检索结果-内蒙古大学图书馆

A Comprehensive Survey of 3D Dense Captioning: Localizing and Describing Objects in 3D Scenes

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yu, Ting Lin, Xiaojun Wang, Shuhui Sheng, Weiguo Huang, Qingming Yu, Jun School of Information Science and Technology Hangzhou Normal University Hangzhou311121 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China Key Laboratory of Complex Systems Modeling and Simulation School of Computer Science and Technology Hangzhou Dianzi University Hangzhou310018 China

Three-Dimensional (3D) dense captioning is an emerging vision-language bridging task that aims to generate multiple detailed and accurate descriptions for 3D scenes. It presents significant potential and challenges due to its closer representation of the real world compared to 2D visual captioning, as well as complexities in data collection and processing of 3D point cloud sources. Despite the popularity and success of existing methods, there is a lack of comprehensive surveys summarizing the advancements in this field, which hinders its progress. In this paper, we provide a comprehensive review of 3D dense captioning, covering task definition, architecture classification, dataset analysis, evaluation metrics, and in-depth prosperity discussions. Based on a synthesis of previous literature, we refine a standard pipeline that serves as a common paradigm for existing methods. We also introduce a clear taxonomy of existing models, summarize technologies involved in different modules, and conduct detailed experiment analysis. Instead of a chronological order introduction, we categorize the methods into different classes to facilitate exploration and analysis of the differences and connections among existing techniques. We also provide a reading guideline to assist readers with different backgrounds and purposes in reading efficiently. Furthermore, we propose a series of promising future directions for 3D dense captioning by identifying challenges and aligning them with the development of related tasks, offering valuable insights and inspiring future research in this field. Our aim is to provide a comprehensive understanding of 3D dense captioning, foster further investigations, and contribute to the development of novel applications in multimedia and related domains. Copyright © 2024, The Authors. All rights reserved.

关键词： Data handling

Targeting Ultra-Emitters for Effective Methane Mitigation in China’s Coal Sector

学校读者我要写书评

暂无评论

ACS ES&T Air

ACS ES&T Air 2024年第7期1卷 734-742页

作者： Helan Wang Bo Zheng Hui Li Qiang Zhang Kebin He Shenzhen Key Laboratory of Ecological Remediation and Carbon Sequestration Institute of Environment and Ecology Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen 518055 China State Environmental Protection Key Laboratory of Sources and Control of Air Pollution Complex Beijing 100084 China Department of Earth System Science Ministry of Education Key Laboratory for Earth System Modeling Institute for Global Change Studies Tsinghua University Beijing 100084 China State Key Joint Laboratory of Environment Simulation and Pollution Control School of Environment Tsinghua University Beijing 100084 China

The energy system fuels climate change as the largest emitter of global greenhouse gases, while a lack of transparent, infrastructure-level information undermines efforts to cut emissions. Coal mining has been the largest emitter of methane (CH4) in China over the past 10 years, which is not tracked at the mine level, and effective mitigation pathways have yet to be established. Herein, we develop a state-of-the-art CH4emission database, comprising 3343 active coal mines in China, by harmonizing multisource information. The results suggest that China’s coal mines emitted 15.8 ± 5.1 million metric tons CH4yr–1in 2019. Those with CH4emission intensities >2 standard deviations above the national mean accounted for 4% of China’s coal production, yet they generated 23% of China’s coal CH4emissions. We project a steady decline in China’s coal CH4emissions by >75% in 2100 compared to 2019 levels under three different scenarios, due to reduced coal demand during energy transition. Targeting ultra-emitters for mine closure will accelerate emission reductions in the midterm and achieve deep CH4emission cuts by >92% in 2100, which buys us time to control global warming. Our idealized mine closure strategy serves as a cost-effective CH4mitigation strategy to enable swift climate action.

关键词： Biological databases Climate Coal Energy Hydrocarbons

Fermi-Energy-Sensitive Universal Conductance Fluctuations in Anisotropic Materials

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Yang, Qiang Hu, Yayun Hou, Zhe Tong, Peiqing School of Physics and Technology Nanjing Normal University Nanjing210023 China Zhejiang Lab Hangzhou311100 China Ministry of Education Key Laboratory of Numerical Simulation of Large Scale Complex Systems Nanjing Normal University Nanjing210023 China

Universal conductance fluctuations (UCF) are a hallmark of quantum interference in mesoscopic devices. According to the Altshuler-Lee-Stone theory, the amplitude of UCF remains independent of system parameters such as Fermi energy and disorder strength. However, recent experiments have demonstrated a significant variation in UCF with respect to Fermi energy in the anisotropic Dirac semimetal Cd3As2, suggesting a dependence on band anisotropy. In this work, we reconcile the discrepancy between theoretical predictions and experimental observations through a detailed study of UCF versus Fermi energy using a tight-binding model with tunable anisotropy parameters. Near the band edge, the Hamiltonian is simplified to an anisotropic free electron gas model, recovering the generalized Altshuler-Lee-Stone theory. However, as the Fermi energy shifts toward the band center, where rotational symmetry breaks into C4 (four-fold rotational) symmetry, the UCF amplitude deviates from the standard theory. Our findings reveal that UCF becomes increasingly sensitive to Fermi energy as the anisotropy grows stronger. Furthermore, using realistic parameters for Cd3As2, our calculations demonstrate an increase in UCF away from the Dirac point, in qualitative agreement with experimental results. The enhancement of UCF occurs in two perpendicular transport directions that we have calculated, albeit with quantitative differences in magnitude, which can be tested in future experiments. Given the prevalence of anisotropic materials and technical advances in engineering anisotropy through strain or twist, our results offer a valuable reference for characterizing intrinsic electronic properties via UCF. © 2025, CC BY.

关键词： Anisotropic media

Prompting Video-Language Foundation Models with Domain-specific Fine-grained Heuristics for Video Question Answering

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yu, Ting Fu, Kunhao Wang, Shuhui Huang, Qingming Yu, Jun School of Information Science and Technology Hangzhou Normal University Hangzhou311121 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China Key Laboratory of Complex Systems Modeling and Simulation School of Computer Science and Technology Hangzhou Dianzi University Hangzhou310018 China

Video Question Answering (VideoQA) represents a crucial intersection between video understanding and language processing, requiring both discriminative unimodal comprehension and sophisticated cross-modal interaction for accurate inference. Despite advancements in multi-modal pre-trained models and video-language foundation models, these systems often struggle with domain-specific VideoQA due to their generalized pre-training objectives. Addressing this gap necessitates bridging the divide between broad cross-modal knowledge and the specific inference demands of VideoQA tasks. To this end, we introduce HeurVidQA, a framework that leverages domain-specific entity-action heuristics to refine pre-trained video-language foundation models. Our approach treats these models as implicit knowledge engines, employing domain-specific entity-action prompters to direct the model’s focus toward precise cues that enhance reasoning. By delivering fine-grained heuristics, we improve the model’s ability to identify and interpret key entities and actions, thereby enhancing its reasoning capabilities. Extensive evaluations across multiple VideoQA datasets demonstrate that our method significantly outperforms existing models, underscoring the importance of integrating domain-specific knowledge into video-language models for more accurate and context-aware VideoQA. Copyright © 2024, The Authors. All rights reserved.

关键词： Inference engines

Analysis of Ω(2012) as a molecule in the chiral quark model

学校读者我要写书评

暂无评论

Physical Review D 2022年第5期106卷 054028-054028页

作者： Xiaohuang Hu Jialun Ping Department of Physics and Jiangsu Key Laboratory for Numerical Simulation of Large Scale Complex Systems Nanjing Normal University Nanjing 210023 People’s Republic of China

Inspired by the updated information on Ω(2012) by the Belle Collaboration, we conduct a study of all possible S-wave pentaquark systems with quark contents sssqq¯,q=u, d in a chiral quark model with the help of Gaussian expansion method. Channel coupling is also considered. The real-scaling method (stabilization method) is employed to identify and check the bound states and the genuine resonances. In addition, the decay widths of all resonances are given. The results show that Ω(2012) can be interpreted as a Ξ*K¯ molecular state with quantum number of IJP=0(32)−. Another bound state Ωπ with IJP=1(32)− is also found. Other resonances are obtained: Ξ*K¯* with IJP=0(12)− and 0(32)−. These pentaquark states is expected to be further verified in future experiments.

关键词： Quark model

Is d∗(2380) a compact hexaquark state?

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Pan, Manying Zhu, Xinmei Ping, Jialun Department of Physics Jiangsu Key Laboratory for Numerical Simulation of Large Scale Complex Systems Nanjing Normal University Nanjing210023 China Department of Physics Yangzhou University Yangzhou225009 China

The most fascinating dibaryon in the non-strange quark sector is d∗(2380), which was reported by WASA-at-COSY Collaboration and confirmed by A2@MAMI Collaboration. The reported mass and decay width are M ≈ 2.37 GeV, Γ ≈ 70 MeV and the quantum numbers are IJP = 03+. The structure of d∗(2380) is still in controversy. In the present calculation, the powerful method in few-body system, Gaussian Expansion Method (GEM) is employed to explore the structure of d∗(2380) in the framework of constituent quark models without assuming the presupposed structure. The results show that the radius of d∗(2380) is around 0.8 fm, it is a very compact object. Because of the compact structure, the color singlet-singlet component has a large overlap with the color octet-octet one, two colorless, large overlapped ∆s dominate the state is possible. Copyright © 2023, The Authors. All rights reserved.

关键词： Color

Analysis of Ω(2012) as a molecule in the chiral quark model

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Hu, Xiaohuang Ping, Jialun Department of Physics Jiangsu Key Laboratory for Numerical Simulation of Large Scale Complex Systems Nanjing Normal University Nanjing210023 China

Inspired by the updated information on Ω(2012) by the Belle Collaboration, we conduct a study of all possible S-wave pentaquark systems with quark contents sssqq¯, q = u, d in a chiral quark model with the help of Gaussian expansion method. Channel coupling is also considered. The real-scaling method (stabilization method) is employed to identify and check the bound states and the genuine resonances. In addition, the decay widths of all resonances are given. The results show that Ω(2012) can be interpreted as a Ξ∗K molecular state with quantum number of IJP= 0(3/2)-. Other resonances are obtained: Ξ∗K∗with IJP= 0(1/2)-and0(3/2)-, Ωπ with IJP= 1(3/2)-. These pentaquark states is expected to be further verified in future experiments. Copyright © 2022, The Authors. All rights reserved.

关键词： Resonance

Exploring Dynamical Phase Transitions in the XY Chain through Linear Quench: Early and Long-term Perspectives

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Cao, Kaiyuan Tong, Peiqing Zhejiang Lab Hangzhou311100 China Department of Physics Institute of Theoretical Physics Nanjing Normal University Nanjing210023 China Jiangsu Key Laboratory for Numerical Simulation of Large Scale Complex Systems Nanjing Normal University Nanjing210023 China

We investigate the nonequilibrium dynamics induced by a finite-time linear quench in the XY chain. Initially, we examine the dynamical quantum phase transition, characterized by the nonanalytic behavior of the Loschmidt amplitude. We find distinct behaviors of DQPTs during and following the ramp. Following the ramp, the ramp crossing the critical point hc is the sufficient condition for the occurrence of DQPT, but it is not during the ramp. Through AIA approximation analysis, we establish that adequate distancing from the critical point is crucial for DQPT manifestation during the ramp, elucidating the absence of DQPT as the ramp gets faster. Additionally, we explore another type of dynamical phase transition, describing the long-term relaxation behavior of the order parameter. Our finding indicates that the asymptotic behavior of the time-dependent part induced by the linear quench is equivalent to that following a sudden quench, i.e., time-dependent part exhibits power-law decays of ∼ t−3/2 and ∼ t−1/2 for the ramp to the commensurate and incommensurate phases, respectively. Moreover, we also delve into the steady part, which showcases nonanalytic singularities at the critical point. Copyright © 2024, The Authors. All rights reserved.

关键词： Phase transitions

Privacy sensitive large-margin model for face de-identification 1st

学校读者我要写书评

暂无评论

Privacy sensitive large-margin model for face de-identifica...

1st International Conference on Neural Computing for Advanced Applications, NCAA 2020

作者： Guo, Zhiqiang Liu, Huigui Kuang, Zhenzhong Nakashima, Yuta Babaguchi, Noboru Key Laboratory of Complex Systems Modeling and Simulation School of Computer Science and Technology Hangzhou Dianzi University Hangzhou310018 China Osaka University Osaka Japan

ISBN: (纸本)9789811576690

There is an increasing concern of face privacy protection along with the wide application of big media data and social networks due to free online data release. Although some pioneering works obtained some achievements, they are not sufficient enough for sanitizing the sensitive identity information. In this paper, we propose a generative approach to de-identify face images yet preserving the non-sensitive information for data reusability. To ensure a high privacy level, we introduce a large-margin model for the synthesized new identities by keeping a safe distance with both the input identity and existing identities. Besides, we show that our face de-identification operation follows the (Formula Presented)-differential privacy rule which can provide a rigorous privacy notion in theory. We evaluate the proposed approach using the vggface dataset and compare with several state-of-the-art methods. The results show that our approach outperforms previous solutions for effective face privacy protection while preserving the major utilities. © Springer Nature Singapore Pte Ltd. 2020.

关键词： Privacy-preserving techniques