no code implementations • 26 May 2025 • Jiongchao Jin, Shengchu Zhao, Dajun Chen, Wei Jiang, Yong Li
To address these challenges, we propose an Aggregation Structural Representation (ASR) module that integrates graph networks with large language models (LLMs) to preserve structural information while enhancing generative capability.
no code implementations • 23 May 2025 • Jianyang Gu, Haonan Wang, Ruoxi Jia, Saeed Vahidian, Vyacheslav Kungurtsev, Wei Jiang, Yiran Chen
We demonstrate the efficacy of CONCORD by achieving state-of-the-art performance on ImageNet-1K and its subsets.
no code implementations • 20 May 2025 • Wei Jiang, Anying Fu, Youling Zhang
Model pruning is a performance optimization technique for large language models like R1 or o3-mini.
no code implementations • 14 May 2025 • Wei Jiang, Junru Li, Kai Zhang, Li Zhang
To tackle these challenges, we propose BiECVC, a BVC framework that incorporates diversified local and non-local context modeling along with adaptive context gating.
1 code implementation • 5 May 2025 • Binghong Chen, Tingting Chai, Wei Jiang, Yuanrong Xu, Guanglu Zhou, Xiangqian Wu
The model is validated on multiple real-world image denoising datasets, outperforming the existing state-of-the-art methods quantitatively and reducing inference time up to 40\%.
no code implementations • 27 Apr 2025 • Wei Jiang, Yongqi Zhai, Jiayu Yang, Feng Gao, Ronggang Wang
In this paper, we present MLICv2 and MLICv2$^+$, enhanced versions of the MLIC series, featuring improved transform techniques, entropy modeling, and instance adaptability.
no code implementations • 23 Apr 2025 • Apostolos I. Rikos, Wei Jiang, Themistoklis Charalambous, Karl H. Johansson
Our second algorithm incorporates a novel event-triggered refinement mechanism, which refines the utilized quantization level to enhance the precision of the estimated optimal solution.
no code implementations • 22 Apr 2025 • Lebin Zhou, Cihan Ruan, Nam Ling, Wei Wang, Wei Jiang
The discrete tokens (i. e., code maps generated by FSQ) are partially masked using a strategic masking scheme, then compressed losslessly with a discrete checkerboard context model to reduce transmission overhead.
1 code implementation • 21 Apr 2025 • Jingkai Zhou, Yifan Wu, Shikai Li, Min Wei, Chao Fan, Weihua Chen, Wei Jiang, Fan Wang
In this paper, we propose a new perspective that, as long as the foundation model is powerful enough, straightforward model modifications with flexible fine-tuning strategies can largely address the above challenges, taking a step towards controllable character animation in the wild.
no code implementations • 3 Apr 2025 • Yongqi Zhai, Luyang Tang, Wei Jiang, Jiayu Yang, Ronggang Wang
Recently, learned video compression (LVC) has shown superior performance under low-delay configuration.
no code implementations • 3 Apr 2025 • Bo Yuan, Yulin Chen, Yin Zhang, Wei Jiang
During collaborative training, we first adopt two SMs to form a co-prediction network and propose a dynamic-enhanced threshold strategy to divide the noisy data into different subsets, then select the clean and noisy samples from these subsets to feed the active annotator LLMs to rectify noisy samples.
1 code implementation • 28 Mar 2025 • Zhonghao Jiang, Xiaoxue Ren, Meng Yan, Wei Jiang, Yong Li, Zhongxin Liu
CoSIL reduces the search space through module call graphs, iteratively searches the function call graph to obtain relevant contexts, and uses context pruning to control the search direction and manage contexts effectively.
no code implementations • 21 Mar 2025 • Mingliang Li, YanRong Li, Lai Wei, Wei Jiang, Zuo-Jun Max Shen
Specifically, for manufacturers with mature ADS technology, the bundle strategy provides consumers with a lower entry barrier by integrating SSH, making the flexible subscription model a dominant strategy; while perpetual licensing outperforms under the unbundle strategy.
1 code implementation • 5 Mar 2025 • Yixin Su, Wei Jiang, Fangquan Lin, Cheng Yang, Sarah M. Erfani, Junhao Gan, Yunxiang Zhao, Ruixuan Li, Rui Zhang
In recommender systems, the patterns of user behaviors (e. g., purchase, click) may vary greatly in different contexts (e. g., time and location).
no code implementations • 12 Feb 2025 • Wei Cheng, Yucheng Lu, Boyang xia, Jiangxia Cao, Kuan Xu, Mingxing Wen, Wei Jiang, Jiaming Zhang, Zhaojie Liu, Liyin Hong, Kun Gai, Guorui Zhou
Post-click conversion rate (CVR) estimation is a vital task in many recommender systems of revenue businesses, e. g., e-commerce and advertising.
no code implementations • 11 Feb 2025 • Lei Lu, Yize Li, Yanzhi Wang, Wei Wang, Wei Jiang
Image compression under ultra-low bitrates remains challenging for both conventional learned image compression (LIC) and generative vector-quantized (VQ) modeling.
no code implementations • 2 Feb 2025 • Dingzhi Yu, Wei Jiang, Yuanyu Wan, Lijun Zhang
In this paper, we address this limitation by introducing a new $\ell*$-smoothness concept that measures the norm of Hessians in terms of a general norm and its dual, and establish convergence for mirror-descent-type algorithms, matching the rates under the classic smoothness.
no code implementations • CVPR 2025 • Zhicheng Wang, Zhiyu Pan, Zhan Peng, Jian Cheng, Liwen Xiao, Wei Jiang, Zhiguo Cao
In the scope of REC, we define the CAD as the measure of the information intensity of one certain fine-grained attribute in visual regions.
1 code implementation • 25 Dec 2024 • Gursimran Singh, Xinglu Wang, Yifan Hu, Timothy Yu, Linzi Xing, Wei Jiang, Zhefeng Wang, Xiaolong Bai, Yi Li, Ying Xiong, Yong Zhang, Zhenan Fan
Large Multimodal Models (LMMs) extend Large Language Models (LLMs) by handling diverse inputs such as images, audio, and video, but at the cost of adding a multimodal encoding stage that increases both computational and memory overhead.
no code implementations • 30 Nov 2024 • Yongqi Zhai, Jiayu Yang, Wei Jiang, Chunhui Yang, Luyang Tang, Ronggang Wang
In this paper, we propose a hybrid context generation module, which combines the advantages of the above methods in an optimal way and achieves accurate compensation at a low bit cost.
no code implementations • 30 Nov 2024 • Yongqi Zhai, Yi Ma, Luyang Tang, Wei Jiang, Ronggang Wang
Scalable coding, which can adapt to channel bandwidth variation, performs well in today's complex network environment.
no code implementations • 26 Nov 2024 • Yufan Zheng, Wei Jiang, Alexander Zhou, Nguyen Quoc Viet Hung, Choujun Zhan, Tong Chen
With the time-varying mechanistic affinity graphs computed with the epidemiology-informed location embeddings, a heterogeneous transmission graph network is designed to encode the mechanistic heterogeneity among locations, providing additional predictive signals to facilitate accurate forecasting.
no code implementations • 20 Nov 2024 • Wei Jiang, Tong Chen, Xinyi Gao, Wentao Zhang, Lizhen Cui, Hongzhi Yin
Given the variations in topics and social impact of the root node, different source information naturally has distinct outreach capabilities, resulting in different heights of propagation trees.
1 code implementation • CVPR 2025 • Wei Jiang, Junru Li, Kai Zhang, Li Zhang
In Learned Video Compression (LVC), improving inter prediction, such as enhancing temporal context mining and mitigating accumulated errors, is crucial for boosting rate-distortion performance.
no code implementations • 10 Oct 2024 • Liang Liu, Xiao Hu, Wei Jiang, Guanglei Meng, Zhujun Wang, Taining Zhang
The solution incorporates a visual processing module and an improved manifold-based sensor fusion algorithm, delivering reliable and accurate positioning information.
no code implementations • 24 Sep 2024 • Lingxin Jin, Meiyu Lin, Wei Jiang, Jinyu Zhan
Spiking Neural Networks (SNNs), the third generation neural networks, are known for their low energy consumption and high robustness.
no code implementations • 9 Sep 2024 • Apostolos I. Rikos, Wei Jiang, Themistoklis Charalambous, Karl H. Johansson
In realistic distributed optimization scenarios, individual nodes possess only partial information and communicate over bandwidth constrained channels.
no code implementations • 29 Aug 2024 • Lebin Zhou, Kun Han, Nam Ling, Wei Wang, Wei Jiang
The first is super-resolution with deferred rendering, to support the gaming solution of rendering and transferring LR images only and restoring HR images on the client side.
no code implementations • 15 Aug 2024 • Lingxin Jin, Xianyu Wen, Wei Jiang, Jinyu Zhan
Deep Neural Networks (DNNs) have found extensive applications in safety-critical artificial intelligence systems, such as autonomous driving and facial recognition systems.
1 code implementation • 18 Jul 2024 • Wei Jiang, Tong Chen, Guanhua Ye, Wentao Zhang, Lizhen Cui, Zi Huang, Hongzhi Yin
Moreover, due to the interval-based predictions and intermittent nature of data filing in many transportation services, the instantaneous dynamics of urban flows can hardly be captured, rendering differential equation-based continuous modeling a loose fit for this setting.
1 code implementation • 18 Jul 2024 • Jiahao Cui, Wei Jiang, Zhan Peng, Zhiyu Pan, Zhiguo Cao
Combining the interpolated and given LDR frames, the complete set of exposure information is available at each time stamp.
no code implementations • 1 Jul 2024 • Xiang Jiao, Dingzhu Wen, Guangxu Zhu, Wei Jiang, Wu Luo, Yuanming Shi
By maximizing the minimum pair-wise discriminant gain instead of its average counterpart, any pair of classes can be better separated in the feature space, and thus leading to a balanced and improved inference accuracy for all classes.
no code implementations • 22 Jun 2024 • Daniel Ayepah-Mensah, Guolin Sun, Yu Pang, Wei Jiang
Network slicing enables industrial Internet of Things (IIoT) networks with multiservice and differentiated resource requirements to meet increasing demands through efficient use and management of network resources.
no code implementations • 17 Jun 2024 • Hui Wang, Nima Tashakor, Wei Jiang, Wei Liu, C. Q. Jiang, Stefan M. Goetz
To stimulate the progress of energy encryption technology and point out security holes, this paper proposes a decryption method for the fundamental principle of encrypted frequency-varying wireless power transfer.
no code implementations • 6 Jun 2024 • Wei Jiang, Sifan Yang, Wenhao Yang, Yibo Wang, Yuanyu Wan, Lijun Zhang
Existing projection-free algorithms for solving this problem suffer from two limitations: 1) they solely focus on the gradient mapping criterion and fail to match the optimal sample complexities in unconstrained settings; 2) their analysis is exclusively applicable to non-convex functions, without considering convex and strongly convex objectives.
no code implementations • 4 Jun 2024 • Wei Jiang, Sifan Yang, Yibo Wang, Lijun Zhang
This paper explores adaptive variance reduction methods for stochastic optimization based on the STORM technique.
no code implementations • 1 Jun 2024 • Wei Jiang, Sifan Yang, Wenhao Yang, Lijun Zhang
Sign stochastic gradient descent (signSGD) is a communication-efficient method that transmits only the sign of stochastic gradients for parameter updating.
no code implementations • 20 Apr 2024 • Lei Lu, Yanyue Xie, Wei Jiang, Wei Wang, Xue Lin, Yanzhi Wang
This paper investigates the challenging problem of learned image compression (LIC) with extreme low bitrates.
no code implementations • 9 Apr 2024 • Wei Jiang, Wei Wang
Our framework can be conveniently used for both learned image compression (LIC) and learned video compression (LVC).
no code implementations • 21 Mar 2024 • Zhuang Xiong, Wei Jiang, Yang Gao, Feng Liu, Hongfu Sun
In this work, we developed a 3D image patch-based diffusion model, namely QSMDiff, for robust QSM reconstruction across different scan parameters, alongside simultaneous super-resolution and image-denoising tasks.
no code implementations • 6 Mar 2024 • Dingzhi Yu, Yunuo Cai, Wei Jiang, Lijun Zhang
In this paper, we investigate the empirical counterpart of Group Distributionally Robust Optimization (GDRO), which aims to minimize the maximal empirical risk across $m$ distinct groups.
no code implementations • 22 Feb 2024 • Ming Liang, Xiaoheng Xie, Gehao Zhang, Xunjin Zheng, Peng Di, Wei Jiang, Hongwei Chen, Chengpeng Wang, Gang Fan
The success of language models in code assistance has spurred the proposal of repository-level code completion as a means to enhance prediction accuracy, utilizing the context from the entire codebase.
1 code implementation • 7 Feb 2024 • Saeed Vahidian, Mingyu Wang, Jianyang Gu, Vyacheslav Kungurtsev, Wei Jiang, Yiran Chen
The most popular methods for constructing the synthetic data rely on matching the convergence properties of training the model with the synthetic dataset and the training dataset.
no code implementations • 2 Feb 2024 • Jiayu Yang, Wei Jiang, Yongqi Zhai, Chunhui Yang, Ronggang Wang
This paper presents a learned video compression method in response to video compression track of the 6th Challenge on Learned Image Compression (CLIC), at DCC 2024. Specifically, we propose a unified contextual video compression framework (UCVC) for joint P-frame and B-frame coding.
no code implementations • 1 Feb 2024 • Wei Jiang, Junru Li, Kai Zhang, Li Zhang
To validate the effectiveness of our proposed LGMC, we integrate it with DCVC-TCM and obtain learned video compression with joint local and global motion compensation (LVC-LGMC).
no code implementations • 31 Jan 2024 • YanRong Li, Juan Du, Fugee Tsung, Wei Jiang
This paper proposes a novel process control and monitoring method for the complex structure of high-dimensional image-based overlay errors (modeled in tensor form), which are collected in semiconductor manufacturing processes.
no code implementations • 26 Jan 2024 • Wei Jiang, Xinyi Gao, Guandong Xu, Tong Chen, Hongzhi Yin
To comprehensively extract preference-aware homophily information latent in the social graph, we propose Social Heterophily-alleviating Rewiring (SHaRe), a data-centric framework for enhancing existing graph-based social recommendation models.
no code implementations • 16 Jan 2024 • Wei Jiang, Yongqi Zhai, Hangyu Li, Ronggang Wang
This short paper describes our method for the track of image compression.
1 code implementation • 4 Dec 2023 • Xiaoyuan Cheng, Yiming Yang, Xiaohang Tang, Wei Jiang, Yukun Hu
To address these challenges, we propose Koopman Embedded Equivariant Control (KEEC) to learn an embedding of the states and vector fields such that a Koopman operator is approximated as the latent dynamics.
1 code implementation • CVPR 2024 • Jianyang Gu, Saeed Vahidian, Vyacheslav Kungurtsev, Haonan Wang, Wei Jiang, Yang You, Yiran Chen
Observing that key factors for constructing an effective surrogate dataset are representativeness and diversity, we design additional minimax criteria in the generative training to enhance these facets for the generated images of diffusion models.
1 code implementation • 20 Nov 2023 • Wei Jiang, Zhuang Xiong, Feng Liu, Nan Ye, Hongfu Sun
Supervised deep learning methods have shown promise in undersampled Magnetic Resonance Imaging (MRI) reconstruction, but their requirement for paired data limits their generalizability to the diverse MRI acquisition parameters.
no code implementations • 14 Nov 2023 • Mohammadreza Doostmohammadian, Wei Jiang, Muwahida Liaquat, Alireza Aghasi, Houman Zarrabi
This work, particularly, is an improvement over existing stochastic-weight undirected networks in case of link removal or packet drops.
no code implementations • 13 Nov 2023 • Shuting He, Hao Luo, Wei Jiang, Xudong Jiang, Henghui Ding
With the help of relational knowledge transfer, VGKT is capable of aligning semantic-group textual features with corresponding visual features without external tools and complex pairwise interaction.
Ranked #9 on
Text based Person Retrieval
on ICFG-PEDES
1 code implementation • 23 Oct 2023 • Yanqing Liu, Jianyang Gu, Kai Wang, Zheng Zhu, Kaipeng Zhang, Wei Jiang, Yang You
Dataset distillation plays a crucial role in creating compact datasets with similar training performance compared with original large-scale ones.
no code implementations • 10 Oct 2023 • Peng Di, Jianguo Li, Hang Yu, Wei Jiang, Wenting Cai, Yang Cao, Chaoyu Chen, Dajun Chen, Hongwei Chen, Liang Chen, Gang Fan, Jie Gong, Zi Gong, Wen Hu, Tingting Guo, Zhichao Lei, Ting Li, Zheng Li, Ming Liang, Cong Liao, Bingchang Liu, Jiachen Liu, Zhiwei Liu, Shaojun Lu, Min Shen, Guangpei Wang, Huan Wang, Zhi Wang, Zhaogui Xu, Jiawei Yang, Qing Ye, Gehao Zhang, Yu Zhang, Zelin Zhao, Xunjin Zheng, Hailian Zhou, Lifu Zhu, Xianying Zhu
It is specifically designed for code-related tasks with both English and Chinese prompts and supports over 40 programming languages.
no code implementations • 20 Sep 2023 • Wei Jiang, Wei Wang, Yue Chen
A set of semantic-class-dependent basis codebooks are learned, which are weighted combined to generate a rich latent feature for high-quality reconstruction.
no code implementations • 17 Sep 2023 • YanRong Li, Juan Du, Wei Jiang
Design of process control scheme is critical for quality assurance to reduce variations in manufacturing systems.
no code implementations • 15 Sep 2023 • Wei Jiang, Zhongkai Yi, Li Wang, Hanwei Zhang, Jihai Zhang, Fangquan Lin, Cheng Yang
Aggregating distributed energy resources in power systems significantly increases uncertainties, in particular caused by the fluctuation of renewable energy generation.
1 code implementation • 15 Sep 2023 • Shiyi Zhu, Jing Ye, Wei Jiang, Siqiao Xue, Qi Zhang, Yifan Wu, Jianguo Li
In fact, anomalous behaviors harming long context extrapolation exist between Rotary Position Embedding (RoPE) and vanilla self-attention unveiled by our work.
no code implementations • 8 Sep 2023 • Apostolos I. Rikos, Wei Jiang, Themistoklis Charalambous, Karl H. Johansson
Distributed methods in which nodes use quantized communication yield a solution at the proximity of the optimal solution, hence reaching an error floor that depends on the quantization level used; the finer the quantization the lower the error floor.
no code implementations • 7 Sep 2023 • Shuting He, Weihua Chen, Kai Wang, Hao Luo, Fan Wang, Wei Jiang, Henghui Ding
Then, to measure the importance of each generated region, we introduce a Region Assessment Module (RAM) that assigns confidence scores to different regions and reduces the negative impact of the occlusion regions by lower scores.
1 code implementation • 21 Aug 2023 • Jianyang Gu, Hao Luo, Kai Wang, Wei Jiang, Yang You, Jian Zhao
In this work, we propose a Color Prompting (CoP) method for data-free continual unsupervised domain adaptive person Re-ID.
Domain Adaptive Person Re-Identification
Person Re-Identification
+1
no code implementations • 7 Aug 2023 • Wei Jiang, Tianyuan Zhang, Shuangcheng Liu, Weiyu Ji, Zichao Zhang, Gang Xiao
Through this pipeline, we establish the Discrete and Continuous Instant-level (DCI) dataset, enabling comprehensive experiments involving three detection models and three physical adversarial attacks.
no code implementations • 29 Jul 2023 • Hongyan Hao, Zhixuan Chu, Shiyi Zhu, Gangwei Jiang, Yan Wang, Caigao Jiang, James Zhang, Wei Jiang, Siqiao Xue, Jun Zhou
In order to surmount this challenge and effectively integrate new sample distribution, we propose a density-based sample selection strategy that utilizes kernel density estimation to calculate sample density as a reference to compute sample weight, and employs weight sampling to construct a new memory set.
1 code implementation • 28 Jul 2023 • Wei Jiang, Jiayu Yang, Yongqi Zhai, Feng Gao, Ronggang Wang
Additionally, to capture global contexts, we propose the linear complexity attention-based global correlations capturing by leveraging the decomposition of the softmax operation.
Ranked #1 on
Image Compression
on kodak
no code implementations • 19 Jul 2023 • Wei Jiang, Qiuheng Zhou, Jiguang He, Mohammad Asif Habibi, Sergiy Melnyk, Mohammed El Absi, Bin Han, Marco Di Renzo, Hans Dieter Schotten, Fa-Long Luo, Tarek S. El-Bawab, Markku Juntti, Merouane Debbah, Victor C. M. Leung
Different from earlier surveys, this paper presents a comprehensive treatment and technology survey on THz communications and sensing in terms of advantages, applications, propagation characterization, channel modeling, measurement campaigns, antennas, transceiver devices, beamforming, networking, the integration of communications and sensing, and experimental testbeds.
1 code implementation • CVPR 2023 • Shuting He, Henghui Ding, Wei Jiang
The inter-class relationships of semantic-related visual features are then required to be aligned with those in semantic space, thereby transferring semantic knowledge to visual feature learning.
1 code implementation • 13 Jun 2023 • Xianliang Yang, Zhihao Liu, Wei Jiang, Chuheng Zhang, Li Zhao, Lei Song, Jiang Bian
Multi-agent reinforcement learning (MARL) models multiple agents that interact and learn within a shared environment.
no code implementations • 13 Jun 2023 • Wei Jiang, Jiayu Qin, Lingyu Wu, Changyou Chen, Tianbao Yang, Lijun Zhang
Learning unnormalized statistical models (e. g., energy-based models) is computationally challenging due to the complexity of handling the partition function.
no code implementations • 12 Jun 2023 • Yining Ma, Wei Jiang, Lingtong Zhang, Junyi Chen, Hong Wang, Chen Lv, Xuesong Wang, Lu Xiong
Current testing scenarios typically employ predefined or scripted BVs, which inadequately reflect the complexity of human-like social behaviors in real-world driving scenarios, and also lack a systematic metric for evaluating the comprehensive intelligence of AVs.
no code implementations • 11 Jun 2023 • Asaad Alghamdi, Xinyu Duan, Wei Jiang, Zhenhai Wang, Yimeng Wu, Qingrong Xia, Zhefeng Wang, Yi Zheng, Mehdi Rezagholizadeh, Baoxing Huai, Peilun Cheng, Abbas Ghaddar
Developing monolingual large Pre-trained Language Models (PLMs) is shown to be very successful in handling different tasks in Natural Language Processing (NLP).
2 code implementations • 26 May 2023 • Jianyang Gu, Kai Wang, Wei Jiang, Yang You
Through maintaining the consistency of training gradients and relationship to the past tasks, the summarized samples are more representative for the stream data compared to the original images.
1 code implementation • 23 May 2023 • Shuting He, Xudong Jiang, Wei Jiang, Henghui Ding
In this work, we address the challenging task of few-shot and zero-shot 3D point cloud semantic segmentation.
1 code implementation • CVPR 2023 • Shuting He, Henghui Ding, Wei Jiang
It is desired to rescue novel objects from background and dominated seen categories.
no code implementations • 19 May 2023 • Rui Song, Lingjuan Lyu, Wei Jiang, Andreas Festag, Alois Knoll
Machine learning (ML) has revolutionized transportation systems, enabling autonomous driving and smart traffic services.
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.
1 code implementation • 12 May 2023 • Peirong Ning, Wei Jiang, Ronggang Wang
In recent years, there has been rapid development in learned image compression techniques that prioritize ratedistortion-perceptual compression, preserving fine details even at lower bit-rates.
no code implementations • 19 Apr 2023 • Wei Jiang, Peirong Ning, Jiayu Yang, Yongqi Zhai, Feng Gao, Ronggang Wang
To tackle this issue, we propose Large Receptive Field Transform Coding with Adaptive Weights for Learned Image Compression (LLIC).
1 code implementation • CVPR 2023 • Jianyang Gu, Kai Wang, Hao Luo, Chen Chen, Wei Jiang, Yuqiang Fang, Shanghang Zhang, Yang You, Jian Zhao
Neural Architecture Search (NAS) has been increasingly appealing to the society of object Re-Identification (ReID), for that task-specific architectures significantly improve the retrieval performance.
Ranked #8 on
Vehicle Re-Identification
on VehicleID Large
2 code implementations • 8 Mar 2023 • Kai Wang, Jianyang Gu, Daquan Zhou, Zheng Zhu, Wei Jiang, Yang You
To the best of our knowledge, we are the first to achieve higher accuracy on complex architectures than simple ones, such as 75. 1\% with ResNet-18 and 72. 6\% with ConvNet-3 on ten images per class of CIFAR-10.
2 code implementations • ICCV 2023 • Yanqing Liu, Jianyang Gu, Kai Wang, Zheng Zhu, Wei Jiang, Yang You
Although there are various matching objectives, currently the strategy for selecting original images is limited to naive random sampling.
no code implementations • 8 Feb 2023 • Xiangyu Wen, Yu Li, Wei Jiang, Qiang Xu
Various watermarking techniques are proposed to protect such intellectual properties (IPs), wherein the DNN providers implant secret information into the model so that they can later claim IP ownership by retrieving their embedded watermarks with some dedicated trigger inputs.
no code implementations • 15 Dec 2022 • Yuandong Ding, Mingxiao Feng, Guozi Liu, Wei Jiang, Chuheng Zhang, Li Zhao, Lei Song, Houqiang Li, Yan Jin, Jiang Bian
In this paper, we consider the inventory management (IM) problem where we need to make replenishment decisions for a large number of stock keeping units (SKUs) to balance their supply and demand.
no code implementations • 20 Nov 2022 • Apostolos I. Rikos, Wei Jiang, Themistoklis Charalambous, Karl H. Johansson
For solving this distributed optimization problem, we combine a gradient descent method with a distributed quantized consensus algorithm (which requires the nodes to exchange quantized messages and converges in a finite number of steps).
1 code implementation • 14 Nov 2022 • Wei Jiang, Jiayu Yang, Yongqi Zhai, Peirong Ning, Feng Gao, Ronggang Wang
Based on MEM and MEM$^+$, we propose image compression models MLIC and MLIC$^+$.
Ranked #1 on
Image Compression
on kodak
no code implementations • 30 Aug 2022 • Mohammadreza Doostmohammadian, Wei Jiang, Themistoklis Charalambous
Every node locally updates its state toward optimizing a global allocation cost function via received information of its neighbouring nodes even when the data exchange over the network is heterogeneously delayed at different links.
no code implementations • 18 Aug 2022 • Fangquan Lin, Wei Jiang, Hanwei Zhang, Cheng Yang
KDD CUP 2022 proposes a time-series forecasting task on spatial dynamic wind power dataset, in which the participants are required to predict the future generation given the historical context factors.
no code implementations • 18 Jul 2022 • Wei Jiang, Gang Li, Yibo Wang, Lijun Zhang, Tianbao Yang
The key issue is to track and estimate a sequence of $\mathbf g(\mathbf{w})=(g_1(\mathbf{w}), \ldots, g_m(\mathbf{w}))$ across iterations, where $\mathbf g(\mathbf{w})$ has $m$ blocks and it is only allowed to probe $\mathcal{O}(1)$ blocks to attain their stochastic values and Jacobians.
no code implementations • 12 Jul 2022 • Xiao Pan, Hao Luo, Weihua Chen, Fan Wang, Hao Li, Wei Jiang, Jianming Zhang, Jianyang Gu, Peike Li
To address this issue, we propose the Ranking-based Backward Compatible Learning (RBCL), which directly optimizes the ranking metric between new features and old features.
no code implementations • 8 Jul 2022 • Zhengang Li, Sheng Lin, Shan Liu, Songnan Li, Xue Lin, Wei Wang, Wei Jiang
Recently, high-quality video conferencing with fewer transmission bits has become a very hot and challenging problem.
1 code implementation • 22 Jun 2022 • Wei Jiang, Wentao Dong
In this work, we investigate into the performance of mainstream neural generative models on the very task of swapping faces.
no code implementations • CVPR 2022 • Zhihao Hu, Guo Lu, Jinyang Guo, Shan Liu, Wei Jiang, Dong Xu
The previous deep video compression approaches only use the single scale motion compensation strategy and rarely adopt the mode prediction technique from the traditional standards like H. 264/H. 265 for both motion and residual compression.
no code implementations • 2 May 2022 • Lijun Zhang, Wei Jiang, JinFeng Yi, Tianbao Yang
In this paper, we investigate an online prediction strategy named as Discounted-Normal-Predictor (Kapralov and Panigrahy, 2010) for smoothed online convex optimization (SOCO), in which the learner needs to minimize not only the hitting cost but also the switching cost.
no code implementations • 11 Apr 2022 • Haojie Liu, Daoxun Xia, Wei Jiang, Chao Xu
In order to mitigate the impact of large modality discrepancy existing in heterogeneous images, previous methods attempt to apply generative adversarial network (GAN) to generate the modality-consisitent data.
1 code implementation • 23 Mar 2022 • Wei Jiang, Kwang Moo Yi, Golnoosh Samei, Oncel Tuzel, Anurag Ranjan
Photorealistic rendering and reposing of humans is important for enabling augmented reality experiences.
no code implementations • 15 Feb 2022 • Wei Jiang, Bokun Wang, Yibo Wang, Lijun Zhang, Tianbao Yang
To address these limitations, we propose a Stochastic Multi-level Variance Reduction method (SMVR), which achieves the optimal sample complexity of $\mathcal{O}\left(1 / \epsilon^{3}\right)$ to find an $\epsilon$-stationary point for non-convex objectives.
no code implementations • 21 Jan 2022 • Peixi Liu, Guangxu Zhu, Wei Jiang, Wu Luo, Jie Xu, Shuguang Cui
This letter studies a vertical federated edge learning (FEEL) system for collaborative objects/human motion recognition by exploiting the distributed integrated sensing and communication (ISAC).
no code implementations • CVPR 2022 • Zhenghao Chen, Guo Lu, Zhihao Hu, Shan Liu, Wei Jiang, Dong Xu
In this work, we propose the first end-to-end optimized framework for compressing automotive stereo videos (i. e., stereo videos from autonomous driving applications) from both left and right views.
no code implementations • 3 Dec 2021 • Wei Jiang, Alexander M. Haimovich, Mark Govoni, Timothy Garner, Osvaldo Simeone
One approach is based on transfer learning: it first pre-trains a detector such that it works well on data collected in previously observed environments, and then it adapts the pre-trained detector to the specific current environment.
no code implementations • 16 Nov 2021 • Wei Jiang, Wei Wang, Songnan Li, Shan Liu
This work addresses two major issues of end-to-end learned image compression (LIC) based on deep neural networks: variable-rate learning where separate networks are required to generate compressed images with varying qualities, and the train-test mismatch between differentiable approximate quantization and true hard quantization.
no code implementations • 22 Oct 2021 • YanRong Li, Juan Du, Wei Jiang
Process control is widely discussed in the manufacturing process, especially for semiconductor manufacturing.
no code implementations • 22 Oct 2021 • YanRong Li, Lai Wei, Wei Jiang
This paper proposes a two-stage pricing strategy for nondurable (such as typical electronics) products, where retail price is cut down at certain time points of the product lifecycle.
no code implementations • 1 Jul 2021 • Yiyang Chen, Wei Jiang, Themistoklis Charalambous
A machine learning (ML) based nominal model update mechanism, which utilizes the linear regression technique to update the nominal model at each ILC trial only using the current trial information, is proposed for non-repetitive TVSs in order to enhance the ILC performance.
no code implementations • 15 Jun 2021 • Sheng Lin, Wei Jiang, Wei Wang, Kaidi Xu, Yanzhi Wang, Shan Liu, Songnan Li
Compressing Deep Neural Network (DNN) models to alleviate the storage and computation requirements is essential for practical applications, especially for resource limited devices.
no code implementations • 16 May 2021 • Xiao Wang, Wei Jiang, Wei Wang, Shan Liu, Brian Kulis, Peter Chin
The key idea is to replace the image to be compressed with a substitutional one that outperforms the original one in a desired way.
no code implementations • 3 May 2021 • Wei Jiang, Kun Liu, Themistoklis Charalambous
First, for all agents whose state matrix has no eigenvalues with positive real parts, a communication-delay-related observer, which is used to construct the controller, is designed for followers to estimate the leader's state information.
no code implementations • 7 Apr 2021 • Hao Wang, Xiangyu Yang, Wei Jiang
Specifically, if the current iterate is in the interior of the feasible set, then the weighted $\ell_{1}$ ball is formed by linearizing the $\ell_{p}$ norm at the current iterate.
1 code implementation • ICCV 2021 • Wei Jiang, Eduard Trulls, Jan Hosang, Andrea Tagliasacchi, Kwang Moo Yi
We propose a novel framework for finding correspondences in images based on a deep neural network that, given two images and a query point in one of them, finds its correspondence in the other.
Ranked #1 on
Dense Pixel Correspondence Estimation
on KITTI 2012
Dense Pixel Correspondence Estimation
Optical Flow Estimation
no code implementations • 19 Feb 2021 • Wei Jiang, Alexander M. Haimovich, Osvaldo Simeone
In the second approach, the transmitter and detector are trained simultaneously.
no code implementations • NeurIPS 2021 • Lijun Zhang, Wei Jiang, Shiyin Lu, Tianbao Yang
Moreover, when the hitting cost is both convex and $\lambda$-quadratic growth, we reduce the competitive ratio to $1 + \frac{2}{\sqrt{\lambda}}$ by minimizing the weighted sum of the hitting cost and the switching cost.
4 code implementations • ICCV 2021 • Shuting He, Hao Luo, Pichao Wang, Fan Wang, Hao Li, Wei Jiang
Extracting robust feature representation is one of the key challenges in object re-identification (ReID).
Ranked #1 on
Person Re-Identification
on Market-1501-C
no code implementations • 5 Feb 2021 • Wei Jiang, Hans Dieter Schotten
In this paper, we propose a novel cooperative multi-relay transmission scheme for mobile terminals to exploit spatial diversity.
Information Theory Signal Processing Information Theory
no code implementations • 5 Feb 2021 • Wei Jiang, Hans Dieter Schotten
Opportunistic relay selection (ORS) has been recognized as a simple but efficient method for mobile nodes to achieve cooperative diversity in slow fading channels.
no code implementations • 2 Feb 2021 • Wei Jiang, Bin Han, Mohammad Asif Habibi, Hans Dieter Schotten
As of today, the fifth generation (5G) mobile communication system has been rolled out in many countries and the number of 5G subscribers already reaches a very large scale.
no code implementations • 11 Jan 2021 • Qiuheng Zhou, Wei Jiang
The results from the measurement are then trained and tested on the channel prediction algorithm.
no code implementations • 4 Jan 2021 • Bin Han, Wei Jiang, Mohammad Asif Habibi, Hans D. Schotten
As of today, 5G mobile systems have been already widely rolled out, it is the right time for academia and industry to explore the next generation mobile communication system beyond 5G.
Networking and Internet Architecture
1 code implementation • 25 Dec 2020 • Jianyang Gu, Hao Luo, Weihua Chen, Yiqi Jiang, Yuqi Zhang, Shuting He, Fan Wang, Hao Li, Wei Jiang
Considering the large gap between the source domain and target domain, we focused on solving two biases that influenced the performance on domain adaptive pedestrian Re-ID and proposed a two-stage training procedure.
1 code implementation • 19 Dec 2020 • Wentao Zhao, Dalin Zhou, Xinguo Qiu, Wei Jiang
We introduce a standard, reproducible benchmark to which the same training settings can be applied for node classification.
no code implementations • CVPR 2021 • Daniel Rebain, Wei Jiang, Soroosh Yazdani, Ke Li, Kwang Moo Yi, Andrea Tagliasacchi
Moreover, we show that a Voronoi spatial decomposition is preferable for this purpose, as it is provably compatible with the Painter's Algorithm for efficient and GPU-friendly rendering.
1 code implementation • ECCV 2020 • Jianan Zhen, Qi Fang, Jiaming Sun, Wentao Liu, Wei Jiang, Hujun Bao, Xiaowei Zhou
Recovering multi-person 3D poses with absolute scales from a single RGB image is a challenging problem due to the inherent depth and scale ambiguity from a single view.
Ranked #11 on
3D Multi-Person Pose Estimation (absolute)
on MuPoTS-3D
no code implementations • 23 Apr 2020 • Kaiyan Chang, Wei Jiang, Jinyu Zhan, Zicheng Gong, Weijia Pan
Specifically, our design can improve the accuracy on MNIST up to 97. 26% compared with RC4. The accuracies on the datasets encrypted by ArchNet are 97. 26%, 84. 15% and 79. 80%, and they are 97. 31%, 82. 31% and 80. 22% on the original datasets, which shows that the encrypted accuracy of ArchNet has the same performance as the base model.
2 code implementations • 22 Apr 2020 • Shuting He, Hao Luo, Weihua Chen, Miao Zhang, Yuqi Zhang, Fan Wang, Hao Li, Wei Jiang
Our solution is based on a strong baseline with bag of tricks (BoT-BS) proposed in person ReID.
no code implementations • 18 Mar 2020 • Islam Elnabarawy, Wei Jiang, Donald C. Wunsch II
Collaborative filtering recommendation systems provide recommendations to users based on their own past preferences, as well as those of other users who share similar interests.
no code implementations • 3 Mar 2020 • Zicheng Qiu, Wei Jiang, Turghunjan Mamut
The experimental results show that the decoding based on the static and fully composed graph reduces state-of-the-art Word Error Rate (WER) on the clean and noiseless speech test task in THUYG-20 to 14. 24%.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
no code implementations • 29 Feb 2020 • Xing Fan, Hao Luo, Chi Zhang, Wei Jiang
Another challenge of RGB-infrared ReID is that the intra-person (images from the same person) discrepancy is often larger than the inter-person (images from different persons) discrepancy, so a dual-subspace pairing strategy is proposed to alleviate this problem.
no code implementations • 2 Dec 2019 • Wei Jiang, Alexander M. Haimovich, Osvaldo Simeone
An end-to-end learning approach is proposed for the joint design of transmitted waveform and detector in a radar system.
Signal Processing
no code implementations • CONLL 2019 • Yue Zhang, Wei Jiang, Qingrong Xia, Junjie Cao, Rui Wang, Zhenghua Li, Min Zhang
Our final submission ranks the third on the overall MRP evaluation metric, the first on EDS and the second on UCCA.
no code implementations • 12 Oct 2019 • Jingjing Qian, Wei Jiang, Hao Luo, Hongyan Yu
Vehicle re-identification (Re-ID) has been attracting increasing interest in the field of computer vision due to the growing utilization of surveillance cameras in public security.
1 code implementation • 17 Sep 2019 • Wei Jiang, Juan Camilo Gamboa Higuera, Baptiste Angles, Weiwei Sun, Mehrsan Javan, Kwang Moo Yi
We propose an optimization-based framework to register sports field templates onto broadcast videos.
3 code implementations • 14 Sep 2019 • Wei Jiang, Malgorzata Bogdan, Julie Josse, Blazej Miasojedow, Veronika Rockova, Traumabase group
We consider the problem of variable selection in high-dimensional settings with missing observations among the covariates.
Methodology Applications Computation
1 code implementation • CVPR 2020 • Weiwei Sun, Wei Jiang, Eduard Trulls, Andrea Tagliasacchi, Kwang Moo Yi
Many problems in computer vision require dealing with sparse, unordered data in the form of point clouds.
3 code implementations • 19 Jun 2019 • Hao Luo, Wei Jiang, Youzhi Gu, Fuxu Liu, Xingyu Liao, Shenqi Lai, Jianyang Gu
The present study collects and evaluates these effective training tricks in person ReID.
Ranked #48 on
Person Re-Identification
on DukeMTMC-reID
no code implementations • 19 Jun 2019 • Zaiqiang Wu, Wei Jiang
The experimental results also show that the proposed differentiable renderer is of higher accuracy and efficiency compared with previous method of differentiable renderer.
no code implementations • 18 Jun 2019 • Xinglong Zhang, Wei Jiang, Shuyou Yu, Xin Xu, Zhizhong Li
So far, many control algorithms have been developed for singularly perturbed systems.
no code implementations • SEMEVAL 2019 • Wei Jiang, Zhenghua Li, Yu Zhang, Min Zhang
The key idea is to convert a UCCA semantic graph into a constituent tree, in which extra labels are deliberately designed to mark remote edges and discontinuous nodes for future recovery.
Ranked #1 on
UCCA Parsing
on SemEval 2019 Task 1
no code implementations • 21 May 2019 • Wei Jiang, Yan Tang
The prevalent approaches of Chinese word segmentation task almost rely on the Bi-LSTM neural network.
2 code implementations • 25 Mar 2019 • Chongsheng Zhang, Guowen Peng, Yuefeng Tao, Feifei Fu, Wei Jiang, George Almpanidis, Ke Chen
Hence, we collect and annotate the ShopSign dataset to advance research in Chinese scene text detection and recognition.
8 code implementations • 17 Mar 2019 • Hao Luo, Youzhi Gu, Xingyu Liao, Shenqi Lai, Wei Jiang
In the literature, some effective training tricks are briefly appeared in several papers or source codes.
Ranked #2 on
Person Re-Identification
on UAV-Human
no code implementations • 17 Mar 2019 • Hao Luo, Xing Fan, Chi Zhang, Wei Jiang
Competition (or confrontation) is observed between the STN module and the ReID module, and two-stage training is applied to acquire a strong STNReID for partial ReID.
no code implementations • CVPR 2019 • Huanyu Liu, Chao Peng, Changqian Yu, Jingbo Wang, Xu Liu, Gang Yu, Wei Jiang
Panoptic segmentation, which needs to assign a category label to each pixel and segment each object instance simultaneously, is a challenging topic.
no code implementations • 11 Mar 2019 • Wei Jiang, Zhenghua Li, Yu Zhang, Min Zhang
The key idea is to convert a UCCA semantic graph into a constituent tree, in which extra labels are deliberately designed to mark remote edges and discontinuous nodes for future recovery.
no code implementations • 5 Mar 2019 • Wei Jiang, Na Ying
The accuracy of the object detection model depends on whether the anchor boxes effectively trained.
no code implementations • 24 Jan 2019 • Zaiqiang Wu, Wei Jiang, Hao Luo, Lin Cheng
To calculate the partial derivatives with respect to the coordinates of the vertices, we employed detection rays to divide vertices of statistical body shape models into different groups depending on whether the vertex is in the region of self-intersection.
1 code implementation • ICCV 2019 • Wei Jiang, Weiwei Sun, Andrea Tagliasacchi, Eduard Trulls, Kwang Moo Yi
We propose a novel image sampling method for differentiable image transformation in deep neural networks.
no code implementations • 16 Oct 2018 • Xing Fan, Hao Luo, Xuan Zhang, Lingxiao He, Chi Zhang, Wei Jiang
Holistic person re-identification (ReID) has received extensive study in the past few years and achieves impressive progress.
no code implementations • 3 Oct 2018 • Ken Goss, Wei Jiang
In this paper, we develop an innovative distributed architecture to obliviously manage and evaluate firewalls to prevent both insider and external attacks oriented to the firewalls.
Cryptography and Security
2 code implementations • 2 Jul 2018 • Xing Fan, Wei Jiang, Hao Luo, Mengjuan Fei
In this paper, we use a modified softmax function, termed Sphere Softmax, to solve the classification problem and learn a hypersphere manifold embedding simultaneously.
no code implementations • 11 Jun 2018 • Wei Jiang, Yan Wu
We propose the DFNet and make two main contributions, one is dynamic loss weights, and the other is residual fusion block (RFB).
1 code implementation • 11 May 2018 • Wei Jiang, Julie Josse, Marc Lavielle, Traumabase group
We propose a complete approach, including the estimation of parameters and their variance, derivation of confidence intervals, a model selection procedure, and a method for prediction on test sets with missing values.
Methodology
no code implementations • 19 Apr 2018 • Yan Wu, Tao Yang, Junqiao Zhao, Linting Guan, Wei Jiang
At the same time, we proposed a highly fused convolutional network (HFCN) based segmentation method for parking slot and lane markings based on the PSV dataset.
15 code implementations • 22 Nov 2017 • Xuan Zhang, Hao Luo, Xing Fan, Weilai Xiang, Yixiao Sun, Qiqi Xiao, Wei Jiang, Chi Zhang, Jian Sun
In this paper, we propose a novel method called AlignedReID that extracts a global feature which is jointly learned with local features.
Ranked #1 on
Person Re-Identification
on CUHK-SYSU
no code implementations • 11 May 2017 • Thangarajah Akilan, Q. M. Jonathan Wu, Wei Jiang
Following the rapidly growing digital image usage, automatic image categorization has become preeminent research area.