no code implementations • CCL 2021 • Liang Liu, Fang Kong
“实体关系抽取旨在从文本中抽取出实体之间的语义关系, 是自然语言处理的一项基本任务。在新闻报道、维基百科等规范文本上该任务的研究相对丰富, 已经取得了一定的效果, 但面向对话文本的相关研究还处于起始阶段。相较于规范文本, 用于实体关系抽取的对话语料规模较小, 对话文本的有效特征难以捕获, 这使得面向对话文本的实体关系抽取更具挑战。该文针对这一任务提出了一个基于Star-Transformer的实体关系抽取模型, 通过融入高速网络进行信息桥接, 并在此基础上融入交互信息和知识, 最后使用多任务学习机制进一步提升模型的性能。在DialogRE公开数据集上实验得到F1值为55. 7%, F1c值为52. 3%, 证明了提出方法的有效性。”
no code implementations • 26 Mar 2024 • Liang Liu, Shuowen Zhang, Shuguang Cui
A key challenge of 6G-oriented ISAC lies in how to perform ubiquitous sensing based on the communication signals and devices.
1 code implementation • 24 Mar 2024 • Xiaojun Hou, Jiazheng Xing, Yijie Qian, Yaowei Guo, Shuo Xin, JunHao Chen, Kai Tang, Mengmeng Wang, Zhengkai Jiang, Liang Liu, Yong liu
Multimodal Visual Object Tracking (VOT) has recently gained significant attention due to its robustness.
Ranked #17 on Rgb-T Tracking on RGBT234
no code implementations • 18 Mar 2024 • Liren He, Zhengkai Jiang, Jinlong Peng, Liang Liu, Qiangang Du, Xiaobin Hu, Wenbing Zhu, Mingmin Chi, Yabiao Wang, Chengjie Wang
In the field of multi-class anomaly detection, reconstruction-based methods derived from single-class anomaly detection face the well-known challenge of ``learning shortcuts'', wherein the model fails to learn the patterns of normal samples as it should, opting instead for shortcuts such as identity mapping or artificial noise elimination.
no code implementations • 7 Mar 2024 • Yuhu Bai, Jiangning Zhang, Yuhang Dong, Guanzhong Tian, Liang Liu, Yunkang Cao, Yabiao Wang, Chengjie Wang
We consider anomaly detection as a discriminative classification problem, wherefore the dual-path feature discrimination module is employed to detect and locate the image-level and feature-level anomalies in the feature space.
no code implementations • 21 Feb 2024 • Zichang Liu, Qingyun Liu, Yuening Li, Liang Liu, Anshumali Shrivastava, Shuchao Bi, Lichan Hong, Ed H. Chi, Zhe Zhao
Further, to accommodate the dissimilarity among the teachers in the committee, we introduce DiverseDistill, which allows the student to understand the expertise of each teacher and extract task knowledge.
no code implementations • 7 Feb 2024 • Yuji Roh, Qingyun Liu, Huan Gui, Zhe Yuan, Yujin Tang, Steven Euijong Whang, Liang Liu, Shuchao Bi, Lichan Hong, Ed H. Chi, Zhe Zhao
By combining two complementing models, LEVI effectively suppresses problematic features in both the fine-tuning data and pre-trained model and preserves useful features for new tasks.
no code implementations • 17 Jan 2024 • XiaoYu Zhang, Haobo Zhang, Ruoqi Deng, Liang Liu, Boya Di
Multi-target detection is one of the primary tasks in radar-based localization and sensing, typically built on phased array antennas.
no code implementations • 6 Jan 2024 • Yuanpeng Tu, Boshen Zhang, Liang Liu, Yuxi Li, Xuhai Chen, Jiangning Zhang, Yabiao Wang, Chengjie Wang, Cai Rong Zhao
Industrial anomaly detection is generally addressed as an unsupervised task that aims at locating defects with only normal training samples.
no code implementations • 3 Jan 2024 • Yuzhou Yang, Yangming Zhou, Qichao Ying, Zhenxing Qian, Dan Zeng, Liang Liu
This paper reviews and summarizes the research results on fact-based fake news from the perspectives of tasks and problems, algorithm strategies, and datasets.
no code implementations • 20 Dec 2023 • Xianzhen Guo, Qin Shi, Liang Liu, Shuowen Zhang
However, in practice, the number of BSs possessing LOS paths to a target can be small, leading to marginal networked sensing gain.
1 code implementation • 10 Dec 2023 • Teng Hu, Jiangning Zhang, Ran Yi, Yuzhen Du, Xu Chen, Liang Liu, Yabiao Wang, Chengjie Wang
Existing anomaly inspection methods are limited in their performance due to insufficient anomaly data.
no code implementations • 26 Oct 2023 • Runnan Liu, Liang Liu, Yin Xu, Dazhi He, Wenjun Zhang, Chang Wen Chen
We first categorize two types of channel covariance matrix changes based on their impact on system design: Type I change, which denotes the change in the BS receive covariance matrix, and Type II change, which denotes the change in the IRS transmit/receive covariance matrix.
no code implementations • 13 Sep 2023 • Gilles Callebaut, Liang Liu, Thomas Eriksson, Liesbet Van der Perre, Ove Edfors, Christian Fager
The proof of the pudding is in the eating - that is why 6G testbeds are essential in the progress towards the next generation of wireless networks.
1 code implementation • ICCV 2023 • Teng Hu, Jiangning Zhang, Liang Liu, Ran Yi, Siqi Kou, Haokun Zhu, Xu Chen, Yabiao Wang, Chengjie Wang, Lizhuang Ma
To address these problems, we propose a novel phasic content fusing few-shot diffusion model with directional distribution consistency loss, which targets different learning objectives at distinct training stages of the diffusion model.
1 code implementation • 7 Sep 2023 • Yue Wang, Jinlong Peng, Jiangning Zhang, Ran Yi, Liang Liu, Yabiao Wang, Chengjie Wang
To improve the facial representation quality, we use feature map of a pre-trained visual backbone as a supervision item and use a partially pre-trained decoder for mask image modeling.
2 code implementations • 7 Sep 2023 • Teng Hu, Ran Yi, Haokun Zhu, Liang Liu, Jinlong Peng, Yabiao Wang, Chengjie Wang, Lizhuang Ma
To solve the problem, we propose Compositional Neural Painter, a novel stroke-based rendering framework which dynamically predicts the next painting region based on the current canvas, instead of dividing the image plane uniformly into painting regions.
1 code implementation • 6 Sep 2023 • Ilayda Yaman, Guoda Tian, Erik Tegler, Jens Gulin, Nikhil Challa, Fredrik Tufvesson, Ove Edfors, Kalle Astrom, Steffen Malkowsky, Liang Liu
We present a unique comparative analysis, and evaluation of vision, radio, and audio based localization algorithms.
no code implementations • 6 Sep 2023 • QiPeng Wang, Liang Liu, Shuowen Zhang
In this paper, we consider a more challenging AOA estimation setup in the intelligent reflecting surface (IRS) assisted integrated sensing and communication (ISAC) system, where LOS paths do not exist between the BS and the users, while the users' signals can be transmitted to the BS merely via their LOS paths to the IRS as well as the LOS path from the IRS to the BS.
no code implementations • 4 Aug 2023 • Rui Wang, Zhaorui Wang, Liang Liu, Shuowen Zhang, Shi Jin
Different from the uplink counterpart where the BS possesses the pilot signals containing the CSI of all the users, in downlink communication, the distributed users merely receive the pilot signals containing their own CSI and cannot leverage the correlation in different users' channels revealed in [1].
1 code implementation • 7 Jun 2023 • Liang Liu, Haixin Guan, Jinlong Ma, Wei Dai, Guangyong Wang, Shaowei Ding
In speech enhancement, the lack of clear structural characteristics in the target speech phase requires the use of conservative and cumbersome network frameworks.
no code implementations • 24 May 2023 • Zhengkai Jiang, Liang Liu, Jiangning Zhang, Yabiao Wang, Mingang Chen, Chengjie Wang
This paper introduces a novel attention mechanism, called dual attention, which is both efficient and effective.
no code implementations • 12 May 2023 • Yi Su, Xiangyu Wang, Elaine Ya Le, Liang Liu, Yuening Li, Haokai Lu, Benjamin Lipshitz, Sriraj Badam, Lukasz Heldt, Shuchao Bi, Ed Chi, Cristos Goodrow, Su-Lin Wu, Lexi Baugher, Minmin Chen
We conduct live experiments on one of the largest short-form video recommendation platforms that serves billions of users to validate the new experiment designs, quantify the long-term values of exploration, and to verify the effectiveness of the adopted neural linear bandit algorithm for exploration.
no code implementations • 4 May 2023 • QiPeng Wang, Liang Liu, Shuowen Zhang, Boya Di, Francis C. M. Lau
In this paper, we show that the distance between a target and its associated IRS can be indirectly estimated based on the length of the BS-target-BS path and the BS-target-IRS-BS path.
1 code implementation • CVPR 2023 • Liang Liu, Boshen Zhang, Jiangning Zhang, Wuhao Zhang, Zhenye Gan, Guanzhong Tian, Wenbing Zhu, Yabiao Wang, Chengjie Wang
Despite the remarkable progress made by modern detection models, this challenge is particularly evident in the semi-supervised case.
1 code implementation • 14 Mar 2023 • Haohan Wang, Liang Liu, Boshen Zhang, Jiangning Zhang, Wuhao Zhang, Zhenye Gan, Yabiao Wang, Chengjie Wang, Haoqian Wang
Recent works on sparsely annotated object detection alleviate this problem by generating pseudo labels for the missing annotations.
1 code implementation • 13 Mar 2023 • Liang Liu, Ling Tian, Zhao Kang, Tianqi Wan
The time series telemetry data generated by on-orbit spacecraft \textcolor{blue}{contains} important information about the status of spacecraft.
1 code implementation • 10 Mar 2023 • Haohan Wang, Liang Liu, Wuhao Zhang, Jiangning Zhang, Zhenye Gan, Yabiao Wang, Chengjie Wang, Haoqian Wang
Few-shot semantic segmentation aims to learn to segment unseen class objects with the guidance of only a few support images.
Ranked #41 on Few-Shot Semantic Segmentation on COCO-20i (1-shot)
no code implementations • 7 Mar 2023 • Guoda Tian, Ilayda Yaman, Michiel Sandra, Xuesong Cai, Liang Liu, Fredrik Tufvesson
High-precision cellular-based localization is one of the key technologies for next-generation communication systems.
no code implementations • 16 Feb 2023 • Qin Shi, Liang Liu, Shuowen Zhang
Recently, there is a growing interest in achieving integrated sensing and communication (ISAC) in the sixth-generation (6G) cellular network.
1 code implementation • CVPR 2023 • Yuanpeng Tu, Boshen Zhang, Yuxi Li, Liang Liu, Jian Li, Jiangning Zhang, Yabiao Wang, Chengjie Wang, Cai Rong Zhao
Collecting large-scale datasets is crucial for training deep models, annotating the data, however, inevitably yields noisy labels, which poses challenges to deep learning algorithms.
Ranked #2 on Image Classification on Clothing1M (using extra training data)
1 code implementation • 14 Feb 2023 • Yuanpeng Tu, Yuxi Li, Boshen Zhang, Liang Liu, Jiangning Zhang, Yabiao Wang, Cai Rong Zhao
Based on the proposed estimators, we devise an adaptive self-supervised training framework, which exploits the contextual reliance and estimated likelihood to refine mask annotations in anomaly areas.
1 code implementation • CVPR 2023 • Yuanpeng Tu, Boshen Zhang, Yuxi Li, Liang Liu, Jian Li, Yabiao Wang, Chengjie Wang, Cai Rong Zhao
Training deep neural networks(DNN) with noisy labels is challenging since DNN can easily memorize inaccurate labels, leading to poor generalization ability.
1 code implementation • 10 Feb 2023 • Ilayda Yaman, Guoda Tian, Martin Larsson, Patrik Persson, Michiel Sandra, Alexander Dürr, Erik Tegler, Nikhil Challa, Henrik Garde, Fredrik Tufvesson, Kalle Åström, Ove Edfors, Steffen Malkowsky, Liang Liu
The dataset includes color images, corresponding depth maps, inertial measurement unit (IMU) readings, channel response between a 5G massive multiple-input and multiple-output (MIMO) testbed and user equipment, audio recorded by 12 microphones, and accurate six degrees of freedom (6DOF) pose ground truth of 0. 5 mm.
1 code implementation • ICCV 2023 • Jiangning Zhang, Xiangtai Li, Jian Li, Liang Liu, Zhucun Xue, Boshen Zhang, Zhengkai Jiang, Tianxin Huang, Yabiao Wang, Chengjie Wang
This paper focuses on developing modern, efficient, lightweight models for dense predictions while trading off parameters, FLOPs, and performance.
2 code implementations • ICCV 2023 • Zhihao Gu, Liang Liu, Xu Chen, Ran Yi, Jiangning Zhang, Yabiao Wang, Chengjie Wang, Annan Shu, Guannan Jiang, Lizhuang Ma
Specifically, we first propose a normality recall memory (NR Memory) to strengthen the normality of student-generated features by recalling the stored normal information.
Ranked #11 on Anomaly Detection on MVTec AD
no code implementations • 6 Nov 2022 • Shaohua Yue, Shuhao Zeng, Hongliang Zhang, Fenghan Lin, Liang Liu, Boya Di
Intelligent omni-surfaces (IOS) have attracted great attention recently due to its potential to achieve full-dimensional communications by simultaneously reflecting and refracting signals toward both sides of the surface.
no code implementations • 5 Jul 2022 • Runnan Liu, Liang Liu, Dazhi He, Wenjun Zhang, Erik G. Larsson
Our paper aims to adopt the classic change detection theory to detect the change in the channel covariance matrix as accurately and quickly as possible such that the new covariance matrix can be re-estimated in time.
no code implementations • 1 Jun 2022 • Liang Liu, Shuowen Zhang, Rui Du, Tong Xiao Han, Shuguang Cui
This article will discuss about the possibility of exploiting the future sixth-generation (6G) cellular network to realize ISAC.
no code implementations • 25 May 2022 • QiPeng Wang, Liang Liu, Shuowen Zhang, Francis C. M. Lau
The classic trilateration technique can localize each target based on its distances to three anchors with known coordinates.
1 code implementation • 18 May 2022 • Liang Liu, Peng Chen, Guangchun Luo, Zhao Kang, Yonggang Luo, Sanchu Han
With the explosive growth of multi-source data, multi-view clustering has attracted great attention in recent years.
no code implementations • 13 May 2022 • Jinlong Peng, Zekun Luo, Liang Liu, Boshen Zhang, Tao Wang, Yabiao Wang, Ying Tai, Chengjie Wang, Weiyao Lin
Image harmonization aims to generate a more realistic appearance of foreground and background for a composite image.
2 code implementations • 19 Mar 2022 • Peng Chen, Zhimin Chen, Liang Liu, Yun Chen, Xianbin Wang
The estimation of direction of arrival (DOA) is a crucial issue in conventional radar, wireless communication, and integrated sensing and communication (ISAC) systems.
no code implementations • 8 Feb 2022 • Zhengkai Jiang, Zhangxuan Gu, Jinlong Peng, Hang Zhou, Liang Liu, Yabiao Wang, Ying Tai, Chengjie Wang, Liqing Zhang
In contrast, we present a simple and efficient single-stage VIS framework based on the instance segmentation method CondInst by adding an extra tracking head.
Ranked #36 on Video Instance Segmentation on YouTube-VIS validation
1 code implementation • 5 Jan 2022 • QiPeng Wang, Liang Liu, Shuowen Zhang, Francis C. M. Lau
In particular, we propose to leverage the temporal correlation in device activity, e. g., a device active in the previous coherence block is more likely to be still active in the current coherence block, to improve the detection and estimation performance.
1 code implementation • CVPR 2022 • Shaohua Guo, Liang Liu, Zhenye Gan, Yabiao Wang, Wuhao Zhang, Chengjie Wang, Guannan Jiang, Wei zhang, Ran Yi, Lizhuang Ma, Ke Xu
The huge burden of computation and memory are two obstacles in ultra-high resolution image segmentation.
no code implementations • 28 Dec 2021 • Liang Liu, Zhao Kang, Ling Tian, Wenbo Xu, Xixu He
To this end, we propose a generic and effective autoencoder framework for multilayer graph clustering named Multilayer Graph Contrastive Clustering Network (MGCCN).
no code implementations • 20 Dec 2021 • Xianfang Zeng, Jiangning Zhang, Liang Liu, Guangzhong Tian, Yong liu
To tackle this problem, we propose a novel domain-adaptive degradation network for face super-resolution in the wild.
1 code implementation • 9 Sep 2021 • Runnan Liu, Liang Liu, Dazhi He, Wenjun Zhang, Erik G. Larsson
This result verifies the possibility to detect the channel covariance change both accurately and quickly in practice.
no code implementations • 7 Sep 2021 • MinKeun Chung, Liang Liu, Andreas Johansson, Sara Gunnarsson, Martin Nilsson, Zhinong Ying, Olof Zander, Kamal Samanta, Chris Clifton, Toshiyuki Koimori, Shinya Morita, Satoshi Taniguchi, Fredrik Tufvesson, Ove Edfors
The UEs are equipped with a beam-switchable antenna array for real-time antenna selection where the one with the highest channel magnitude, out of four pre-defined beams, is selected.
no code implementations • 20 Aug 2021 • Qin Shi, Liang Liu, Shuowen Zhang, Shuguang Cui
A novel two-phase sensing framework is proposed to localize the passive targets that cannot transmit/receive reference signals to/from the base stations (BSs), where the ranges of the targets are estimated based on their reflected OFDM signals to the BSs in Phase I, and the location of each target is estimated based on its ranges to different BSs in Phase II.
no code implementations • 22 Jun 2021 • Rui Wang, Liang Liu, Shuowen Zhang, Changyuan Yu
Specifically, in Phase I, the correlation coefficients between the channels of a typical BS antenna and those of the other antennas are estimated; while in Phase II, the cascaded channel of the typical antenna is estimated.
no code implementations • CVPR 2021 • Haiyang Zhang, XiMing Xing, Liang Liu
Unreliable labels derived from large-scale dataset prevent neural networks from fully exploring the data.
1 code implementation • 18 Jun 2021 • Peng Chen, Liang Liu, Zhengrui Ma, Zhao Kang
In recent years, multi-view subspace clustering has achieved impressive performance due to the exploitation of complementary imformation across multiple views.
1 code implementation • 27 Jan 2021 • QiPeng Wang, Liang Liu, Shuowen Zhang, Francis C. M. Lau
In particular, we propose to leverage the temporal correlation in user activity, i. e., a device active at the previous time slot is more likely to be still active at the current moment, to improve the detection performance.
Action Detection Activity Detection Information Theory Signal Processing Information Theory
no code implementations • 1 Jan 2021 • Haiyang Zhang, Jiaming Duan, Liang Liu
After that, with the message-passing mechanism, CKEM selects and transfers relevant knowledge from external semantic knowledge bank to original visual-based class representations in Knowledge Fusion Model(KFM).
1 code implementation • 14 Dec 2020 • Xiaoyang Lyu, Liang Liu, Mengmeng Wang, Xin Kong, Lina Liu, Yong liu, Xinxin Chen, Yi Yuan
To obtainmore accurate depth estimation in large gradient regions, itis necessary to obtain high-resolution features with spatialand semantic information.
Ranked #7 on Unsupervised Monocular Depth Estimation on KITTI-C
no code implementations • 9 Dec 2020 • Jesus Rodriguez Sanchez, Fredrik Rusek, Ove Edfors, Liang Liu
The Large Intelligent Surface (LIS) is a promising technology in the areas of wireless communication, remote sensing and positioning.
no code implementations • 2 Dec 2020 • MinKeun Chung, Liang Liu, Andreas Johansson, Martin Nilsson, Olof Zander, Zhinong Ying, Fredrik Tufvesson, Ove Edfors
In this paper, we present a real-time mmWave (28 GHz) massive MIMO testbed with hybrid beamforming.
no code implementations • 12 Nov 2020 • Liang Liu, Shuowen Zhang
Since the technologies of orthogonal frequency division multiplexing (OFDM) and multiple-input multiple-output (MIMO) are widely used in the legacy cellular systems, this paper proposes a two-stage signal processing approach for radar sensing in an MIMO-OFDM system, where the scattered channels caused by various targets are estimated in the first stage, and the location information of the targets is then extracted from their scattered channels in the second stage.
no code implementations • 20 Oct 2020 • Liang Liu, Ya-Feng Liu
A great amount of endeavour has recently been devoted to the joint device activity detection and channel estimation problem in massive machine-type communications.
1 code implementation • ECCV 2020 • Jiangning Zhang, Chao Xu, Liang Liu, Mengmeng Wang, Xia Wu, Yong liu, Yunliang Jiang
The proposed DTVNet consists of two submodules: \emph{Optical Flow Encoder} (OFE) and \emph{Dynamic Video Generator} (DVG).
1 code implementation • ECCV 2020 • Liang Liu, Hao Lu, Hongwei Zou, Haipeng Xiong, Zhiguo Cao, Chunhua Shen
Inspired by scale weighing, we propose a novel 'counting scale' termed LibraNet where the count value is analogized by weight.
no code implementations • 31 May 2020 • Liang Liu, Xiaopeng Luo
In this paper, we propose a novel accelerated stochastic gradient method with momentum, which momentum is the weighted average of previous gradients.
no code implementations • 18 May 2020 • Jiangning Zhang, Liang Liu, Chao Xu, Yong liu
Recent works in the person re-identification task mainly focus on the model accuracy while ignore factors related to the efficiency, e. g. model size and latency, which are critical for practical application.
3 code implementations • 30 Apr 2020 • Jiangning Zhang, Liang Liu, Zhu-Cun Xue, Yong liu
Audio-guided face reenactment aims at generating photorealistic faces using audio information while maintaining the same facial movement as when speaking to a real person.
1 code implementation • 6 Apr 2020 • Jun Chen, Liang Liu, Yong liu, Xianfang Zeng
Furthermore, we also design a shift vector processing element (SVPE) array to replace all 16-bit multiplications with SHIFT operations in convolution operation on FPGAs.
2 code implementations • CVPR 2020 • Liang Liu, Jiangning Zhang, Ruifei He, Yong liu, Yabiao Wang, Ying Tai, Donghao Luo, Chengjie Wang, Jilin Li, Feiyue Huang
Unsupervised learning of optical flow, which leverages the supervision from view synthesis, has emerged as a promising alternative to supervised methods.
Ranked #2 on Optical Flow Estimation on KITTI 2012 unsupervised
1 code implementation • 16 Mar 2020 • Chunfang Deng, Mengmeng Wang, Liang Liu, Yong liu
Small object detection remains an unsolved challenge because it is hard to extract information of small objects with only a few pixels.
no code implementations • 14 Jan 2020 • Jesus Rodriguez Sanchez, Ove Edfors, Fredrik Rusek, Liang Liu
The Large Intelligent Surface (LIS) concept has emerged recently as a new paradigm for wireless communication, remote sensing and positioning.
3 code implementations • 7 Jan 2020 • Haipeng Xiong, Hao Lu, Chengxin Liu, Liang Liu, Chunhua Shen, Zhiguo Cao
Visual counting, a task that aims to estimate the number of objects from an image/video, is an open-set problem by nature, i. e., the number of population can vary in [0, inf) in theory.
5 code implementations • ICCV 2019 • Haipeng Xiong, Hao Lu, Chengxin Liu, Liang Liu, Zhiguo Cao, Chunhua Shen
A dense region can always be divided until sub-region counts are within the previously observed closed set.
Ranked #3 on Crowd Counting on TRANCOS
no code implementations • 19 Jun 2019 • Guangyao Zhai, Liang Liu, Linjian Zhang, Yong liu
The feature-encoding module encodes the short-term motion feature in an image pair, while the memory-propagating module captures the long-term motion feature in the consecutive image pairs.
1 code implementation • CVPR 2020 • Jiangning Zhang, Xianfang Zeng, Mengmeng Wang, Yusu Pan, Liang Liu, Yong liu, Yu Ding, Changjie Fan
This paper presents a novel multi-identity face reenactment framework, named FReeNet, to transfer facial expressions from an arbitrary source face to a target face with a shared model.
no code implementations • 21 Oct 2017 • Heng Qi, Wu Liu, Liang Liu
Mobile visual search applications are emerging that enable users to sense their surroundings with smart phones.
no code implementations • 10 Sep 2015 • Liang Liu, Lili Yu
The primary goal of this study is to provide quantitative evidence of the evolutionary linkages, with emphasis on character usage, among different period genres of classical Chinese poetry.