1 code implementation • 5 Feb 2025 • Xingye Chen, Wei Feng, Zhenbang Du, Weizhen Wang, Yanyin Chen, Haohan Wang, Linkai Liu, Yaoyu Li, Jinyuan Zhao, Yu Li, Zheng Zhang, Jingjing Lv, Junjie Shen, Zhangang Lin, Jingping Shao, Yuanjie Shao, Xinge You, Changxin Gao, Nong Sang
In web data, advertising images are crucial for capturing user attention and improving advertising effectiveness.
no code implementations • 25 Jan 2025 • Lei Wang, Xiao-Feng Gong, Xi-Yuan Liu, Wei Feng, Qiu-Hua Lin
We consider tensor data completion of an incomplete observation of multidimensional harmonic (MH) signals.
no code implementations • 25 Jan 2025 • Xi-Yuan Liu, Xiao-Feng Gong, Lei Wang, Wei Feng, Qiu-Hua Lin
Recently, coupled tensor decomposition has been widely used in data fusion of a hyperspectral image (HSI) and a multispectral image (MSI) for hyperspectral super-resolution (HSR).
no code implementations • 9 Jan 2025 • Wei Tang, Jiawei Yu, Yuang Li, Yanqing Zhao, Weidong Zhang, Wei Feng, Min Zhang, Hao Yang
The inaccurate translation of numbers can lead to significant security issues, ranging from financial setbacks to medical inaccuracies.
1 code implementation • 9 Dec 2024 • Lianyu Hu, Fanhua Shang, Liang Wan, Wei Feng
iLLaVA can nearly 2$\times$ the throughput, and reduce the memory costs by half with only a 0. 2\% - 0. 5\% performance drop across models of different scales including 7B, 13B and 34B.
no code implementations • 6 Dec 2024 • Yaojie Zhang, Tianlun Huang, Weijun Wang, Wei Feng
Traditional point cloud registration (PCR) methods for feature matching often employ the nearest neighbor policy.
no code implementations • 24 Oct 2024 • Xinran Fang, Chengleyang Lei, Wei Feng, Yunfei Chen, Ning Ge, Shi Jin
To maintain the task-level connections between the sensor-computing center link and the computing center-actuator link, we propose to treat the sensor and actuator as a virtual user.
no code implementations • 24 Oct 2024 • Xinran Fang, Chengleyang Lei, Wei Feng, Yunfei Chen, Ming Xiao, Ning Ge, Chengxiang Wang
We derive optimal closed-form solutions for intra-loop allocation and propose an efficient iterative algorithm for inter-loop optimization.
1 code implementation • 11 Oct 2024 • Houlun Chen, Xin Wang, Hong Chen, Zeyang Zhang, Wei Feng, Bin Huang, Jia Jia, Wenwu Zhu
In this paper, we propose a more challenging fine-grained VCMR benchmark requiring methods to localize the best-matched moment from the corpus with other partially matched candidates.
no code implementations • 11 Oct 2024 • Zekun Qian, Ruize Han, Junhui Hou, Linqi Song, Wei Feng
In this paper, we propose VOVTrack, a novel method that integrates object states relevant to MOT and video-centric training to address this challenge from a video object tracking standpoint.
1 code implementation • 9 Oct 2024 • Lianyu Hu, Tongkai Shi, Wei Feng, Fanhua Shang, Liang Wan
Plentiful ablations are further given to show the generalizability and reliability of our method upon different modality-missing ratios and types.
1 code implementation • 9 Oct 2024 • Wanchao Liang, Tianyu Liu, Less Wright, Will Constable, Andrew Gu, Chien-chin Huang, Iris Zhang, Wei Feng, Howard Huang, Junjie Wang, Sanket Purandare, Gokul Nadathur, Stratos Idreos
By stacking training optimizations, we demonstrate accelerations of 65. 08% with 1D parallelism at the 128-GPU scale (Llama 3. 1 8B), an additional 12. 59% with 2D parallelism at the 256-GPU scale (Llama 3. 1 70B), and an additional 30% with 3D parallelism at the 512-GPU scale (Llama 3. 1 405B) on NVIDIA H100 GPUs over optimized baselines.
no code implementations • 25 Sep 2024 • Tongkai Shi, Lianyu Hu, Fanhua Shang, Jichao Feng, Peidong Liu, Wei Feng
To address these limitations, we propose a novel Pose-Guided Motion Model (PGMM) for generating fine-grained and motion-consistent sign language videos.
no code implementations • 23 Sep 2024 • Hong Chen, Xin Wang, Yuwei Zhou, Bin Huang, YiPeng Zhang, Wei Feng, Houlun Chen, Zeyang Zhang, Siao Tang, Wenwu Zhu
Particularly, two dominant families of techniques are: i) The multi-modal large language model (MLLM) such as GPT-4V, which shows impressive ability for multi-modal understanding; ii) The diffusion model such as Sora, which exhibits remarkable multi-modal powers, especially with respect to visual generation.
no code implementations • 8 Sep 2024 • Yaojie Zhang, Weijun Wang, Tianlun Huang, Zhiyong Wang, Wei Feng
Partial to Partial Point Cloud Registration (partial PCR) remains a challenging task, particularly when dealing with a low overlap rate.
1 code implementation • 1 Aug 2024 • Zhenbang Du, Wei Feng, Haohan Wang, Yaoyu Li, Jingsen Wang, Jian Li, Zheng Zhang, Jingjing Lv, Xin Zhu, Junsheng Jin, Junjie Shen, Zhangang Lin, Jingping Shao
In the e-commerce realm, compelling advertising images are pivotal for attracting customer attention.
no code implementations • 19 Jul 2024 • Zekun Qian, Ruize Han, Wei Feng, Junhui Hou, Linqi Song, Song Wang
We study a novel yet practical problem of open-corpus multi-object tracking (OCMOT), which extends the MOT into localizing, associating, and recognizing generic-category objects of both seen (base) and unseen (novel) classes, but without the category text list as prompt.
no code implementations • 18 Jul 2024 • Wei Feng, Xin Wang, Hong Chen, Zeyang Zhang, Wenwu Zhu
(iii) We also attempt video morphing and personalized generation methods to improve the subject consistency of long video generation, providing ablation experimental results for the subtasks of long video generation.
1 code implementation • 11 Jul 2024 • Li Yuepan, Fan Lyu, Yuyang Li, Wei Feng, Guangcan Liu, Fanhua Shang
Parallel Continual Learning (PCL) tasks investigate the training methods for continual learning with multi-source input, where data from different tasks are learned as they arrive.
no code implementations • 5 Jul 2024 • Long Teng, Wei Feng, Menglong Zhu, Xinchao Li
Thus it is difficult to perform supervised learning for motion tracking.
1 code implementation • 26 Jun 2024 • Yiguo Jiang, Xuhang Chen, Chi-Man Pun, Shuqiang Wang, Wei Feng
The low-frequency part typically contains illumination information, while the high-frequency part contains detailed content information.
no code implementations • 6 Jun 2024 • Shufan Zhang, Minda Ma, Nan Zhou, Jinyue Yan, Wei Feng, Ran Yan, Kairui You, Jingjing Zhang, Jing Ke
Buildings produce one-third of carbon emissions globally, however, data absence regarding global floorspace poses challenges in advancing building carbon neutrality.
2 code implementations • 23 May 2024 • Ziqi Shi, Fan Lyu, Ye Liu, Fanhua Shang, Fuyuan Hu, Wei Feng, Zhang Zhang, Liang Wang
Continual Test-Time Adaptation (CTTA) is an emerging and challenging task where a model trained in a source domain must adapt to continuously changing conditions during testing, without access to the original source data.
no code implementations • 15 May 2024 • Fan Lyu, Daofeng Liu, Linglan Zhao, Zhang Zhang, Fanhua Shang, Fuyuan Hu, Wei Feng, Liang Wang
Moreover, the continual doman drift in sequential learning tasks may entail the gradual displacement of the decision boundaries in the learned feature space, rendering the learned knowledge susceptible to forgetting.
1 code implementation • 17 Apr 2024 • Lianyu Hu, Wei Feng, Liqing Gao, Zekang Liu, Liang Wan
In specific, CorrNet+ employs a correlation module and an identification module to build human body trajectories.
no code implementations • 14 Apr 2024 • Haosong Peng, Wei Feng, Hao Li, Yufeng Zhan, Ren Jin, Yuanqing Xia
Through extensive experiments, our findings reveal that Arena can boost inference speeds by up to 1. 58\(\times\) and 1. 82\(\times\) on average while consuming only 47\% and 31\% of the bandwidth, respectively, all with high inference accuracy.
1 code implementation • 12 Apr 2024 • Lianyu Hu, Tongkai Shi, Liqing Gao, Zekang Liu, Wei Feng
Besides, fully fine-tuning the model easily forgets the generic essential knowledge acquired in the pretraining stage and overfits the downstream data.
1 code implementation • 9 Apr 2024 • Jianlang Chen, Xuhong Ren, Qing Guo, Felix Juefei-Xu, Di Lin, Wei Feng, Lei Ma, Jianjun Zhao
To achieve high accuracy on both clean and adversarial data, we propose building a spatial-temporal continuous representation using the semantic text guidance of the object of interest.
1 code implementation • 19 Mar 2024 • Lianyu Hu, Liqing Gao, Zekang Liu, Wei Feng
Current methods utilize spatial graph modules and temporal modules to capture spatial and temporal features, respectively.
1 code implementation • CVPR 2024 • Feilong Tang, Zhongxing Xu, Zhaojun Qu, Wei Feng, Xingjian Jiang, ZongYuan Ge
Inspired by prototype learning theory, we propose leveraging prototype awareness to capture diverse and fine-grained feature attributes of instances.
no code implementations • 11 Mar 2024 • Chengleyang Lei, Wei Feng, Peng Wei, Yunfei Chen, Ning Ge, Shiwen Mao
Specifically, the linear quadratic regulator (LQR) control cost is used to measure the closed-loop utility, and a sum LQR cost minimization problem is formulated to jointly optimize the splitting of sensor data and allocation of communication and computing resources.
no code implementations • 3 Feb 2024 • Xiangqun Zhang, Ruize Han, Wei Feng
In this paper, we study a new problem of cross-domain video based person re-identification (Re-ID).
1 code implementation • 31 Jan 2024 • Wei Feng, Feifan Wang, Ruize Han, Zekun Qian, Song Wang
Multi-view multi-human association and tracking (MvMHAT), is a new but important problem for multi-person scene video surveillance, aiming to track a group of people over time in each view, as well as to identify the same person across different views at the same time, which is different from previous MOT and multi-camera MOT tasks only considering the over-time human tracking.
no code implementations • 2 Jan 2024 • Fan Lyu, Wei Feng, Yuepan Li, Qing Sun, Fanhua Shang, Liang Wan, Liang Wang
The goal of Continual Learning (CL) is to continuously learn from new data streams and accomplish the corresponding tasks.
1 code implementation • 30 Dec 2023 • Lianyu Hu, Liqing Gao, Zekang Liu, Chi-Man Pun, Wei Feng
First, the prompts of the vision and language branches in these methods are usually separated or uni-directionally correlated.
no code implementations • 21 Dec 2023 • Wei Feng, Xin Wang, Hong Chen, Zeyang Zhang, Houlun Chen, Zihan Song, Yuwei Zhou, Yuekui Yang, Haiyang Wu, Wenwu Zhu
Recently, researchers have attempted to investigate the capability of LLMs in handling videos and proposed several video LLM models.
1 code implementation • 20 Dec 2023 • Haohan Wang, Wei Feng, Yaoyu Li, Zheng Zhang, Jingjing Lv, Junjie Shen, Zhangang Lin, Jingping Shao
Furthermore, for products with specific and fine-grained requirements in layout, elements, etc, a Personality-Wise Generator is devised to learn such personalized style directly from a reference image to resolve textual ambiguities, and is trained in a self-supervised manner for more efficient training data usage.
no code implementations • 14 Dec 2023 • Zhaochen Li, Fengheng Li, Wei Feng, Honghe Zhu, Yaoyu Li, Zheng Zhang, Jingjing Lv, Junjie Shen, Zhangang Lin, Jingping Shao, Zhenglu Yang
At the planning stage, we propose a PlanNet to generate the layout of the product and other visual components considering both the appearance features of the product and semantic features of the text, which improves the diversity and rationality of the layouts.
no code implementations • 31 Oct 2023 • Weiqi Li, Fan Lyu, Fanhua Shang, Liang Wan, Wei Feng
Real-world data is extremely imbalanced and presents a long-tailed distribution, resulting in models that are biased towards classes with sufficient samples and perform poorly on rare classes.
no code implementations • 28 Sep 2023 • Wei Feng, Lie Ju, Lin Wang, Kaimin Song, ZongYuan Ge
We conducted extensive experiments on the dermatology dataset ISIC 2019, and the experimental results show that our approach can effectively leverage knowledge from known categories to discover new semantic categories.
2 code implementations • 21 Aug 2023 • Zhijin Ge, Fanhua Shang, Hongying Liu, Yuanyuan Liu, Liang Wan, Wei Feng, Xiaosen Wang
Deep neural networks are vulnerable to adversarial examples crafted by applying human-imperceptible perturbations on clean inputs.
1 code implementation • 16 Aug 2023 • Lianyu Hu, Liqing Gao, Zekang Liu, Chi-Man Pun, Wei Feng
Then these features are fed into a policy network to intelligently select a subsequence to process.
Ranked #9 on
Sign Language Recognition
on CSL-Daily
no code implementations • 7 Aug 2023 • Xinran Fang, Wei Feng, Yunfei Chen, Ning Ge, Gan Zheng
In this paper, we propose a communication optimization scheme for a specific cooperation system named the "mother-daughter system".
1 code implementation • 26 Jun 2023 • Yun Guo, Wei Feng, Zheng Zhang, Xiancong Ren, Yaoyu Li, Jingjing Lv, Xin Zhu, Zhangang Lin, Jingping Shao
Product image segmentation is vital in e-commerce.
no code implementations • 24 Jun 2023 • Ran Yan, Nan Zhou, Wei Feng, Minda Ma, Xiwang Xiang, Chao Mao
(2) Building electrification played a significant role in decarbonizing space cooling (-87. 7 in China and -130. 2 kilograms of carbon dioxide (kgCO2) per household in India) and appliances (-169. 7 in China and -43. 4 kgCO2 per household in India).
1 code implementation • 15 Jun 2023 • Fengheng Li, An Liu, Wei Feng, Honghe Zhu, Yaoyu Li, Zheng Zhang, Jingjing Lv, Xin Zhu, Junjie Shen, Zhangang Lin, Jingping Shao
To advance research in this field, we have constructed a poster layout dataset named CGL-Dataset V2.
no code implementations • 18 May 2023 • Xiaoguang Li, Qing Guo, Pingping Cai, Wei Feng, Ivor Tsang, Song Wang
State-of-the-art shadow removal methods train deep neural networks on collected shadow & shadow-free image pairs, which are desired to complete two distinct tasks via shared weights, i. e., data restoration for shadow regions and identical mapping for non-shadow regions.
no code implementations • 17 May 2023 • Wei Feng, Lvwei Wang, Zaiyun Lin, Yanhao Zhu, Han Wang, Jianqiang Dong, Rong Bai, Huting Wang, Jielong Zhou, Wei Peng, Bo Huang, Wenbiao Zhou
Generative models for molecules based on sequential line notation (e. g.
no code implementations • 19 Apr 2023 • Ruan Lu, Zhou HangCheng, Ran Meng, Zhao Jin, Qin JiaoYu, Wei Feng, Wang ChenZi
The challenges faced by text classification with large tag systems in natural language processing tasks include multiple tag systems, uneven data distribution, and high noise.
1 code implementation • 8 Apr 2023 • Lie Ju, Yicheng Wu, Wei Feng, Zhen Yu, Lin Wang, Zhuoting Zhu, ZongYuan Ge
However, in practical scenarios, unlabeled data would be from unseen classes or unseen domains, and it is still challenging to exploit them by existing SSL methods.
no code implementations • 23 Mar 2023 • Bo Zhang, Zuheng Ming, Wei Feng, Yaqian Liu, Liang He, Kaixing Zhao
To benefit the complementary information between heterogeneous data, we introduce a new Multimodal Transformer (MMFormer) for Remote Sensing (RS) image classification using Hyperspectral Image (HSI) accompanied by another source of data such as Light Detection and Ranging (LiDAR).
3 code implementations • CVPR 2023 • Lianyu Hu, Liqing Gao, Zekang Liu, Wei Feng
Visualizations demonstrate the effects of CorrNet on emphasizing human body trajectories across adjacent frames.
1 code implementation • ICCV 2023 • Xiaoguang Li, Qing Guo, Rabab Abdelfattah, Di Lin, Wei Feng, Ivor Tsang, Song Wang
In this work, we find that pretraining shadow removal networks on the image inpainting dataset can reduce the shadow remnants significantly: a naive encoder-decoder network gets competitive restoration quality w. r. t.
no code implementations • 9 Jan 2023 • Yuhao Liu, Qing Guo, Lan Fu, Zhanghan Ke, Ke Xu, Wei Feng, Ivor W. Tsang, Rynson W. H. Lau
Hence, in this paper, we propose to remove shadows at the image structure level.
no code implementations • ICCV 2023 • Fan Lyu, Qing Sun, Fanhua Shang, Liang Wan, Wei Feng
In Parallel Continual Learning (PCL), the parallel multiple tasks start and end training unpredictably, thus suffering from training conflict and catastrophic forgetting issues.
1 code implementation • CVPR 2024 • Zekun Qian, Ruize Han, Wei Feng, Feifan Wang, Song Wang
We tackle a new problem of multi-view camera and subject registration in the bird's eye view (BEV) without pre-given camera calibration.
1 code implementation • 5 Dec 2022 • Xi Zhao, Wei Feng, Zheng Zhang, Jingjing Lv, Xin Zhu, Zhangang Lin, Jinghe Hu, Jingping Shao
Recently, segmentation-based methods are quite popular in scene text detection, which mainly contain two steps: text kernel segmentation and expansion.
2 code implementations • 30 Nov 2022 • Lianyu Hu, Liqing Gao, Zekang Liu, Wei Feng
To relieve this problem, we propose a self-emphasizing network (SEN) to emphasize informative spatial regions in a self-motivated way, with few extra computations and without additional expensive supervision.
Ranked #10 on
Sign Language Recognition
on CSL-Daily
no code implementations • 27 Nov 2022 • Kaile Du, Fan Lyu, Linyan Li, Fuyuan Hu, Wei Feng, Fenglei Xu, Xuefeng Xi, Hanjing Cheng
In contrast, the inter-task relationships leverage hard and soft labels from data and a constructed expert network.
no code implementations • 21 Nov 2022 • Likai Wang, Ruize Han, Wei Feng, Song Wang
In this paper, we study a new problem of unsupervised domain adaptive gait recognition (UDA-GR), that learns a gait identifier with supervised labels from the indoor scenes (source domain), and is applied to the outdoor wild scenes (target domain).
1 code implementation • 21 Nov 2022 • Likai Wang, Xiangqun Zhang, Ruize Han, Jialin Yang, Xiaoyu Li, Wei Feng, Song Wang
In this paper, we focus on the relatively new yet practical problem of clothes-changing video-based person re-identification (CCVReID), which is less studied.
no code implementations • IEEE Transactions on Network Science and Engineering 2022 • Jiachen Sun, Ning Ge, Xu Chen, Wei Feng, Jianhua Lu
This screening algorithm is customer-oriented and offers personalized commodities by preventing unqualified sellers from participating in the transaction.
no code implementations • 11 Oct 2022 • Lin Wang, Xiufen Ye, Donghao Zhang, Wanji He, Lie Ju, Yi Luo, Huan Luo, Xin Wang, Wei Feng, Kaimin Song, Xin Zhao, ZongYuan Ge
In this work, we introduce the image matting into the 3D scenes and use the alpha matte, i. e., a soft mask, to describe lesions in a 3D medical image.
1 code implementation • 25 Sep 2022 • Qing Sun, Fan Lyu, Fanhua Shang, Wei Feng, Liang Wan
Continual Learning (CL) sequentially learns new tasks like human beings, with the goal to achieve better Stability (S, remembering past tasks) and Plasticity (P, adapting to new tasks).
no code implementations • 23 Sep 2022 • Cunling Bian, Wei Feng, Fanbo Meng, Song Wang
Skeleton-based human action recognition has been drawing more interest recently due to its low sensitivity to appearance changes and the accessibility of more skeleton data.
no code implementations • 16 Sep 2022 • Lin Wang, Xiufen Ye, Donghao Zhang, Wanji He, Lie Ju, Xin Wang, Wei Feng, Kaimin Song, Xin Zhao, ZongYuan Ge
It can be caused by many factors, such as the imaging properties, pathological anatomy, and the weak representation of the binary masks, which brings challenges to accurate 3D segmentation.
no code implementations • 31 Aug 2022 • Chengleyang Lei, Wei Feng, Jue Wang, Shi Jin, Ning Ge
This letter presents a sensing-communication-computing-control (SC3) integrated satellite unmanned aerial vehicle (UAV) network, where the UAV is equipped with on-board sensors, mobile edge computing (MEC) servers, base stations and satellite communication module.
no code implementations • 19 Aug 2022 • Wei Feng, Ruochen Huang, Yun Yu, Huiting Sun, Yun Liu
Event extraction is an important work of medical text processing.
1 code implementation • 18 Aug 2022 • Lianyu Hu, Shenglan Liu, Wei Feng
In such conditions, short-term dependencies are few formally considered, which are critical for classifying similar actions.
Ranked #1 on
Skeleton Based Action Recognition
on Kinetics-400
no code implementations • 16 Aug 2022 • Yueshan Lin, Wei Feng, Ting Zhou, Yanmin Wang, Yunfei Chen, Ning Ge, Cheng-Xiang Wang
The sixth-generation (6G) network will shift its focus to supporting everything including various machine-type devices (MTDs) in an everyone-centric manner.
1 code implementation • 18 Jul 2022 • Lianyu Hu, Liqing Gao, Zekang Liu, Wei Feng
In this paper, we derive temporal lift pooling (TLP) from the Lifting Scheme in signal processing to intelligently downsample features of different temporal hierarchies.
1 code implementation • 8 Jul 2022 • Wei Feng, Lin Wang, Lie Ju, Xin Zhao, Xin Wang, Xiaoyu Shi, ZongYuan Ge
Existing unsupervised domain adaptation methods based on adversarial learning have achieved good performance in several medical imaging tasks.
no code implementations • 19 May 2022 • Xinran Fang, Wei Feng, Yunfei Chen, Ning Ge, Yan Zhang
In this survey, we discuss joint communication and sensing (JCAS) in the context of MIMO.
no code implementations • 25 Apr 2022 • Ruize Han, Wei Feng, Qing Guo, QinGhua Hu
Visual object tracking is an important task in computer vision, which has many real-world applications, e. g., video surveillance, visual navigation.
no code implementations • 13 Apr 2022 • Nan Li, Wei Feng, Qian Zhang
Active camera relocalization (ACR) is a new problem in computer vision that significantly reduces the false alarm caused by image distortions due to camera pose misalignment in fine-grained change detection (FGCD).
1 code implementation • CVPR 2022 • Xiaoguang Li, Qing Guo, Di Lin, Ping Li, Wei Feng, Song Wang
As a result, the final method takes the advantage of effective semantic & image-level filling for high-fidelity inpainting.
1 code implementation • 10 Mar 2022 • Kaile Du, Fan Lyu, Fuyuan Hu, Linyan Li, Wei Feng, Fenglei Xu, Qiming Fu
The key challenges of LML image recognition are the construction of label relationships on Partial Labels of training data and the Catastrophic Forgetting on old classes, resulting in poor generalization.
1 code implementation • 8 Mar 2022 • Jiacheng Li, Ruize Han, Haomin Yan, Zekun Qian, Wei Feng, Song Wang
The core of human group detection is the human social relation representation and division. In this paper, we propose a new two-stage multi-head framework for human group detection.
1 code implementation • 8 Mar 2022 • Ruize Han, Haomin Yan, Jiacheng Li, Songmiao Wang, Wei Feng, Song Wang
To obtain a more comprehensive activity understanding for a crowded scene, in this paper, we propose a new problem of panoramic human activity recognition (PAR), which aims to simultaneous achieve the individual action, social group activity, and global activity recognition.
no code implementations • 22 Feb 2022 • Likai Wang, Ruize Han, Wei Feng
Gait recognition, a long-distance biometric technology, has aroused intense interest recently.
no code implementations • 27 Jan 2022 • Peng Wei, Kun Guo, Ye Li, Jue Wang, Wei Feng, Shi Jin, Ning Ge, Ying-Chang Liang
Mobile edge computing (MEC) is considered a novel paradigm for computation-intensive and delay-sensitive tasks in fifth generation (5G) networks and beyond.
1 code implementation • 7 Jan 2022 • Qing Guo, Jingyang Sun, Felix Juefei-Xu, Lei Ma, Di Lin, Wei Feng, Song Wang
First, we propose the uncertainty-aware cascaded predictive filtering (UC-PFilt) that can identify the difficulties of reconstructing clean pixels via predicted kernels and remove the residual rain traces effectively.
1 code implementation • CVPR 2022 • Ruize Han, Yiyang Gan, Jiacheng Li, Feifan Wang, Wei Feng, Song Wang
In this paper, we develop a new approach that can simultaneously handle three tasks: i) localizing the side-view camera in the top view; ii) estimating the view direction of the side-view camera; iii) detecting and associating the same subjects on the ground across the complementary views.
no code implementations • 9 Dec 2021 • Tielang Gong, Yuxin Dong, Hong Chen, Bo Dong, Wei Feng, Chen Li
Our results show that the Markov dependence impacts on the generalization error in the way that sample size would be discounted by a multiplicative factor depending on the spectral gap of underlying Markov chain.
no code implementations • 27 Nov 2021 • Lan Fu, Qing Guo, Felix Juefei-Xu, Hongkai Yu, Wei Feng, Yang Liu, Song Wang
The observation of this work motivates us to design a novel detection-aware shadow removal framework, which empowers shadow removal to achieve higher restoration quality and enhance the shadow robustness of deployed facial landmark detectors.
no code implementations • 29 Sep 2021 • Qing Sun, Fan Lyu, Fanhua Shang, Wei Feng, Liang Wan
Traditionally, the primary goal of LL is to achieve the trade-off between the Stability (remembering past tasks) and Plasticity (adapting to new tasks).
1 code implementation • ICCV 2021 • Yujun Zhang, Lei Zhu, Wei Feng, Huazhu Fu, Mingqian Wang, Qingxia Li, Cheng Li, Song Wang
Lane detection plays a key role in autonomous driving.
no code implementations • 18 Aug 2021 • Qian Zhang, Qing Guo, Ruijun Gao, Felix Juefei-Xu, Hongkai Yu, Wei Feng
To this end, we first propose the physical modelbased adversarial relighting attack (ARA) denoted as albedoquotient-based adversarial relighting attack (AQ-ARA).
1 code implementation • 6 Aug 2021 • Ye Liu, Lei Zhu, Shunda Pei, Huazhu Fu, Jing Qin, Qing Zhang, Liang Wan, Wei Feng
Our DID-Net predicts the three component maps by progressively integrating features across scales, and refines each map by passing an independent refinement network.
Ranked #8 on
Image Dehazing
on Haze4k
no code implementations • 4 Aug 2021 • Wei Feng, Lie Ju, Lin Wang, Kaimin Song, Xin Wang, Xin Zhao, Qingyi Tao, ZongYuan Ge
In this work, we explore unsupervised domain adaptation in retinal vessel segmentation by using entropy-based adversarial learning and transfer normalization layer to train a segmentation network, which generalizes well across domains and requires no annotation of the target domain.
no code implementations • 28 Jul 2021 • Qing Guo, Zhijie Wang, Felix Juefei-Xu, Di Lin, Lei Ma, Wei Feng, Yang Liu
3D point cloud completion is very challenging because it heavily relies on the accurate understanding of the complex 3D shapes (e. g., high-curvature, concave/convex, and hollowed-out 3D shapes) and the unknown & diverse patterns of the partially available point clouds.
no code implementations • CVPR 2021 • Wei Feng, Fei Yin, Xu-Yao Zhang, Cheng-Lin Liu
To overcome the lack of character-level annotations, we propose a novel weakly-supervised character center detection module, which only uses word-level annotated real images to generate character-level labels.
no code implementations • 18 May 2021 • Qing Guo, Felix Juefei-Xu, Changqing Zhou, Wei Feng, Yang Liu, Song Wang
In both cases, Sparta leads to CNNs with higher robustness than the vanilla ReLU, verifying the flexibility and versatility of the proposed method.
no code implementations • 28 Apr 2021 • Ruijun Gao, Qing Guo, Felix Juefei-Xu, Hongkai Yu, Wei Feng
We also visualize the correlation matrices, which inspire us to jointly apply different perturbations to improve the success rate of the attack.
no code implementations • 1 Mar 2021 • Chengxiao Liu, Wei Feng, Xiaoming Tao, Ning Ge
Nevertheless, communication and MEC systems are coupled with each other under the influence of complex propagation environment in the MEC-empowered NTN, which makes it hard to orchestrate the resources.
2 code implementations • CVPR 2021 • Lan Fu, Changqing Zhou, Qing Guo, Felix Juefei-Xu, Hongkai Yu, Wei Feng, Yang Liu, Song Wang
We conduct extensive experiments on the ISTD, ISTD+, and SRD datasets to validate our method's effectiveness and show better performance in shadow regions and comparable performance in non-shadow regions over the state-of-the-art methods.
Ranked #6 on
Shadow Removal
on ISTD+
no code implementations • 21 Jan 2021 • Shaoxing Mo, Yulong Zhong, Xiaoqing Shi, Wei Feng, Xin Yin, Jichun Wu
The Gravity Recovery and Climate Experiment (GRACE) satellite and its successor GRACE Follow-On (GRACE-FO) provide valuable and accurate observations of terrestrial water storage anomalies (TWSAs) at a global scale.
no code implementations • 1 Jan 2021 • Qing Guo, Felix Juefei-Xu, Changqing Zhou, Lei Ma, Xiaofei Xie, Wei Feng, Yang Liu
Moreover, comprehensive evaluations have demonstrated two important properties of our method: First, superior transferability across DNNs.
no code implementations • 14 Dec 2020 • Fan Lyu, Shuai Wang, Wei Feng, Zihan Ye, Fuyuan Hu, Song Wang
Rehearsal, seeking to remind the model by storing old knowledge in lifelong learning, is one of the most effective ways to mitigate catastrophic forgetting, i. e., biased forgetting of previous knowledge when moving to new tasks.
no code implementations • 1 Dec 2020 • Mengbiao Zhao, Wei Feng, Fei Yin, Xu-Yao Zhang, Cheng-Lin Liu
We propose an Expectation-Maximization (EM) based weakly-supervised learning framework to train an accurate arbitrary-shaped text detector using only a small amount of polygon-level annotated data combined with a large amount of weakly annotated data.
1 code implementation • CVPR 2022 • Ruijun Gao, Qing Guo, Felix Juefei-Xu, Hongkai Yu, Huazhu Fu, Wei Feng, Yang Liu, Song Wang
In this paper, we address this problem from the perspective of adversarial attacks and identify a novel task: adversarial co-saliency attack.
no code implementations • 19 Sep 2020 • Liming Zhai, Felix Juefei-Xu, Qing Guo, Xiaofei Xie, Lei Ma, Wei Feng, Shengchao Qin, Yang Liu
To defend the DNNs from the negative rain effect, we also present a defensive deraining strategy, for which we design an adversarial rain augmentation that uses mixed adversarial rain layers to enhance deraining models for downstream DNN perception.
2 code implementations • 19 Sep 2020 • Qing Guo, Jingyang Sun, Felix Juefei-Xu, Lei Ma, Xiaofei Xie, Wei Feng, Yang Liu
To fill this gap, in this paper, we regard the single-image deraining as a general image-enhancing problem and originally propose a model-free deraining method, i. e., EfficientDeRain, which is able to process a rainy image within 10~ms (i. e., around 6~ms on average), over 80 times faster than the state-of-the-art method (i. e., RCDNet), while achieving similar de-rain effects.
no code implementations • 17 Sep 2020 • Jianyu Cao, Wei Feng, Ning Ge, Jianhua Lu
Only a few research efforts have been devoted to other random delay characteristics, such as the delay bound violation probability and the probability distribution of the delay, by decoupling the transmission and computation processes of MEC.
no code implementations • 22 Jul 2020 • Chengxiao Liu, Wei Feng, Yunfei Chen, Cheng-Xiang Wang, Ning Ge
In fifth generation (5G) and beyond Internet of Things (IoT), it becomes increasingly important to serve a massive number of IoT devices outside the coverage of terrestrial cellular networks.
no code implementations • 14 Jul 2020 • Yupeng Cheng, Qing Guo, Felix Juefei-Xu, Wei Feng, Shang-Wei Lin, Weisi Lin, Yang Liu
To this end, we initiate the very first attempt to study this problem from the perspective of adversarial attack and propose the adversarial denoise attack.
no code implementations • 13 Jun 2020 • Hua Qi, Qing Guo, Felix Juefei-Xu, Xiaofei Xie, Lei Ma, Wei Feng, Yang Liu, Jianjun Zhao
As the GAN-based face image and video generation techniques, widely known as DeepFakes, have become more and more matured and realistic, there comes a pressing and urgent demand for effective DeepFakes detectors.
no code implementations • 1 Jun 2020 • Xiangling Li, Wei Feng, Jue Wang, Yunfei Chen, Ning Ge, Cheng-Xiang Wang
In this paper, we study the integration of UAVs with existing MCNs, and investigate the potential gains of hybrid satellite-UAV-terrestrial networks for maritime coverage.
no code implementations • 24 Mar 2020 • Zhongguo Li, Fan Lyu, Wei Feng, Song Wang
Paired egocentric interaction recognition (PEIR) is the task to collaboratively recognize the interactions between two persons with the videos in their corresponding views.
no code implementations • 18 Mar 2020 • Shuai Wang, Fan Lyu, Wei Feng, Song Wang
In this paper, we argue that for REC the referring expression and the target region are semantically correlated and subject, location and relationship consistency exist between vision and language. On top of this, we propose a novel approach called MutAtt to construct mutual guidance between vision and language, which treat vision and language equally thus yield compact information matching.
no code implementations • 22 Feb 2020 • Qian Zhang, Wei Feng, Liang Wan, Fei-Peng Tian, Xiaowei Wang, Ping Tan
Besides, we also theoretically prove the invariance of our ALR approach to the ambiguity of normal and lighting decomposition.
1 code implementation • 14 Feb 2020 • Qiang Li, Wei Feng
By using the public data from Jan. 20 to Feb. 11, 2020, we perform data-driven analysis and forecasting on the COVID-19 epidemic in mainland China, especially Hubei province.
1 code implementation • NeurIPS 2020 • Qing Guo, Felix Juefei-Xu, Xiaofei Xie, Lei Ma, Jian Wang, Bing Yu, Wei Feng, Yang Liu
Besides, the attack is further enhanced by adaptively tuning the translations of object and background.
1 code implementation • ECCV 2020 • Qing Guo, Xiaofei Xie, Felix Juefei-Xu, Lei Ma, Zhongguo Li, Wanli Xue, Wei Feng, Yang Liu
We identify that online object tracking poses two new challenges: 1) it is difficult to generate imperceptible perturbations that can transfer across frames, and 2) real-time trackers require the attack to satisfy a certain level of efficiency.
no code implementations • ICCV 2019 • Wei Feng, Wenhao He, Fei Yin, Xu-Yao Zhang, Cheng-Lin Liu
Motivated from the name of TextSnake, which is only a detection model, we call the proposed text spotting framework TextDragon.
Ranked #11 on
Text Spotting
on SCUT-CTW1500
1 code implementation • ICLR 2020 • Xiaoran Xu, Wei Feng, Yunsheng Jiang, Xiaohui Xie, Zhiqing Sun, Zhi-Hong Deng
We propose Dynamically Pruned Message Passing Networks (DPMPN) for large-scale knowledge graph reasoning.
no code implementations • 21 Aug 2019 • Qing Guo, Wei Feng, Zhihao Chen, Ruijun Gao, Liang Wan, Song Wang
In this paper, we address these two problems by constructing a Blurred Video Tracking benchmark, which contains a variety of videos with different levels of motion blurs, as well as ground truth tracking results for evaluating trackers.
no code implementations • 6 Aug 2019 • Zheng Liu, Zidong Jiang, Wei Feng, Hui Feng
Classical CNN based object detection methods only extract the objects' image features, but do not consider the high-level relationship among objects in context.
2 code implementations • 3 Aug 2019 • Jie Tang, Fei-Peng Tian, Wei Feng, Jian Li, Ping Tan
It is thus necessary to complete the sparse LiDAR data, where a synchronized guidance RGB image is often used to facilitate this completion.
no code implementations • 26 Jul 2019 • Ruize Han, Yujun Zhang, Wei Feng, Chenxing Gong, Xiao-Yu Zhang, Jiewen Zhao, Liang Wan, Song Wang
However, for such collaborative analysis, the first step is to associate people, referred to as subjects in this paper, across these two views.
1 code implementation • 30 May 2019 • Xiaoran Xu, Wei Feng, Zhiqing Sun, Zhi-Hong Deng
Instead, inspired by the consciousness prior proposed by Yoshua Bengio, we explore reasoning with the notion of attentive awareness from a cognitive perspective, and formulate it in the form of attentive message passing on graphs, called neural consciousness flow (NeuCFlow).
no code implementations • 15 Mar 2019 • Wei Feng, Wentao Liu, Tong Li, Jing Peng, Chen Qian, Xiaolin Hu
Human-object interactions (HOI) recognition and pose estimation are two closely related tasks.
no code implementations • 1 Nov 2018 • Xiaoran Xu, Songpeng Zu, Chengliang Gao, Yuan Zhang, Wei Feng
Real-world scenarios demand reasoning about process, more than final outcome prediction, to discover latent causal chains and better understand complex systems.
1 code implementation • 25 Jul 2018 • Xiaoran Xu, Songpeng Zu, Yuan Zhang, Hanning Zhou, Wei Feng
Then, the SCG can be trained based on these surrogate costs using standard backpropagation.
no code implementations • 12 Feb 2018 • Xiaochuan Fan, Hao Guo, Kang Zheng, Wei Feng, Song Wang
In particular, we design a Mask Weight Network (MWN) to learn a set of masks and then apply channel-wise masking operations to ROI feature map, followed by a global pooling and a cheap fully-connected layer.
no code implementations • ICCV 2017 • Qing Guo, Wei Feng, Ce Zhou, Rui Huang, Liang Wan, Song Wang
How to effectively learn temporal variation of target appearance, to exclude the interference of cluttered background, while maintaining real-time response, is an essential problem of visual object tracking.
Ranked #5 on
Visual Object Tracking
on OTB-2013
no code implementations • CVPR 2016 • Wei Feng, Fei-Peng Tian, Qian Zhang, Jizhou Sun
Based on inexpensive platform with unreliable absolute repositioning accuracy (ARA), we propose a hand-eye calibration free strategy to actively relocate camera into the same 6D pose that produces the input reference image, by sequentially correcting 3D relative rotation and translation.
no code implementations • ICCV 2015 • Wei Feng, Fei-Peng Tian, Qian Zhang, Nan Zhang, Liang Wan, Jizhou Sun
To guarantee detection sensitivity and accuracy of minute changes, in an observation, we capture a group of images under multiple illuminations, which need only to be roughly aligned to the last time lighting conditions.
no code implementations • 19 May 2014 • Wei Feng, Jiaya Jia, Zhi-Qiang Liu
From our study, we make some reasonable recommendations of combining existing methods that perform the best in different situations for this challenging problem.
no code implementations • CVPR 2013 • Liang Li, Wei Feng, Liang Wan, Jiawan Zhang
For this purpose, we aim at constructing maximum cohesive SP-grid, which is composed of real nodes, i. e. SPs, and dummy nodes that are meaningless in the image with only position-taking function in the grid.