检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhang, Pengcheng Yu, Xiaohan Bai, Xiao Zheng, Jin Ning, Xin School of Computer Science and Engineering State Key Laboratory of Complex & Critical Software Environment Jiangxi Research Institute Beihang University Beijing China School of Computing Macquarie University Sydney Australia Institute of Semiconductors Chinese Academy of Sciences Beijing China

The development of person search techniques has been greatly promoted in recent years for its superior practicality and challenging goals. Despite their significant progress, existing person search models still lack the ability to continually learn from increasing real-world data and adaptively process input from different domains. To this end, this work introduces the continual person search task that sequentially learns on multiple domains and then performs person search on all seen domains. This requires balancing the stability and plasticity of the model to continually learn new knowledge without catastrophic forgetting. For this, we propose a Prompt-based Continual Person Search (PoPS) model in this paper. First, we design a compositional person search transformer to construct an effective pre-trained transformer without exhaustive pre-training from scratch on large-scale person search data. This serves as the fundamental for prompt-based continual learning. On top of that, we design a domain incremental prompt pool with a diverse attribute matching module. For each domain, we independently learn a set of prompts to encode the domain-oriented knowledge. Meanwhile, we jointly learn a group of diverse attribute projections and prototype embeddings to capture discriminative domain attributes. By matching an input image with the learned attributes across domains, the learned prompts can be properly selected for model inference. Extensive experiments are conducted to validate the proposed method for continual person search. The source code is available at https://***/PatrickZad/PoPS. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

GeoMamba: Towards Multi-granular POI Recommendation with Geographical state Space Model 39

GeoMamba: Towards Multi-granular POI Recommendation with Geo...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Qin, Yifang Xie, Jiaxuan Xiao, Zhiping Zhang, Ming State Key Laboratory for Multimedia Information Processing School of Computer Science PKU-Anker LLM Lab Peking University China School of Earth and Space Sciences Peking University China Paul G. Allen School of Computer Science and Engineering University of Washington United States

ISBN: (纸本)157735897X

Point-of-Interest (POI) recommendation plays an important role in a wide range of location-based social network applications, aiming to accurately predicting users' next visits based on their historical check-in records. Previous efforts have primarily focused on the modifications of existing sequential models, neglecting the fact that POI visiting sequences typically involve continuous state transformation of geographical and intention signals. Additionally, the diverse time span between check-ins require the model to properly recognize user's multi-granular preference. While recent advances of state Space Model (SSM) have revealed their potential in handling intricate temporal signals, we propose a state-based model that is tailored for spatio-temporal POI sequences. On top of traditional SSMs that are typically limited to linear sequences like Mamba, we propose GeoMamba, which customizes the model states to accommodate the spatio-temporal sequences, especially fitting for POI recommendations. Specifically, while the approximation operator HiPPO sets the foundation of linear SSMs, we introduce a novel GaPPO operator that extends the model's state space into graph-represented geographical domains. This innovation allows us to construct locational SSM encoders that seamlessly integrate users' spatio-temporal characteristics. The sequence-aware outputs of GeoMamba are further processed to generate multi-scale behavior representations. Extensive experimental results illustrate the superiority of GeoMamba over several state-of-the-art baselines. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： state space methods

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Shaping for Rotationally Symmetrical Two-Dimensional Constellations

Probabilistic Shaping for Rotationally Symmetrical Two-Dimen...

引用

IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)

作者： Ruimin Yuan Xinyuanmeng Yao Jiayi Yang Baoming Bai Xiao Ma State Key Lab. of ISN Xidian University Xi’an China School of Computer Science and Engineering Sun Yat-sen University Guangzhou China School of Electronics and Communication Engineering Sun Yat-sen University Shenzhen China

ISBN: (数字)9798350362244

ISBN: (纸本)9798350362251

A ring-based constant composition distribution matcher (R-CCDM) is designed for shaping rotationally symmetrical two-dimensional (RS-2D) constellations. The procedure of distribution matching can be divided into two steps. First, nonuniformly distributed rings are generated by CCDM to approach a probability distribution calculated from that of modulation symbols. Second, a uniform mapping is performed to select one amplitude signal point from each ring. Compared with CCDM, the proposed DM contains multiple amplitude compositions, and hence achieves less rate loss. Numerical results show that, at moderate spectral efficiency, probabilistic shaping with R-CCDM outperforms that with CCDM by about $0.2 \sim 0.3 \mathrm{~dB}$ for different modulation formats.

关键词： 6G mobile communication Quadrature amplitude modulation Spectral efficiency Simulation Modulation Symbols Probabilistic logic Probability distribution Land mobile radio

来源：评论

学校读者我要写书评

暂无评论

Linear time algorithms for k-means with multi-swap local search 23

Linear time algorithms for k-means with multi-swap local sea...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Junyu Huang Qilong Feng Ziyun Huang Jinhui Xu Jianxin Wang School of Computer Science and Engineering Central South University Changsha China and Xiangjiang Laboratory Changsha China Department of Computer Science and Software Engineering Penn State Erie The Behrend College Department of Computer Science and Engineering State University of New York at Buffalo NY School of Computer Science and Engineering Central South University Changsha China and Xiangjiang Laboratory Changsha China and The Hunan Provincial Key Lab of Bioinformatics Central South University Changsha China

The local search methods have been widely used to solve the clustering problems. In practice, local search algorithms for clustering problems mainly adapt the singleswap strategy, which enables them to handle large-scale datasets and achieve linear running time in the data size. However, compared with multi-swap local search algorithms, there is a considerable gap on the approximation ratios of the single-swap local search algorithms. Although the current multi-swap local search algorithms provide small constant approximation, the proposed algorithms tend to have large polynomial running time, which cannot be used to handle large-scale datasets. In this paper, we propose a multi-swap local search algorithm for the k-means problem with linear running time in the data size. Given a swap size t, our proposed algorithm can achieve a (50(1 + 1/t) + ε)-approximation, which improves the current best result 509 (ICML 2019) with linear running time in the data size. Our proposed method, compared with previous multi-swap local search algorithms, is the first one to achieve linear running time in the data size. To obtain a more practical algorithm for the problem with better clustering quality and running time, we propose a sampling-based method which accelerates the process of clustering cost update during swaps. Besides, a recombination mechanism is proposed to find potentially better solutions. Empirical experiments show that our proposed algorithms achieve better performances compared with branch and bound solver (NeurIPS 2022) and other existing state-of-the-art local search algorithms on both small and large datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robust Synthetic-to-Real Transfer for Stereo Matching

Robust Synthetic-to-Real Transfer for Stereo Matching

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Jiawei Zhang Jiahe Li Lei Huang Xiaohan Yu Lin Gu Jin Zheng Xiao Bai State Key Laboratory of Complex & Critical Software Environment School of Computer Science and Engineering Jiangxi Research Institute Beihang University SKLCCSE Institute of Artificial Intelligence Beihang University School of Computing Macquarie University Australia RIKEN AIP The University of Tokyo

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

With advancements in domain generalized stereo matching networks, models pre-trained on synthetic data demonstrate strong robustness to unseen domains. However, few studies have investigated the robustness after fine-tuning them in real-world scenarios, during which the domain generalization ability can be seriously degraded. In this paper, we explore fine-tuning stereo matching networks without compromising their robustness to unseen domains. Our motivation stems from comparing Ground Truth (GT) versus Pseudo label (PL) for fine-tuning: GT degrades, but PL preserves the domain generalization ability. Empirically, we find the difference between GT and PL implies valuable information that can regularize networks during fine-tuning. We also propose a framework to utilize this difference for fine-tuning, consisting of a frozen Teacher, an exponential moving average (EMA) Teacher, and a Student network. The core idea is to utilize the EMA Teacher to measure what the Student has learned and dynamically improve GT and PL for fine-tuning. We integrate our framework with state-of-the-art networks and evaluate its effectiveness on several real-world datasets. Extensive experiments show that our method effectively preserves the domain generalization ability during fine-tuning. Code is available at: https://***/jiaw-z/DKT-Stereo.

关键词： computer vision Codes Robustness Data models Pattern matching Synthetic data Meteorology

来源：评论

学校读者我要写书评

暂无评论

Instruction Tuning-free Visual Token Complement for Multimodal LLMs

arXiv

引用

arXiv 2024年

作者： Wang, Dongsheng Cui, Jiequan Li, Miaoge Lin, Wang Chen, Bo Zhang, Hanwang College of Computer Science and Software Engineering Shenzhen University China School of Computer Science and Engineering Nanyang Technological University Singapore Department of Computing Hong Kong Polytechnic University Hong Kong College of Computer Science and Technology Zhejiang University China National Key Lab of Radar Signal Processing Xidian University China

As the open community of large language models (LLMs) matures, multimodal LLMs (MLLMs) have promised an elegant bridge between vision and language. However, current research is inherently constrained by challenges such as the need for high-quality instruction pairs and the loss of visual information in image-to-text training objectives. To this end, we propose a Visual Token Complement framework (VTC) that helps MLLMs regain the missing visual features and thus improve response accuracy. Specifically, our VTC integrates text-to-image generation as a guide to identifying the text-irrelevant features, and a visual selector is then developed to generate complementary visual tokens to enrich the original visual input. Moreover, an iterative strategy is further designed to extract more visual information by iteratively using the visual selector without any additional training. Notably, the training pipeline requires no additional image-text pairs, resulting in a desired instruction tuning-free property. Both qualitative and quantitative experiments demonstrate the superiority and efficiency of our VTC. Copyright © 2024, The Authors. All rights reserved.

关键词： Visual BASIC

来源：评论

学校读者我要写书评

暂无评论

Domain adaptation for large-vocabulary object detectors 24

Domain adaptation for large-vocabulary object detectors

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Kai Jiang Jiaxing Huang Weiying Xie Jie Lei Yunsong Li Ling Shao Shijian Lu State Key Laboratory of Integrated Services Networks Xidian University Xi'an China S-lab School of Computer Science and Engineering Nanyang Technological University School of Electrical and Data Engineering at the University of Technology Sydney UCAS-Terminus AI Lab University of Chinese Academy of Sciences China

ISBN: (纸本)9798331314385

Large-vocabulary object detectors (LVDs) aim to detect objects of many categories, which learn super objectness features and can locate objects accurately while applied to various downstream data. However, LVDs often struggle in recognizing the located objects due to domain discrepancy in data distribution and object vocabulary. At the other end, recent vision-language foundation models such as CLIP demonstrate superior open-vocabulary recognition capability. This paper presents KGD, a Knowledge Graph Distillation technique that exploits the implicit knowledge graphs (KG) in CLIP for effectively adapting LVDs to various downstream domains. KGD consists of two consecutive stages: 1) KG extraction that employs CLIP to encode downstream domain data as nodes and their feature distances as edges, constructing KG that inherits the rich semantic relations in CLIP explicitly; and 2) KG encapsulation that transfers the extracted KG into LVDs to enable accurate cross-domain object classification. In addition, KGD can extract both visual and textual KG independently, providing complementary vision and language knowledge for object localization and object classification in detection tasks over various downstream domains. Experiments over multiple widely adopted detection benchmarks show that KGD outperforms the state-of-the-art consistently by large margins.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EvSTVSR: Event Guided Space-Time Video Super-Resolution 39

EvSTVSR: Event Guided Space-Time Video Super-Resolution

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Yan, Haojie Lu, Zhan Chen, Zehao Ma, De Tang, Huajin Zheng, Qian Pan, Gang The State Key Lab of Brain-Machine Intelligence Zhejiang University China College of Computer Science and Technology Zhejiang University China School of Electrical and Electronic Engineering Nanyang Technological University Singapore

ISBN: (纸本)157735897X

In the domain of space-time video super-resolution, it is typically challenging to handle complex motions (including large and nonlinear motions) and varying illumination scenes due to the lack of inter-frame information. Leveraging the dense temporal information provided by event signals offers a promising solution. Traditional event-based methods typically rely on multiple images, using motion estimation and compensation, which can introduce errors. Accumulated errors from multiple frames often lead to artifacts and blurriness in the output. To mitigate these issues, we propose EvSTVSR, a method that uses fewer adjacent frames and integrates dense temporal information from events to guide alignment. Additionally, we introduce a coordinate-based feature fusion upsampling module to achieve spatial super-resolution. Experimental results demonstrate that our method not only outperforms existing RGB-based approaches but also excels in handling large motion scenarios. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Holographic Integrated Data and Energy Transfer

arXiv

引用

arXiv 2024年

作者： Huang, Qingxiao Hu, Jie Zhao, Yizhe Yang, Kun School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu611731 China State Key Laboratory of Novel Software Technology Nanjing University Nanjing210008 China Suzhou215163 China School of Computer Science and Electronic Engineering University of Essex United Kingdom

Thanks to the application of metamaterials, holographic multiple-input multiple-output (H-MIMO) is expected to achieve a higher spatial diversity gain by enabling the ability to generate any current distribution on the surface. With the aid of electromagnetic (EM) manipulation capability of H-MIMO, integrated data and energy transfer (IDET) system can fully exploits the EM channel to realize energy focusing and eliminate inter-user interference, which yields the concept of holographic IDET (H-IDET). In this paper, we invetigate the beamforming designs for H-IDET systems, where the sum-rate of data users (DUs) are maximized by guaranteeing the energy harvesting requirements of energy users (EUs). In order to solve the non-convex functional programming, a block coordinate descent (BCD) based scheme is proposed, wherein the Fourier transform and the equivalence between the signal-to-interference-plus-noise ratio (SINR) and the mean-square error (MSE) are also conceived, followed by the successive convex approximation (SCA) and an initialization scheme to enhance robustness. Numerical results illustrate that our proposed H-IDET scheme outperforms benchmark schemes, especially the one adopting traditional discrete antennas. Besides, the near-field focusing using EM channel model achieves better performance compared to that using the traditional channel model, especially for WET where the EUs are usually close to the transmitter. Copyright © 2024, The Authors. All rights reserved.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Accurate and Complete Captions for Question-controlled Text-aware Image Captioning

Accurate and Complete Captions for Question-controlled Text-...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yehuan Wang Jian Hu Lin Shang Department of Computer Science and Technology State Key Laboratory for Novel Software Technology Nanjing University Nanjing China School of Mechanical Engineering Nanjing University of Science and Technology Nanjing China

Question-controlled Text-aware Image Captioning (Qc-TextCap), is the task of generating a distinctive scene text aware caption according to several personalized questions when given an image. However, due to the diversity of visual scene, it is hard for current Optical Character Recognition (OCR) systems to extract complete scene text sentences from the images. Besides, existing works are limited in their use of question features and visual features. In this paper, we propose a Multimodal Transformer plus Scene text clustering and Cross modal attention (MTSC) to tackle the above challenges. We devise scene text clustering to group relevant scene text pieces which are detected as separate results by current OCR systems. To better utilize the information in questions and images, we design cross modal attention to enrich the features of both modalities. We extensively evaluate our model on the two Qc-TextCap datasets and superior results are achieved when comparing to state-of-the-art approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：