no code implementations • 12 Apr 2024 • Zhiwei Yang, Jing Liu, Peng Wu
Further, we propose a learnable text prompt mechanism with the assist of a normality visual prompt to further improve the matching accuracy of video event description text and video frames.
no code implementations • 1 Apr 2024 • Xuran Li, Peng Wu, Yanting Chen, Xingjun Ma, Zhen Zhang, Kaixiang Dong
Deep neural networks (DNNs) are known to be sensitive to adversarial input perturbations, leading to a reduction in either prediction accuracy or individual fairness.
1 code implementation • 8 Feb 2024 • Yixu Feng, Cheng Zhang, Pei Wang, Peng Wu, Qingsen Yan, Yanning Zhang
Further, we design a novel Color and Intensity Decoupling Network (CIDNet) with two branches dedicated to processing the decoupled image brightness and color in the HVI space.
Ranked #1 on Low-Light Image Enhancement on VV
Low-light Image Deblurring and Enhancement Low-Light Image Enhancement
1 code implementation • Electronics 2024 • Yanju Meng, Peng Wu, Jian Feng, XiaoMing Zhang
For global, we propose the global-feature aggregation encoder (GFAE), which employs a pooling strategy and computes the covariance matrix between channels instead of the spatial dimensions, changing the computational complexity from quadratic to linear, and this accelerates the inference of the model.
no code implementations • 13 Nov 2023 • Peng Wu, Xuerong Zhou, Guansong Pang, Yujia Sun, Jing Liu, Peng Wang, Yanning Zhang
Particularly, we devise a semantic knowledge injection module to introduce semantic knowledge from large language models for the detection task, and design a novel anomaly synthesis module to generate pseudo unseen anomaly videos with the help of large vision generation models for the classification task.
no code implementations • 13 Oct 2023 • Shuangshuang Yuan, Peng Wu, Yuehui Chen, Qiang Li
Class imbalance exists in many classification problems, and since the data is designed for accuracy, imbalance in data classes can lead to classification challenges with a few classes having higher misclassification costs.
no code implementations • 10 Oct 2023 • Jingbo Jia, Peng Wu, Hussain Dawood
To address the problem of insufficient failure data generated by disks and the imbalance between the number of normal and failure data.
no code implementations • 10 Oct 2023 • Guangfu Gao, Peng Wu, Hussain Dawood
Large scale data storage is susceptible to failure.
no code implementations • 10 Oct 2023 • Shuangshuang Yuan, Peng Wu, Yuehui Chen
Data class imbalance is a common problem in classification problems, where minority class samples are often more important and more costly to misclassify in a classification task.
no code implementations • 4 Oct 2023 • Lingru Zhou, Yiqi Gao, Manqing Zhang, Peng Wu, Peng Wang, Yanning Zhang
To address this challenge, we construct a human-centric video surveillance captioning dataset, which provides detailed descriptions of the dynamic behaviors of 7, 820 individuals.
1 code implementation • 22 Aug 2023 • Peng Wu, Xuerong Zhou, Guansong Pang, Lingru Zhou, Qingsen Yan, Peng Wang, Yanning Zhang
With the benefit of dual branch, VadCLIP achieves both coarse-grained and fine-grained video anomaly detection by transferring pre-trained knowledge from CLIP to WSVAD task.
no code implementations • 9 Aug 2023 • Haoqing Li, Shuo Tang, Peng Wu, Pau Closas
Global Navigation Satellite System (GNSS) is pervasive in navigation and positioning applications, where precise position and time referencing estimations are required.
1 code implementation • 24 Jul 2023 • Peng Wu, Jing Liu, Xiangteng He, Yuxin Peng, Peng Wang, Yanning Zhang
In this context, we propose a novel task called Video Anomaly Retrieval (VAR), which aims to pragmatically retrieve relevant anomalous videos by cross-modalities, e. g., language descriptions and synchronous audios.
no code implementations • 5 Jun 2023 • Peng Wu, Helena Calatrava, Tales Imbiriba, Pau Closas
Jamming signals can jeopardize the operation of GNSS receivers until denying its operation.
1 code implementation • 18 May 2023 • Xuran Li, Peng Wu, Kaixiang Dong, Zhen Zhang, Yanting Chen
This matrix categorizes predictions as true fair, true biased, false fair, and false biased, and the perturbations guided by it can produce a dual impact on instances and their similar counterparts to either undermine prediction accuracy (robustness) or cause biased predictions (individual fairness).
no code implementations • 17 Apr 2023 • Haoxuan Li, Yanghao Xiao, Chunyuan Zheng, Peng Wu
Recommender systems are seen as an effective tool to address information overload, but it is widely known that the presence of various biases makes direct training on large-scale observational data result in sub-optimal prediction performance.
no code implementations • CVPR 2023 • Zhiwei Yang, Jing Liu, Zhaoyang Wu, Peng Wu, Xiaotao Liu
Video anomaly detection (VAD) is a significant computer vision problem.
no code implementations • 14 Dec 2022 • Peng Wu, Tales Imbiriba, Victor Elvira, Pau Closas
When data is only available in a distributed fashion or when different sensors are used to infer a quantity of interest, data fusion becomes essential.
no code implementations • 17 Nov 2022 • Yiyang Shen, Rongwei Yu, Peng Wu, Haoran Xie, Lina Gong, Jing Qin, Mingqiang Wei
We propose ImLiDAR, a new 3OD paradigm to narrow the cross-sensor discrepancies by progressively fusing the multi-scale features of camera Images and LiDAR point clouds.
no code implementations • 12 Nov 2022 • Quanyu Dai, Haoxuan Li, Peng Wu, Zhenhua Dong, Xiao-Hua Zhou, Rui Zhang, Jie Sun
However, in this paper, by theoretically analyzing the bias, variance and generalization bounds of DR methods, we find that existing DR approaches may have poor generalization caused by inaccurate estimation of propensity scores and imputation errors, which often occur in practice.
1 code implementation • 16 Sep 2022 • Zhuoran Liu, Leqi Zou, Xuan Zou, Caihua Wang, Biao Zhang, Da Tang, Bolin Zhu, Yijie Zhu, Peng Wu, Ke Wang, Youlong Cheng
In this paper, we present Monolith, a system tailored for online training.
no code implementations • 29 Aug 2022 • Peng Wu, Lipeng Gu, Xuefeng Yan, Haoran Xie, Fu Lee Wang, Gary Cheng, Mingqiang Wei
Such a module will guide our PV-RCNN++ to integrate more object-related point-wise and voxel-wise features in the pivotal areas.
1 code implementation • 22 Jul 2022 • Zhiwei Yang, Peng Wu, Jing Liu, Xiaotao Liu
Existing methods for anomaly detection based on memory-augmented autoencoder (AE) have the following drawbacks: (1) Establishing a memory bank requires additional memory space.
no code implementations • 12 Jul 2022 • Hao liu, Bin Chen, Bo wang, Chunpeng Wu, Feng Dai, Peng Wu
To address the coupling problem, we propose a Cycle Self-Training (CST) framework for SSOD, which consists of two teachers T1 and T2, two students S1 and S2.
no code implementations • 9 Jul 2022 • Haoxuan Li, Quanyu Dai, Yuru Li, Yan Lyu, Zhenhua Dong, Xiao-Hua Zhou, Peng Wu
Doubly robust (DR) learning has been studied in many tasks in RS, with the advantage that unbiased learning can be achieved when either a single imputation or a single propensity model is accurate.
1 code implementation • 1 Jul 2022 • Jichao Zhang, Jingjing Chen, Hao Tang, Enver Sangineto, Peng Wu, Yan Yan, Nicu Sebe, Wei Wang
Solving this problem using an unsupervised method remains an open problem, especially for high-resolution face images in the wild, which are not easy to annotate with gaze and head pose labels.
1 code implementation • 18 May 2022 • Xuran Li, Peng Wu, Jing Su
We propose in this paper a new fairness criterion, accurate fairness, to align individual fairness with accuracy.
no code implementations • 10 May 2022 • Haoxuan Li, Chunyuan Zheng, Peng Wu
However, in this paper, we show that DR methods are unstable and have unbounded bias, variance, and generalization bounds to extremely small propensities.
4 code implementations • 2 May 2022 • Minghui Yang, Peng Wu, Jing Liu, Hui Feng
By comparing the similarities and differences between input samples and memory samples in the memory pool to give effective guesses about abnormal regions; In the inference phase, MemSeg directly determines the abnormal regions of the input image in an end-to-end manner.
Ranked #14 on Anomaly Detection on MVTec AD
1 code implementation • 13 Apr 2022 • Zangwei Zheng, Pengtai Xu, Xuan Zou, Da Tang, Zhen Li, Chenguang Xi, Peng Wu, Leqi Zou, Yijie Zhu, Ming Chen, Xiangzhuo Ding, Fuzhao Xue, Ziheng Qin, Youlong Cheng, Yang You
Our experiments show that previous scaling rules fail in the training of CTR prediction neural networks.
no code implementations • 19 Mar 2022 • Haoxuan Li, Yan Lyu, Chunyuan Zheng, Peng Wu
Bias is a common problem inherent in recommender systems, which is entangled with users' preferences and poses a great challenge to unbiased learning.
1 code implementation • 23 Feb 2022 • Yan Lyu, Sunhao Dai, Peng Wu, Quanyu Dai, yuhao deng, Wenjie Hu, Zhenhua Dong, Jun Xu, Shengyu Zhu, Xiao-Hua Zhou
To better support the studies of causal inference and further explanations in recommender systems, we propose a novel semi-synthetic data generation framework for recommender systems where causal graphical models with missingness are employed to describe the causal mechanism of practical recommendation scenarios.
no code implementations • 24 Jan 2022 • Peng Wu, Jean-François Muzy, Emmanuel Bacry
We introduce a family of random measures $M_{H, T} (d t)$, namely log S-fBM, such that, for $H>0$, $M_{H, T}(d t) = e^{\omega_{H, T}(t)} d t$ where $\omega_{H, T}(t)$ is a Gaussian process that can be considered as a stationary version of an $H$-fractional Brownian motion.
no code implementations • 18 Jan 2022 • Peng Wu, Haoxuan Li, yuhao deng, Wenjie Hu, Quanyu Dai, Zhenhua Dong, Jie Sun, Rui Zhang, Xiao-Hua Zhou
Recently, recommender system (RS) based on causal inference has gained much attention in the industrial community, as well as the states of the art performance in many prediction and debiasing tasks.
no code implementations • 31 Jul 2021 • Peng Wu, Julius Partridge, Enrico Anderlini, Yuanchang Liu, Richard Bucknall
In the proposed framework, a Twin-Delayed Deep Deterministic Policy Gradient agent is trained using an extensive volume of historical load profiles to generate a generic energy management strategy.
1 code implementation • 26 Jul 2021 • Peng Wu, Xiangteng He, Mingqian Tang, Yiliang Lv, Jing Liu
Based on these, we naturally construct hierarchical representations in the individual-local-global manner, where the individual level focuses on the alignment between frame and word, local level focuses on the alignment between video clip and textual context, and global level focuses on the alignment between the whole video and text.
no code implementations • 9 Jul 2021 • Peng Wu, Tales Imbiriba, Junha Park, Sunwoo Kim, Pau Closas
Localization and tracking of objects using data-driven methods is a popular topic due to the complexity in characterizing the physics of wireless channel propagation models.
no code implementations • 7 Jul 2021 • Yifu Wang, Jiaqi Yang, Xin Peng, Peng Wu, Ling Gao, Kun Huang, Jiaben Chen, Laurent Kneip
We present a new solution to tracking and mapping with an event camera.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Peng Wu, Bowei Zou, Ridong Jiang, AiTi Aw
As an essential component of task-oriented dialogue systems, Dialogue State Tracking (DST) takes charge of estimating user intentions and requests in dialogue contexts and extracting substantial goals (states) from user utterances to help the downstream modules to determine the next actions of dialogue systems.
Dialogue State Tracking Multi-domain Dialogue State Tracking +1
1 code implementation • ECCV 2020 • Peng Wu, Jing Liu, Yujia Shi, Yujia Sun, Fangtao Shao, Zhaoyang Wu, Zhiwei Yang
Violence detection has been studied in computer vision for years.
1 code implementation • ACL 2019 • Peng Wu, Shu-Jian Huang, Rongxiang Weng, Zaixiang Zheng, Jianbing Zhang, Xiaohui Yan, Jia-Jun Chen
However, one critical problem is that current approaches only get high accuracy for questions whose relations have been seen in the training data.
no code implementations • MDPI 2019 • Peng Wu, Shaojing Su, Zhen Zuo *, Xiaojun Guo, Bei Sun and Xudong Wen
This paper proposes a hybrid firefly algorithm (hybrid‐FA) method, combining the weighted least squares (WLS) algorithm and FA, which can reduce computation as well as achieve high accuracy.
no code implementations • 28 Mar 2019 • Conghui Zheng, Li Pan, Peng Wu
Network embedding is the process of learning low-dimensional representations for nodes in a network, while preserving node features.
no code implementations • 11 Oct 2018 • Lan Hu, Yuchen Cao, Peng Wu, Laurent Kneip
Most problems involving simultaneous localization and mapping can nowadays be solved using one of two fundamentally different approaches.
1 code implementation • 2 Apr 2018 • Qiong Zhu, Peng Wu, R. N. Bhatt, Xin Wan
Motivated by the recent numerical studies on the Chalker-Coddington network model that found a larger-than-expected critical exponent of the localization length characterizing the integer quantum Hall plateau transitions, we revisited the exponent calculation in the continuum model and in the lattice model, both projected to the lowest Landau level or subband.
Disordered Systems and Neural Networks