2 code implementations • ICCV 2021 • Li Liu, Qingle Huang, Sihao Lin, Hongwei Xie, Bing Wang, Xiaojun Chang, Xiaodan Liang
Extensive experiments on two vision tasks, including ImageNet classification and Pascal VOC segmentation, demonstrate the superiority of our ICKD, which consistently outperforms many existing methods, advancing the state-of-the-art in the fields of Knowledge Distillation.
Ranked #21 on Knowledge Distillation on ImageNet
2 code implementations • 27 May 2022 • TingTing Liang, Hongwei Xie, Kaicheng Yu, Zhongyu Xia, Zhiwei Lin, Yongtao Wang, Tao Tang, Bing Wang, Zhi Tang
Fusing the camera and LiDAR information has become a de-facto standard for 3D object detection tasks.
1 code implementation • 22 Jun 2020 • Changhao Chen, Bing Wang, Chris Xiaoxuan Lu, Niki Trigoni, Andrew Markham
Deep learning based localization and mapping has recently attracted significant attention.
1 code implementation • 18 Sep 2023 • Mingjie Pan, Jiaming Liu, Renrui Zhang, Peixiang Huang, Xiaoqi Li, Bing Wang, Hongwei Xie, Li Liu, Shanghang Zhang
3D occupancy prediction holds significant promise in the fields of robot perception and autonomous driving, which quantifies 3D scenes into grid cells with semantic labels.
1 code implementation • ACL 2022 • Xinyu Pi, Bing Wang, Yan Gao, Jiaqi Guo, Zhoujun Li, Jian-Guang Lou
The robustness of Text-to-SQL parsers against adversarial perturbations plays a crucial role in delivering highly reliable applications.
2 code implementations • 19 Apr 2022 • Bing Wang, Zhengdi Yu, Bo Yang, Jie Qin, Toby Breckon, Ling Shao, Niki Trigoni, Andrew Markham
We present RangeUDF, a new implicit representation based framework to recover the geometry and semantics of continuous 3D scene surfaces from point clouds.
1 code implementation • 15 Aug 2022 • Bing Wang, Lu Chen, Bo Yang
In this paper, we study the problem of 3D scene geometry decomposition and manipulation from 2D views.
1 code implementation • CVPR 2021 • Changlin Li, Guangrun Wang, Bing Wang, Xiaodan Liang, Zhihui Li, Xiaojun Chang
Here, we explore a dynamic network slimming regime, named Dynamic Slimmable Network (DS-Net), which aims to achieve good hardware-efficiency via dynamically adjusting filter numbers of networks at test time with respect to different inputs, while keeping filters stored statically and contiguously in hardware to prevent the extra burden.
1 code implementation • 21 Sep 2021 • Changlin Li, Guangrun Wang, Bing Wang, Xiaodan Liang, Zhihui Li, Xiaojun Chang
Dynamic networks have shown their promising capability in reducing theoretical computation complexity by adapting their architectures to the input during inference.
1 code implementation • 5 Oct 2023 • Haiping Wang, YuAn Liu, Bing Wang, Yujing Sun, Zhen Dong, Wenping Wang, Bisheng Yang
Matching cross-modality features between images and point clouds is a fundamental problem for image-to-point cloud registration.
1 code implementation • CVPR 2023 • Zihui Zhang, Bo Yang, Bing Wang, Bo Li
Our method consists of three major components, 1) the feature extractor to learn per-point features from input point clouds, 2) the superpoint constructor to progressively grow the sizes of superpoints, and 3) the semantic primitive clustering module to group superpoints into semantic elements for the final semantic segmentation.
1 code implementation • ICCV 2021 • Changlin Li, Tao Tang, Guangrun Wang, Jiefeng Peng, Bing Wang, Xiaodan Liang, Xiaojun Chang
In this work, we present Block-wisely Self-supervised Neural Architecture Search (BossNAS), an unsupervised NAS method that addresses the problem of inaccurate architecture rating caused by large weight-sharing space and biased supervision in previous methods.
1 code implementation • 8 Sep 2019 • Bing Wang, Changhao Chen, Chris Xiaoxuan Lu, Peijun Zhao, Niki Trigoni, Andrew Markham
Deep learning has achieved impressive results in camera localization, but current single-image techniques typically suffer from a lack of robustness, leading to large outliers.
Ranked #2 on Visual Localization on Oxford RobotCar Full
1 code implementation • 18 Dec 2023 • Bing Wang, Changyu Ren, Jian Yang, Xinnian Liang, Jiaqi Bai, Linzheng Chai, Zhao Yan, Qian-Wen Zhang, Di Yin, Xing Sun, Zhoujun Li
Our framework comprises a core decomposer agent for Text-to-SQL generation with few-shot chain-of-thought reasoning, accompanied by two auxiliary agents that utilize external tools or models to acquire smaller sub-databases and refine erroneous SQL queries.
1 code implementation • 30 May 2022 • Kaicheng Yu, Tang Tao, Hongwei Xie, Zhiwei Lin, Zhongwei Wu, Zhongyu Xia, TingTing Liang, Haiyang Sun, Jiong Deng, Dayang Hao, Yongtao Wang, Xiaodan Liang, Bing Wang
There are two critical sensors for 3D perception in autonomous driving, the camera and the LiDAR.
1 code implementation • 1 Nov 2019 • Chris Xiaoxuan Lu, Stefano Rosa, Peijun Zhao, Bing Wang, Changhao Chen, John A. Stankovic, Niki Trigoni, Andrew Markham
This paper presents the design, implementation and evaluation of milliMap, a single-chip millimetre wave (mmWave) radar based indoor mapping system targetted towards low-visibility environments to assist in emergency response.
1 code implementation • ICCV 2021 • Bing Wang, Changhao Chen, Zhaopeng Cui, Jie Qin, Chris Xiaoxuan Lu, Zhengdi Yu, Peijun Zhao, Zhen Dong, Fan Zhu, Niki Trigoni, Andrew Markham
Accurately describing and detecting 2D and 3D keypoints is crucial to establishing correspondences across images and point clouds.
1 code implementation • 15 Apr 2021 • Muhamad Risqi U. Saputra, Chris Xiaoxuan Lu, Pedro P. B. de Gusmao, Bing Wang, Andrew Markham, Niki Trigoni
Simultaneous Localization and Mapping (SLAM) system typically employ vision-based sensors to observe the surrounding environment.
1 code implementation • 26 Apr 2023 • Bing Wang, Xinnian Liang, Jian Yang, Hui Huang, Shuangzhi Wu, Peihao Wu, Lu Lu, Zejun Ma, Zhoujun Li
Large Language Models (LLMs) are constrained by their inability to process lengthy inputs, resulting in the loss of critical historical information.
1 code implementation • CVPR 2023 • Ping Chen, Xingpeng Zhang, Ye Li, Ju Tao, Bin Xiao, Bing Wang, Zongjie Jiang
Inspired by the transfer learning, we designed the Delta Age AdaIN (DAA) operation to obtain the feature difference with each age, which obtains the style map of each age through the learned values representing the mean and standard deviation.
1 code implementation • COLING 2022 • Bing Wang, Liang Ding, Qihuang Zhong, Ximing Li, DaCheng Tao
Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment analysis task, which focuses on detecting the sentiment polarity towards the aspect in a sentence.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +4
1 code implementation • CVPR 2022 • Jia-Xing Zhong, Kaichen Zhou, Qingyong Hu, Bing Wang, Niki Trigoni, Andrew Markham
Scene flow is a powerful tool for capturing the motion field of 3D point clouds.
Ranked #1 on 3D Action Recognition on NTU RGB+D
2 code implementations • CVPR 2022 • Sihao Lin, Hongwei Xie, Bing Wang, Kaicheng Yu, Xiaojun Chang, Xiaodan Liang, Gang Wang
To this end, we propose a novel one-to-all spatial matching knowledge distillation approach.
1 code implementation • 7 Nov 2021 • Peijun Zhao, Chris Xiaoxuan Lu, Bing Wang, Niki Trigoni, Andrew Markham
To avoid the drawbacks of conventional DFT pre-processing, we propose a learnable pre-processing module, named CubeLearn, to directly extract features from raw radar signal and build an end-to-end deep neural network for mmWave FMCW radar motion recognition applications.
1 code implementation • 8 Feb 2022 • Li Liu, Qingle Huang, Sihao Lin, Hongwei Xie, Bing Wang, Xiaojun Chang, Xiaodan Liang
Extensive experiments on two vision tasks, includ-ing ImageNet classification and Pascal VOC segmentation, demonstrate the superiority of our ICKD, which consis-tently outperforms many existing methods, advancing thestate-of-the-art in the fields of Knowledge Distillation.
2 code implementations • 5 Mar 2020 • Wei Wang, Bing Wang, Peijun Zhao, Changhao Chen, Ronald Clark, Bo Yang, Andrew Markham, Niki Trigoni
In this paper, we present a novel end-to-end learning-based LiDAR relocalization framework, termed PointLoc, which infers 6-DoF poses directly using only a single point cloud as input, without requiring a pre-built map.
Robotics
1 code implementation • 17 Dec 2022 • Bing Wang, Yan Gao, Zhoujun Li, Jian-Guang Lou
Following this study, we propose a simple yet effective counterfactual example generation approach that automatically produces ambiguous and unanswerable text-to-SQL examples.
1 code implementation • 8 Aug 2022 • Qianying Lin, Wen-Ji Zhou, Yanshi Wang, Qing Da, Qing-Guo Chen, Bing Wang
SAM supports efficient training and real-time inference for user behavior sequences with lengths on the scale of thousands.
1 code implementation • 15 May 2023 • Bing Wang, Ximing Li, Zhiyao Yang, Yuanyuan Guan, Jiayin Li, Shengsheng Wang
To solve the problems, we fine-tune PLMs by leveraging the frequency information of words and propose a novel USRL framework, namely Sentence Representation Learning with Frequency-induced Adversarial tuning and Incomplete sentence filtering (SLT-FAI).
1 code implementation • 8 Dec 2021 • Xiwen Liang, Fengda Zhu, Yi Zhu, Bingqian Lin, Bing Wang, Xiaodan Liang
The vision-language navigation (VLN) task requires an agent to reach a target with the guidance of natural language instruction.
1 code implementation • 12 Mar 2020 • Kaichen Zhou, Changhao Chen, Bing Wang, Muhamad Risqi U. Saputra, Niki Trigoni, Andrew Markham
We conjecture that this is because of the naive approaches to feature space fusion through summation or concatenation which do not take into account the different strengths of each modality.
no code implementations • 6 Jan 2018 • Li Wang, Ting Liu, Bing Wang, Xulei Yang, Gang Wang
First, we learn RNN parameters to discriminate between the target object and background in the first frame of a test sequence.
no code implementations • 9 Sep 2017 • Mingwei Cao, Ming Yang, Chunxiang Wang, Yeqiang Qian, Bing Wang
In view of contemporary panoramic camera-laser scanner system, the traditional calibration method is not suitable for panoramic cameras whose imaging model is extremely nonlinear.
no code implementations • 15 May 2016 • Bing Wang, Li Wang, Bing Shuai, Zhen Zuo, Ting Liu, Kap Luk Chan, Gang Wang
Then the Siamese CNN and temporally constrained metrics are jointly learned online to construct the appearance-based tracklet affinity models.
no code implementations • 20 Nov 2015 • Bing Wang, Gang Wang, Kap Luk Chan, Li Wang
In this paper, we present a novel method based on online target-specific metric learning and coherent dynamics estimation for tracklet (track fragment) association by network flow optimization in long-term multi-person tracking.
no code implementations • 20 Apr 2016 • Bing Shuai, Zhen Zuo, Gang Wang, Bing Wang
The local beliefs of pixels are output by CNN-Ensemble.
no code implementations • 13 Sep 2015 • Zhen Zuo, Bing Shuai, Gang Wang, Xiao Liu, Xingxing Wang, Bing Wang
In this manuscript, we integrate CNNs with HRNNs, and develop end-to-end convolutional hierarchical recurrent neural networks (C-HRNNs).
no code implementations • CVPR 2016 • Bing Shuai, Zhen Zuo, Gang Wang, Bing Wang
In image labeling, local representations for image units are usually generated from their surrounding image patches, thus long-range contextual information is not effectively encoded.
Ranked #18 on Semantic Segmentation on COCO-Stuff test
no code implementations • 9 Jan 2014 • Bing Wang, Yao-hua Meng, Xiao-hong Yu
For learning problem of Radial Basis Function Process Neural Network (RBF-PNN), an optimization training method based on GA combined with SA is proposed in this paper.
no code implementations • CVPR 2014 • Bing Wang, Gang Wang, Kap Luk Chan, Li Wang
In our method, target-specific similarity metrics are learned, which give rise to the appearance-based models used in the tracklet affinity estimation.
no code implementations • CVPR 2015 • Bing Shuai, Gang Wang, Zhen Zuo, Bing Wang, Lifan Zhao
We adopt Convolutional Neural Networks (CNN) as our parametric model to learn discriminative features and classifiers for local patch classification.
no code implementations • 23 Jun 2019 • Jian-Ya Ding, Chao Zhang, Lei Shen, Shengyin Li, Bing Wang, Yinghui Xu, Le Song
In many applications, a similar MIP model is solved on a regular basis, maintaining remarkable similarities in model structures and solution appearances but differing in formulation coefficients.
no code implementations • 29 Jul 2019 • Hao-Ran Wei, Yue Zhang, Bing Wang, Yang Yang, Hao Li, Hongqi Wang
Motivated by the development of deep convolution neural networks (DCNNs), tremendous progress has been gained in the field of aircraft detection.
no code implementations • 11 Aug 2019 • Changhao Chen, Chris Xiaoxuan Lu, Bing Wang, Niki Trigoni, Andrew Markham
In addition we show how DynaNet can indicate failures through investigation of properties such as the rate of innovation (Kalman Gain).
no code implementations • 25 Nov 2019 • Hao Wang, Bing Wang, Jianyong Duan, Jiajun Zhang
Spelling error detection serves as a crucial preprocessing in many natural language processing applications.
no code implementations • 26 Nov 2019 • Bo Yang, Xianlong Tan, Zhengmao Chen, Bing Wang, Dan Li, Zhongping Yang, Xiping Wu, Yi Lin
To our best knowledge, this is the first work that aims at building a real and multilingual ASR corpus for the air traffic related research.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 30 Dec 2019 • Changhao Chen, Stefano Rosa, Chris Xiaoxuan Lu, Bing Wang, Niki Trigoni, Andrew Markham
By integrating the observations from different sensors, these mobile agents are able to perceive the environment and estimate system states, e. g. locations and orientations.
no code implementations • 26 Oct 2020 • Guibin Chen, BoSheng Wang, Xiaoliang Wang, Huanjun Deng, Bing Wang, Shuo Zhang
Lidar odometry (LO) is a key technology in numerous reliable and accurate localization and mapping systems of autonomous driving.
no code implementations • 15 Dec 2020 • Bing Wang, Jiaqi Quan, Jianfei Han, Xiaopeng Shen, Hongwei Wu, Yiming Pan
The public and scientists constantly have different perspectives.
Quantum Physics Mesoscale and Nanoscale Physics Other Condensed Matter Optics
no code implementations • 31 Dec 2020 • Victoria Manfredi, Alicia Wolfe, Bing Wang, Xiaolan Zhang
While routing in wireless networks has been studied extensively, existing protocols are typically designed for a specific set of network conditions and so cannot accommodate any drastic changes in those conditions.
no code implementations • 21 Sep 2021 • Lin William Cong, Ke Tang, Bing Wang, Jingyuan Wang
We build a deep-learning-based SEIR-AIM model integrating the classical Susceptible-Exposed-Infectious-Removed epidemiology model with forecast modules of infection, community mobility, and unemployment.
no code implementations • 30 Sep 2021 • Yuquan Chen, Fumian Wang, Bing Wang
This paper investigates the fixed-time consensus problem for a class of multi-agent systems with simple dynamics.
no code implementations • 29 Sep 2021 • Qianying Lin, Wen-Ji Zhou, Yanshi Wang, Qing Da, Qing-Guo Chen, Bing Wang
Extensive empirical studies show that our method outperforms various state-of-the-art sequential modeling methods on both public and industrial datasets for long sequential user behavior modeling.
no code implementations • 20 Nov 2021 • Bing Wang, Yue Wang, Ximing Li, Jihong Ouyang
The recent generative dataless methods construct document-specific category priors by using seed word occurrences only, however, such category priors often contain very limited and even noisy supervised signals.
no code implementations • 23 Jul 2022 • Victoria Manfredi, Alicia P. Wolfe, Xiaolan Zhang, Bing Wang
Designing effective routing strategies for mobile wireless networks is challenging due to the need to seamlessly adapt routing behavior to spatially diverse and temporally changing network conditions.
no code implementations • IEEE Transactions on Geoscience and Remote Sensing 2021 • Bing Wang, Zhirui Wang, Xian Sun, Hongqi Wang, Kun fu
After metatraining, DMML-Net can be applied for the few-shot segmentation tasks of novel geographic objects with only a few gradient steps on the small training set.
no code implementations • 7 Mar 2023 • Kai Lu, Bo Yang, Bing Wang, Andrew Markham
Our experiments on manipulating complex articulated objects show that the proposed approach is more generalizable to unseen objects with large intra-class variations, outperforming previous approaches.
no code implementations • 19 May 2023 • Yibo Wang, Wenhao Yang, Wei Jiang, Shiyin Lu, Bing Wang, Haihong Tang, Yuanyu Wan, Lijun Zhang
Specifically, we first provide a novel dynamic regret analysis for an existing projection-free method named $\text{BOGD}_\text{IP}$, and establish an $\mathcal{O}(T^{3/4}(1+P_T))$ dynamic regret bound, where $P_T$ denotes the path-length of the comparator sequence.
no code implementations • 15 Jun 2023 • Junkai Mao, Yuexing Han, Bing Wang
Most of the present spatio-temporal models cannot provide a general framework for stable, and accurate forecasting of epidemics with diverse evolution trends.
no code implementations • 27 Aug 2023 • Changhao Chen, Bing Wang, Chris Xiaoxuan Lu, Niki Trigoni, Andrew Markham
Deep learning based localization and mapping approaches have recently emerged as a new research direction and receive significant attentions from both industry and academia.
Simultaneous Localization and Mapping Visual Localization +1
no code implementations • 30 Aug 2023 • Zhihao Jia, Bing Wang, Changhao Chen
In this work, we propose the Drone-NeRF framework to enhance the efficient reconstruction of unbounded large-scale scenes suited for drone oblique photography using Neural Radiance Fields (NeRF).
1 code implementation • 19 Sep 2023 • Sybille Légitime, Kaustubh Prabhu, Devin McConnell, Bing Wang, Dipak K. Dey, Derek Aguiar
Opioids are an effective analgesic for acute and chronic pain, but also carry a considerable risk of addiction leading to millions of opioid use disorder (OUD) cases and tens of thousands of premature deaths in the United States yearly.
no code implementations • 30 Oct 2023 • Bing Wang, Weizi Li, Anthony Bradlow, Antoni T. Y. Chan, Eghosa Bazuaye
But in practice, blood testing data is not always available at the point of referrals, so we need methods to leverage multimodal data such as semi-structured and unstructured data for early detection of IA.
no code implementations • 1 Dec 2023 • Junkai Mao, Yuexing Han, Gouhei Tanaka, Bing Wang
To capture this property, we use adaptive methods to generate static backbone graphs containing the primary information and temporal models to generate dynamic temporal graphs of epidemic data, fusing them to generate a backbone-based dynamic graph.
no code implementations • 6 Dec 2023 • Yuexing Han, Guanxin Wan, Bing Wang
Finally, the many generated features on the Geodesic curve are used to train the various machine learning models.
no code implementations • 18 Dec 2023 • Jihong Ouyang, Zhiyao Yang, Silong Liang, Bing Wang, Yimeng Wang, Ximing Li
And we propose an ABSA-specific augmentation method to create such augmentations.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +2
no code implementations • 3 Jan 2024 • Yuexing Han, Liheng Ruan, Bing Wang
Images generated by most of generative models trained with limited data often exhibit deficiencies in either fidelity, diversity, or both.
no code implementations • 13 Jan 2024 • Linzheng Chai, Jian Yang, Tao Sun, Hongcheng Guo, Jiaheng Liu, Bing Wang, Xiannian Liang, Jiaqi Bai, Tongliang Li, Qiyao Peng, Zhoujun Li
To bridge the gap among different languages, we propose a cross-lingual instruction fine-tuning framework (xCOT) to transfer knowledge from high-resource languages to low-resource languages.
no code implementations • 3 Feb 2024 • Wenzhi Guo, Bing Wang, Lijun Chen
We introduce NeuV-SLAM, a novel dense simultaneous localization and mapping pipeline based on neural multiresolution voxels, characterized by ultra-fast convergence and incremental expansion capabilities.
no code implementations • 19 Mar 2024 • Ying Chen, Yong liu, Kai Wu, Qiang Nie, Shang Xu, Huifang Ma, Bing Wang, Chengjie Wang
Deep learning-based image matching methods play a crucial role in computer vision, yet they often suffer from substantial computational demands.
no code implementations • 21 Mar 2024 • Lizhe Liu, Bohua Wang, Hongwei Xie, Daqi Liu, Li Liu, Zhiqiang Tian, Kuiyuan Yang, Bing Wang
Vision-centric 3D environment understanding is both vital and challenging for autonomous driving systems.
no code implementations • 21 Mar 2024 • Guangchi Fang, Bing Wang
In this study, we explore the challenge of efficiently representing scenes with a constrained number of Gaussians.
no code implementations • 24 Mar 2024 • Dongrui Liu, Daqi Liu, Xueqian Li, Sihao Lin, Hongwei Xie, Bing Wang, Xiaojun Chang, Lei Chu
Neural Scene Flow Prior (NSFP) and Fast Neural Scene Flow (FNSF) have shown remarkable adaptability in the context of large out-of-distribution autonomous driving.
no code implementations • 26 Mar 2024 • Jian Yang, Hongcheng Guo, Yuwei Yin, Jiaqi Bai, Bing Wang, Jiaheng Liu, Xinnian Liang, Linzheng Cahi, Liqun Yang, Zhoujun Li
Our method aims to minimize the representation distance of different languages by regarding the image as a central language.
no code implementations • 15 Apr 2024 • Yuexing Han, Guanxin Wan, Bing Wang, Yi Liu
These outcomes underscore the potential of FAGC to address the challenge of limited image data in materials science, providing a powerful tool for establishing detailed and quantitative relationships between complex microstructures and material properties.