023 • Jia Gong, Lin Geng Foo, Zhipeng Fan, Qiuhong Ke, Hossein Rahmani, Jun Liu
Monocular 3D human pose estimation is quite challenging due to the inherent ambiguity and occlusion, which often lead to high uncertainty and indeterminacy.
Ranked #11 on 3D Human Pose Estimation on MPI-INF-3DHP
no code implementations • 23 Nov 2022 • Jiawei Zhan, Jun Liu, Wei Tang, Guannan Jiang, Xi Wang, Bin-Bin Gao, Tianliang Zhang, Wenlong Wu, Wei zhang, Chengjie Wang, Yuan Xie
This paper builds a unified framework to perform effective noisy-proposal suppression and to interact between global and local features for robust feature learning.
no code implementations • 2 Nov 2022 • Jinxiang Lai, Siqian Yang, Guannan Jiang, Xi Wang, Yuxi Li, Zihui Jia, Xiaochen Chen, Jun Liu, Bin-Bin Gao, Wei zhang, Yuan Xie, Chengjie Wang
In this paper, for the first time, we investigate the contributions of different distance metrics, and propose an adaptive fusion scheme, bringing significant improvements in few-shot classification.
1 code implementation • 2 Nov 2022 • Jinxiang Lai, Siqian Yang, Wenlong Liu, Yi Zeng, Zhongyi Huang, Wenlong Wu, Jun Liu, Bin-Bin Gao, Chengjie Wang
Few-Shot Learning (FSL) alleviates the data shortage challenge via embedding discriminative target-aware features among plenty seen (base) and few unseen (novel) labeled samples.
no code implementations • 13 Oct 2022 • Haoxuan Qu, Yanchao Li, Lin Geng Foo, Jason Kuen, Jiuxiang Gu, Jun Liu
Confidence estimation, a task that aims to evaluate the trustworthiness of the model's prediction output during deployment, has received lots of research attention recently, due to its importance for the safe deployment of deep models.
1 code implementation • ACMMM 2022 • Wujin Li, Jiawei Zhan, Jinbao Wang, Bizhong Xia, Bin-Bin Gao, Jun Liu, Chengjie Wang, Feng Zheng
We believe that the proposed task and benchmark will be beneficial to the field of AD.
no code implementations • CVPR 2023 • Xiaole Tang, XiLe Zhao, Jun Liu, Jianli Wang, Yuchun Miao, Tieyong Zeng
To address this challenge, we suggest a dataset-free deep residual prior for the kernel induced error (termed as residual) expressed by a customized untrained deep neural network, which allows us to flexibly adapt to different blurs and images in real scenarios.
no code implementations • 3 Oct 2022 • Haoxuan Qu, Li Xu, Yujun Cai, Lin Geng Foo, Jun Liu
In this paper, we show that optimizing the heatmap prediction in such a way, the model performance of body joint localization, which is the intrinsic objective of this task, may not be consistently improved during the optimization process of the heatmap prediction.
no code implementations • 30 Sep 2022 • William Zou, Hans De Sterck, Jun Liu
One of the largest bottlenecks in distributed training is communicating gradients across different nodes.
no code implementations • 12 Sep 2022 • Mohammad Aali, Jun Liu
We develop a control structure based on a multiple CBFs scheme for a multi-steering tractor-trailer system to ensure a collision-free maneuver for both the tractor and trailer in the presence of several obstacles.
no code implementations • 8 Sep 2022 • Jinxiang Lai, Wenlong Liu, Jun Liu
Continual Learning (CL) focuses on developing algorithms with the ability to adapt to new environments and learn new skills.
1 code implementation • Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS 2022) 2022 • Bin-Bin Gao, Xiaochen Chen, Zhongyi Huang, Congchong Nie, Jun Liu, Jinxiang Lai, Guannan Jiang, Xi Wang, Chengjie Wang
This paper focus on few-shot object detection~(FSOD) and instance segmentation~(FSIS), which requires a model to quickly adapt to novel classes with a few labeled instances.
Ranked #3 on Few-Shot Object Detection on MS-COCO (1-shot)
no code implementations • 3 Sep 2022 • Tianjiao Li, Lin Geng Foo, Qiuhong Ke, Hossein Rahmani, Anran Wang, Jinghua Wang, Jun Liu
We design a novel Dynamic Spatio-Temporal Specialization (DSTS) module, which consists of specialized neurons that are only activated for a subset of samples that are highly similar.
no code implementations • 26 Jul 2022 • Guangchen Shi, Yirui Wu, Jun Liu, Shaohua Wan, Wenhai Wang, Tong Lu
Second, to resist overfitting issues caused by few training samples, a hyper-class embedding is learned by clustering all category embeddings for initialization and aligned with category embedding of the new class for enhancement, where learned knowledge assists to learn new knowledge, thus alleviating performance dependence on training data scale.
no code implementations • 25 Jul 2022 • Yunsheng Pang, Qiuhong Ke, Hossein Rahmani, James Bailey, Jun Liu
Human interaction recognition is very important in many applications.
Ranked #2 on Human Interaction Recognition on SBU
no code implementations • 23 Jul 2022 • Li Xu, Haoxuan Qu, Jason Kuen, Jiuxiang Gu, Jun Liu
Video scene graph generation (VidSGG) aims to parse the video content into scene graphs, which involves modeling the spatio-temporal contextual information in the video.
no code implementations • 20 Jul 2022 • Lin Geng Foo, Tianjiao Li, Hossein Rahmani, Qiuhong Ke, Jun Liu
Early action prediction aims to successfully predict the class label of an action before it is completely performed.
1 code implementation • 21 Jun 2022 • Dong Liang, Jun Liu, Kuanquan Wang, Gongning Luo, Wei Wang, Shuo Li
The morphological changes in knee cartilage (especially femoral and tibial cartilages) are closely related to the progression of knee osteoarthritis, which is expressed by magnetic resonance (MR) images and assessed on the cartilage segmentation results.
1 code implementation • 4 Jun 2022 • Ruikun Zhou, Thanin Quartz, Hans De Sterck, Jun Liu
This paper proposes a learning framework to simultaneously stabilize an unknown nonlinear system with a neural controller and learn a neural Lyapunov function to certify a region of attraction (ROA) for the closed-loop system.
no code implementations • 22 May 2022 • Chuanzheng Wang, Yiming Meng, Stephen L. Smith, Jun Liu
More specifically, we propose a data-driven stochastic control barrier function (DDSCBF) framework and use supervised learning to learn the unknown stochastic dynamics via the DDSCBF scheme.
1 code implementation • 20 May 2022 • Jiajia Chen, Xin Xin, Xianfeng Liang, Xiangnan He, Jun Liu
However, existing graph-based methods fails to consider the bias offsets of users (items).
2 code implementations • 11 May 2022 • Yawei Li, Kai Zhang, Radu Timofte, Luc van Gool, Fangyuan Kong, Mingxi Li, Songwei Liu, Zongcai Du, Ding Liu, Chenhui Zhou, Jingyi Chen, Qingrui Han, Zheyuan Li, Yingqi Liu, Xiangyu Chen, Haoming Cai, Yu Qiao, Chao Dong, Long Sun, Jinshan Pan, Yi Zhu, Zhikai Zong, Xiaoxiao Liu, Zheng Hui, Tao Yang, Peiran Ren, Xuansong Xie, Xian-Sheng Hua, Yanbo Wang, Xiaozhong Ji, Chuming Lin, Donghao Luo, Ying Tai, Chengjie Wang, Zhizhong Zhang, Yuan Xie, Shen Cheng, Ziwei Luo, Lei Yu, Zhihong Wen, Qi Wu1, Youwei Li, Haoqiang Fan, Jian Sun, Shuaicheng Liu, Yuanfei Huang, Meiguang Jin, Hua Huang, Jing Liu, Xinjian Zhang, Yan Wang, Lingshun Long, Gen Li, Yuanfan Zhang, Zuowei Cao, Lei Sun, Panaetov Alexander, Yucong Wang, Minjie Cai, Li Wang, Lu Tian, Zheyuan Wang, Hongbing Ma, Jie Liu, Chao Chen, Yidong Cai, Jie Tang, Gangshan Wu, Weiran Wang, Shirui Huang, Honglei Lu, Huan Liu, Keyan Wang, Jun Chen, Shi Chen, Yuchun Miao, Zimo Huang, Lefei Zhang, Mustafa Ayazoğlu, Wei Xiong, Chengyi Xiong, Fei Wang, Hao Li, Ruimian Wen, Zhijing Yang, Wenbin Zou, Weixin Zheng, Tian Ye, Yuncheng Zhang, Xiangzhen Kong, Aditya Arora, Syed Waqas Zamir, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Dandan Gaoand Dengwen Zhouand Qian Ning, Jingzhu Tang, Han Huang, YuFei Wang, Zhangheng Peng, Haobo Li, Wenxue Guan, Shenghua Gong, Xin Li, Jun Liu, Wanjun Wang, Dengwen Zhou, Kun Zeng, Hanjiang Lin, Xinyu Chen, Jinsheng Fang
The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29. 00dB on DIV2K validation set.
1 code implementation • CVPR 2022 • Haoxi Ran, Jun Liu, Chengjie Wang
Based on a simple baseline of PointNet++ (SSG version), Umbrella RepSurf surpasses the previous state-of-the-art by a large margin for classification, segmentation and detection on various benchmarks in terms of performance and efficiency.
Ranked #6 on 3D Point Cloud Classification on ModelNet40
2 code implementations • 9 May 2022 • Wei Dai, Rui Liu, Tianyi Wu, Min Wang, Jianqin Yin, Jun Liu
Visual features of skin lesions vary significantly because the images are collected from patients with different lesion colours and morphologies by using dissimilar imaging equipment.
1 code implementation • 2 May 2022 • Fangzhi Xu, Jun Liu, Qika Lin, Yudai Pan, Lingling Zhang
Firstly, we introduce different extraction strategies to split the text into two sets of logical units, and construct the logical graph and the syntax graph respectively.
Ranked #14 on Reading Comprehension on ReClor
1 code implementation • CVPR 2022 • Xun Long Ng, Kian Eng Ong, Qichen Zheng, Yun Ni, Si Yong Yeo, Jun Liu
More specifically, our dataset contains 50 hours of annotated videos to localize relevant animal behavior segments in long videos for the video grounding task, 30K video sequences for the fine-grained multi-label action recognition task, and 33K frames for the pose estimation task, which correspond to a diverse range of animals with 850 species across 6 major animal classes.
Ranked #2 on Action Recognition on Animal Kingdom
no code implementations • 29 Mar 2022 • Haifeng Li, Weihong Guo, Jun Liu, Li Cui, Dongxing Xie
In medical imaging for instance, intensity inhomogeneity and noise are common.
no code implementations • 18 Mar 2022 • Jun Liu, Tong Ruan, Haofen Wang, Huanhuan Zhang
The dialogue state tracking (DST) module in the medical dialogue system which interprets utterances into the machine-readable structure for downstream tasks is particularly challenging.
no code implementations • 8 Mar 2022 • Zhiyu Mou, Jun Liu, Xiang Yun, Feifei Gao, Qihui Wu
We first propose a graph attention self-supervised learning algorithm (GASSL) to detect the HUAVs of a single UAV cluster, where the GASSL can fit the IFS at the same time.
1 code implementation • 3 Mar 2022 • Yongxing Dai, Yifan Sun, Jun Liu, Zekun Tong, Yi Yang, Ling-Yu Duan
Instead of directly aligning the source and target domains against each other, we propose to align the source and target domains against their intermediate domains for a smooth knowledge transfer.
no code implementations • 28 Feb 2022 • Shengjing Tian, Jun Liu, Xiuping Liu
In this work, we investigate a more challenging task in the LiDAR point clouds, class-agnostic tracking, where a general model is supposed to be learned for any specified targets of both observed and unseen categories.
no code implementations • 21 Feb 2022 • Jun Liu, Haitao Zhao, Dongtang Ma, Kai Mei, Jibo Wei
In this paper, we aim to quantitatively analyze why DNNs can achieve comparable performance in the physical layer comparing with traditional techniques, and also drive their cost in terms of computational complexity.
no code implementations • 9 Feb 2022 • Jun Liu, Ye Yuan
We further provide last-iterate almost sure convergence rates analysis for stochastic gradient methods on weakly convex smooth functions, in contrast with most existing results in the literature that only provide convergence in expectation for a weighted average of the iterates.
1 code implementation • ICLR 2022 • Xiaotong Li, Yongxing Dai, Yixiao Ge, Jun Liu, Ying Shan, Ling-Yu Duan
In this paper, we improve the network generalization ability by modeling the uncertainty of domain shifts with synthesized feature statistics during training.
no code implementations • CVPR 2022 • Jia Gong, Zhipeng Fan, Qiuhong Ke, Hossein Rahmani, Jun Liu
The existing pose estimation approaches often require a large number of annotated images to attain good estimation performance, which are laborious to acquire.
no code implementations • CVPR 2022 • Xia Kong, Zuodong Gao, Xiaofan Li, Ming Hong, Jun Liu, Chengjie Wang, Yuan Xie, Yanyun Qu
Our ICCE promotes intra-class compactness with inter-class separability on both seen and unseen classes in the embedding space and visual feature space.
1 code implementation • CVPR 2022 • Haiwei Wu, Jiantao Zhou, Jinyu Tian, Jun Liu
To fight against the OSN-shared forgeries, in this work, a novel robust training scheme is proposed.
no code implementations • 27 Dec 2021 • Mohamed Serry, Jun Liu
Under-approximations of reachable sets and tubes have been receiving growing research attention due to their important roles in control synthesis and verification.
no code implementations • 23 Dec 2021 • Lei Wang, Jun Liu, Piotr Koniusz
In this paper, we propose a Few-shot Learning pipeline for 3D skeleton-based action recognition by Joint tEmporal and cAmera viewpoiNt alIgnmEnt (JEANIE).
no code implementations • 6 Dec 2021 • Fangzhi Xu, Qika Lin, Jun Liu, Lingling Zhang, Tianzhe Zhao, Qi Chai, Yudai Pan
Textbook Question Answering (TQA) is a complex multimodal task to infer answers given large context descriptions and abundant diagrams.
1 code implementation • 4 Dec 2021 • Feng Xu, Chuang Zhu, Wenqi Tang, Ying Wang, Yu Zhang, Jie Li, Hongchuan Jiang, Zhongyue Shi, Jun Liu, Mulan Jin
Conclusion: Our study provides a novel DL-based biomarker on primary tumor CNB slides to predict the metastatic status of ALN preoperatively for patients with EBC.
no code implementations • 4 Nov 2021 • WeiFu Fu, Congchong Nie, Ting Sun, Jun Liu, Tianliang Zhang, Yong liu
Our method focuses on the problem in following two aspects: the long-tail distribution and the segmentation quality of mask and boundary.
Ranked #3 on Instance Segmentation on LVIS v1.0 val
no code implementations • 17 Oct 2021 • Yudai Pan, Jun Liu, Lingling Zhang, Xin Hu, Tianzhe Zhao, Qika Lin
Relation reasoning in knowledge graphs (KGs) aims at predicting missing relations in incomplete triples, whereas the dominant paradigm is learning the embeddings of relations and entities, which is limited to a transductive setting and has restriction on processing unseen entities in an inductive situation.
no code implementations • 3 Oct 2021 • Yanan Dai, Pengxiong Zhu, Bangde Xue, Yun Ling, Xibao Shi, Liang Geng, Qi Zhang, Jun Liu
Hence, the prediction accuracy of DZL is used as an approximator of coronary stenosis indicator.
no code implementations • 23 Sep 2021 • Haoxuan Qu, Hossein Rahmani, Li Xu, Bryan Williams, Jun Liu
In contrast to batch learning where all training data is available at once, continual learning represents a family of methods that accumulate knowledge and learn continuously with data available in sequential order.
no code implementations • 8 Sep 2021 • Geng-Xin Xu, Chen Liu, Jun Liu, Zhongxiang Ding, Feng Shi, Man Guo, Wei Zhao, Xiaoming Li, Ying WEI, Yaozong Gao, Chuan-Xian Ren, Dinggang Shen
Particularly, we propose a domain translator and align the heterogeneous data to the estimated class prototypes (i. e., class centers) in a hyper-sphere manifold.
no code implementations • 4 Sep 2021 • Chenjie Wang, Chengyuan Li, Bin Luo, Wei Wang, Jun Liu
Then we extend SOLOV2 to capture temporal information in video to learn motion information, and propose a moving object instance segmentation network with RiWFPN called RiWNet.
1 code implementation • ICCV 2021 • Haoxi Ran, Wei Zhuo, Jun Liu, Li Lu
We further verify the expandability of RPNet, in terms of both depth and width, on the tasks of classification and segmentation.
Ranked #18 on 3D Point Cloud Classification on ModelNet40
no code implementations • 18 Aug 2021 • Haoran Peng, He Huang, Li Xu, Tianjiao Li, Jun Liu, Hossein Rahmani, Qiuhong Ke, Zhicheng Guo, Cong Wu, Rongchang Li, Mang Ye, Jiahao Wang, Jiaxu Zhang, Yuanzhong Liu, Tao He, Fuwei Zhang, Xianbin Liu, Tao Lin
In this paper, we introduce the Multi-Modal Video Reasoning and Analyzing Competition (MMVRAC) workshop in conjunction with ICCV 2021.
no code implementations • 16 Aug 2021 • Jun Liu, Jiayao Gao, Sanjay Jha, Wen Hu
By exploiting both the original and the conjugate of the physical layer, Seirios can resolve the direct path from multiple reflectors in both indoor and outdoor environments.
1 code implementation • 6 Aug 2021 • Yan Bai, Jile Jiao, Shengsen Wu, Yihang Lou, Jun Liu, Xuetao Feng, Ling-Yu Duan
It is a heavy workload to re-extract features of the whole database every time. Feature compatibility enables the learned new visual features to be directly compared with the old features stored in the database.
no code implementations • 5 Aug 2021 • Duo Peng, Yinjie Lei, Lingqiao Liu, Pingping Zhang, Jun Liu
In this work, we propose two simple yet effective texture randomization mechanisms, Global Texture Randomization (GTR) and Local Texture Randomization (LTR), for Domain Generalization based SRSS.
3 code implementations • ICCV 2021 • Yongxing Dai, Jun Liu, Yifan Sun, Zekun Tong, Chi Zhang, Ling-Yu Duan
To ensure these two properties to better characterize appropriate intermediate domains, we enforce the bridge losses on intermediate domains' prediction space and feature space, and enforce a diversity loss on the two domain factors.
Domain Adaptive Person Re-Identification Person Re-Identification
no code implementations • ICCV 2021 • Siyuan Yang, Jun Liu, Shijian Lu, Meng Hwa Er, Alex C. Kot
We investigate unsupervised representation learning for skeleton action recognition, and design a novel skeleton cloud colorization technique that is capable of learning skeleton representations from unlabeled skeleton sequence data.
1 code implementation • 15 Jul 2021 • Ye Yuan, Jun Liu, Dou Jin, Zuogong Yue, Ruijuan Chen, Maolin Wang, Chuan Sun, Lei Xu, Feng Hua, Xin He, Xinlei Yi, Tao Yang, Hai-Tao Zhang, Shaochun Sui, Han Ding
Although there has been a joint effort in tackling such a critical issue by proposing privacy-preserving machine learning frameworks, such as federated learning, most state-of-the-art frameworks are built still in a centralized way, in which a central client is needed for collecting and distributing model information (instead of data itself) from every other client, leading to high communication pressure and high vulnerability when there exists a failure at or attack on the central client.
no code implementations • 14 Jul 2021 • Kai Mei, Jun Liu, Xiaoying Zhang, Kuo Cao, Nandana Rajatheva, Jibo Wei
Besides, a training data construction approach utilizing least square (LS) estimation results is proposed so that the training data can be collected during the data transmission.
1 code implementation • 30 Jun 2021 • Zhiyu Mou, Feifei Gao, Jun Liu, Qihui Wu
Numerical results show that the proposed algorithms can rebuild the communication connectivity of the USNET more quickly than the existing algorithms under both one-off UEDs and general UEDs.
1 code implementation • CVPR 2021 • Guoshun Nan, Rui Qiao, Yao Xiao, Jun Liu, Sicong Leng, Hao Zhang, Wei Lu
2) Meanwhile, we introduce a dual contrastive learning approach (DCL) to better align the text and video by maximizing the mutual information (MI) between query and video clips, and the MI between start/end frames of a target moment and the others within a video to learn more informative visual representations.
no code implementations • 19 Jun 2021 • Feihong Shen, Jun Liu
The neural network and quantum computing are both significant and appealing fields, with their interactive disciplines promising for large-scale computing tasks that are untackled by conventional computers.
no code implementations • CVPR 2021 • Yan Bai, Jile Jiao, Wang Ce, Jun Liu, Yihang Lou, Xuetao Feng, Ling-Yu Duan
Recently, person re-identification (ReID) has vastly benefited from the surging waves of data-driven methods.
no code implementations • 11 Jun 2021 • Feihong Shen, Jun Liu, Ping Hu
In this work, we consider counterfactual methods to avoid the confounder in the original model.
no code implementations • 7 Jun 2021 • XiaoHong Wang, Xudong Jiang, Henghui Ding, Yuqian Zhao, Jun Liu
In this paper, we propose a novel knowledge-aware deep framework that incorporates some clinical knowledge into collaborative learning of two important melanoma diagnosis tasks, i. e., skin lesion segmentation and melanoma recognition.
no code implementations • 2 Jun 2021 • Jun Liu, Haitao Zhao, Dongtang Ma, Kai Mei, Jibo Wei
Deep Neural Network (DNN)-based physical layer techniques are attracting considerable interest due to their potential to enhance communication systems.
no code implementations • CVPR 2021 • Yongxing Dai, Xiaotong Li, Jun Liu, Zekun Tong, Ling-Yu Duan
Specifically, we propose a decorrelation loss to make the source domain networks (experts) keep the diversity and discriminability of individual domains' characteristics.
no code implementations • 6 Apr 2021 • Chuanzheng Wang, Yiming Meng, Stephen L. Smith, Jun Liu
We propose a notion of stochastic control barrier functions (SCBFs)and show that SCBFs can significantly reduce the control efforts, especially in the presence of noise, compared to stochastic reciprocal control barrier functions (SRCBFs), and offer a less conservative estimation of safety probability, compared to stochastic zeroing control barrier functions (SZCBFs).
no code implementations • 3 Apr 2021 • Yinan Li, Zhibing Sun, Jun Liu
We show that the proposed algorithm is sound for full LTL specifications, and robustly complete for specifications recognizable by deterministic B\"uchi automata (DBA), the latter in the sense that control strategies can be found whenever the given specification can be satisfied with additional bounded disturbances.
2 code implementations • CVPR 2021 • Tianjiao Li, Jun Liu, Wei zhang, Yun Ni, Wenqian Wang, Zhiheng Li
Human behavior understanding with unmanned aerial vehicles (UAVs) is of great significance for a wide range of applications, which simultaneously brings an urgent demand of large, challenging, and comprehensive benchmarks for the development and evaluation of UAV-based models.
no code implementations • EACL 2021 • Tianxing He, Jun Liu, Kyunghyun Cho, Myle Ott, Bing Liu, James Glass, Fuchun Peng
We find that mix-review effectively regularizes the finetuning process, and the forgetting problem is alleviated to some extent.
no code implementations • CVPR 2021 • Jun Liu, Ryan Wen Liu, Jianing Sun, Tieyong Zeng
To improve visual quality under different weather/imaging conditions, we propose a real-time light correction method to recover the degraded scenes in the cases of sandstorms, underwater, and haze.
3 code implementations • CVPR 2021 • Li Xu, He Huang, Jun Liu
In this paper, we create a novel dataset, SUTD-TrafficQA (Traffic Question Answering), which takes the form of video QA based on the collected 10, 080 in-the-wild videos and annotated 62, 535 QA pairs, for benchmarking the cognitive capability of causal inference and event understanding models in complex traffic scenarios.
Ranked #2 on Video Question Answering on SUTD-TrafficQA
no code implementations • 18 Mar 2021 • Bo Tang, Jun Liu, Hai Wang, Yihua Hu
Range profiling refers to the measurement of target response along the radar slant range.
no code implementations • 10 Mar 2021 • Shaowei Wang, Lingling Zhang, Xuan Luo, Yi Yang, Xin Hu, Jun Liu
Another type of diagrams such as from Computer Science is composed of graphics containing complex topologies and relations, and research on this type of diagrams is still blank.
no code implementations • 7 Feb 2021 • Zekun Li, Wei Zhao, Feng Shi, Lei Qi, Xingzhi Xie, Ying WEI, Zhongxiang Ding, Yang Gao, Shangjie Wu, Jun Liu, Yinghuan Shi, Dinggang Shen
How to fast and accurately assess the severity level of COVID-19 is an essential problem, when millions of people are suffering from the pandemic around the world.
no code implementations • ICCV 2021 • Zhipeng Fan, Jun Liu, Yao Wang
A novel model, called Motion Adaptive Pose Net is proposed to exploit the compressed streams to efficiently decode pose sequences from videos.
no code implementations • ICCV 2021 • Yujun Cai, Yiwei Wang, Yiheng Zhu, Tat-Jen Cham, Jianfei Cai, Junsong Yuan, Jun Liu, Chuanxia Zheng, Sijie Yan, Henghui Ding, Xiaohui Shen, Ding Liu, Nadia Magnenat Thalmann
Notably, by considering this problem as a conditional generation process, we estimate a parametric distribution of the missing regions based on the input conditions, from which to sample and synthesize the full motion series.
no code implementations • ICCV 2021 • Tianjiao Li, Qiuhong Ke, Hossein Rahmani, Rui En Ho, Henghui Ding, Jun Liu
This makes online continual action recognition a challenging task.
no code implementations • ICCV 2021 • Henghui Ding, HUI ZHANG, Jun Liu, Jiaxin Li, Zijian Feng, Xudong Jiang
In this work, we treat each respective region in an image as a whole, and capture the structure topology as well as the affinity among different regions.
1 code implementation • 26 Dec 2020 • Yongxing Dai, Jun Liu, Yan Bai, Zekun Tong, Ling-Yu Duan
To this end, we propose a novel approach, called Dual-Refinement, that jointly refines pseudo labels at the off-line clustering phase and features at the on-line training phase, to alternatively boost the label purity and feature discriminability in the target domain for more reliable re-ID.
no code implementations • 22 Dec 2020 • Zehua Sun, Qiuhong Ke, Hossein Rahmani, Mohammed Bennamoun, Gang Wang, Jun Liu
Human Action Recognition (HAR) aims to understand human behavior and assign a label to each action.
no code implementations • 18 Dec 2020 • Chengyuan Li, Jun Liu, Hailong Hong, Wenju Mao, Chenjie Wang, Chudi Hu, Xin Su, Bin Luo
On the basis of this, a novel octave convolution-based semantic attention feature pyramid network (OcSaFPN) is proposed to get higher accuracy in object detection with noise.
no code implementations • 16 Dec 2020 • Jun Liu, Zhu Wang
In this paper we propose to use model reduction techniques for speeding up the diagonalization-based parallel-in-time (ParaDIAG) preconditioner, for iteratively solving all-at-once systems from evolutionary PDEs.
Numerical Analysis Numerical Analysis Dynamical Systems
1 code implementation • 29 Nov 2020 • Yanping Chen, Lefei Wu, Qinghua Zheng, Ruizhang Huang, Jun Liu, Liyuan Deng, Junhui Yu, Yongbin Qing, Bo Dong, Ping Chen
Then, a regression operation is introduced to regress boundaries of NEs in a sentence.
1 code implementation • 25 Nov 2020 • Jie Ma, Qi Chai, Jun Liu, Qingyu Yin, Pinghui Wang, Qinghua Zheng
Textbook Question Answering (TQA) is a task that one should answer a diagram/non-diagram question given a large multi-modal context consisting of abundant essays and diagrams.
1 code implementation • 11 Nov 2020 • Jingxiong Li, Yaqi Wang, Shuai Wang, Jun Wang, Jun Liu, Qun Jin, Lingling Sun
Moreover, massive data collection is impractical for a newly emerged disease, which limited the performance of data thirsty deep learning models.