检索结果-内蒙古大学图书馆

Grasp as You Say: Language-guided Dexterous Grasp Generation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wei, Yi-Lin Jiang, Jian-Jian Xing, Chengyi Tan, Xian-Tuo Wu, Xiao-Ming Li, Hao Cutkosky, Mark Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Stanford University United States Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

This paper explores a novel task "Dexterous Grasp as You Say" (DexGYS), enabling robots to perform dexterous grasping based on human commands expressed in natural language. However, the development of this field is hindered by the lack of datasets with natural human guidance;thus, we propose a language-guided dexterous grasp dataset, named DexGYSNet, offering high-quality dexterous grasp annotations along with flexible and fine-grained human language guidance. Our dataset construction is cost-efficient, with the carefully-design hand-object interaction retargeting strategy, and the LLM-assisted language guidance annotation system. Equipped with this dataset, we introduce the DexGYSGrasp framework for generating dexterous grasps based on human language instructions, with the capability of producing grasps that are intent-aligned, high quality and diversity. To achieve this capability, our framework decomposes the complex learning process into two manageable progressive objectives and introduce two components to realize them. The first component learns the grasp distribution focusing on intention alignment and generation diversity. And the second component refines the grasp quality while maintaining intention consistency. Extensive experiments are conducted on DexGYSNet and real world environments for validation. Copyright © 2024, The Authors. All rights reserved.

关键词： Natural language processing systems

EPIMR:Prediction of Enhancer-Promoter Interactions by Multi-Scale ResNet on Image Representation

学校读者我要写书评

暂无评论

Big Data Mining and Analytics 2024年第3期7卷 668-681页

作者： Qiaozhen Meng Yinuo Lyu Xiaoqing Peng Junhai Xu Jijun Tang Fei Guo School of Computer Science and Technology College of Intelligence and ComputingTianjin UniversityTianjin 300350China Aeronautical Information Service Center of the Civil Aviation Administration of China(AISC.ATMB.CAAC) Beijing 100015China Center for Medical Genetics&Hunan Key Laboratory of Medical Genetics School of Life SciencesCentral South UniversityChangsha 410038China Shenzhen Institute of Advanced Technology Chinese Academy of SciencesShenzhen 518000China School of Computer Science and Engineering Central South UniversityChangsha 410083China

Prediction of enhancer-promoter interactions(EPIs)is key to regulating gene expression and diagnosing genetic *** to limited resolution,biological experiments perform not as well as expected while precisely identifying specific interactions,giving rise to computational biology *** EPI predictors have been developed,but their prediction accuracy still needs to be ***,we design a new model named EPIMR to identify enhancer-promoter ***,Hilbert Curve is utilized to represent sequences to images to preserve the position and spatial ***,a multi-scale residual neural network(ResNet)is used to learn the distinguishing features of different abstraction ***,matching heuristics are adopted to concatenate the learned features of enhancers and promoters,which pays attention to their potential interaction *** results on six cell lines indicate that EPIMR performs better than existing methods,with higher area under the precision-recall curve(AUPR)and area under the receiver operating characteristic(AUROC)results on benchmark and under-sampling ***,our model is pre-trained on all cell lines,which improves not only the transferability of cross-cell line prediction,but also cell line-specific prediction *** conclusion,our method serves as a valuable technical tool for predicting enhancer-promoter interactions,contributing to the understanding of gene transcription *** code and results are available at https://***/guofei-tju/EPIMR.

关键词： enhancer-promoter interactions Hilbert Curve multi-scale residual neural network(ResNet)

Selective Hourglass Mapping for Universal Image Restoration Based on Diffusion Model

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zheng, Dian Wu, Xiao-Ming Yang, Shuzhou Zhang, Jian Hu, Jian-Fang Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China School of Electronic and Computer Engineering Peking University China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Universal image restoration is a practical and potential computer vision task for real-world applications. The main challenge of this task is handling the different degradation distributions at once. Existing methods mainly utilize task-specific conditions (e.g., prompt) to guide the model to learn different distributions separately, named multi-partite mapping. However, it is not suitable for universal model learning as it ignores the shared information between different tasks. In this work, we propose an advanced selective hourglass mapping strategy based on diffusion model, termed DiffUIR. Two novel considerations make our DiffUIR non-trivial. Firstly, we equip the model with strong condition guidance to obtain accurate generation direction of diffusion model (selective). More importantly, DiffUIR integrates a flexible shared distribution term (SDT) into the diffusion algorithm elegantly and naturally, which gradually maps different distributions into a shared one. In the reverse process, combined with SDT and strong condition guidance, DiffUIR iteratively guides the shared distribution to the task-specific distribution with high image quality (hourglass). Without bells and whistles, by only modifying the mapping strategy, we achieve state-of-the-art performance on five image restoration tasks, 22 benchmarks in the universal setting and zero-shot generalization setting. Surprisingly, by only using a lightweight model (only 0.89M), we could achieve outstanding performance. The source code and pre-trained models are available at https://***/iSEE-laboratory/DiffUIR. Copyright © 2024, The Authors. All rights reserved.

关键词： Image reconstruction

Ultra-high extinction ratio optical pulse generation with a thin film lithium niobate modulator for distributed acoustic sensing

学校读者我要写书评

暂无评论

Photonics Research 2024年第1期12卷 40-50页

作者： YUAN SHEN XIAOQIAN SHU LINGMEI MA SHAOLIANG YU GENGXIN CHEN LIU LIU RENYOU GE BIGENG CHEN YUNJIANG RAO Research Center for Optical Fiber Sensing Zhejiang LaboratoryHangzhou 311100China Research Center for Intelligent Optoelectronic Computing Zhejiang LaboratoryHangzhou 311100China International Research Center for Advanced Photonics College of Optical Science and EngineeringZhejiang UniversityHangzhou 310058China Fiber Optics Research Center(FORC) Key Laboratory of Optical Fiber Sensing and CommunicationsUniversity of Electronic Science and Technology of ChinaChengdu 611731China

We experimentally demonstrate ultra-high extinction ratio(ER)optical pulse modulation with an electro-optical modulator(EOM)on thin film lithium niobate(TFLN)and its application for fiber optic distributed acoustic sensing(DAS).An interface carrier effect leading to a relaxation-tail response of TFLN EOM is discovered,which can be well addressed by a small compensation component following the main driving *** ultrahigh ER>50 dB is achieved by canceling out the tailed response during pulse modulation using the EOM based on a cascaded Mach–Zehnder interferometer(MZI)*** modulated optical_(√)pulses are then utilized as a probe light for a DAS system,showing a sensitivity up to-62.9 dB·rad∕Hz~2(7 pε/Hz)for 2-km single-mode sensing *** crosstalk suppression of 24.9 dB along the fiber is also obtained when the ER is improved from 20 dB to 50 dB,clearly revealing its importance to the sensing performance.

关键词： modulator pulse interferometer

NECA: Neural Customizable Human Avatar

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xiao, Junjin Zhang, Qing Xu, Zhan Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Adobe Research United States Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Human avatar has become a novel type of 3D asset with various applications. Ideally, a human avatar should be fully customizable to accommodate different settings and environments. In this work, we introduce NECA, an approach capable of learning versatile human representation from monocular or sparse-view videos, enabling granular customization across aspects such as pose, shadow, shape, lighting and texture. The core of our approach is to represent humans in complementary dual spaces and predict disentangled neural fields of geometry, albedo, shadow, as well as an external lighting, from which we are able to derive realistic rendering with high-frequency details via volumetric rendering. Extensive experiments demonstrate the advantage of our method over the state-of-the-art methods in photorealistic rendering, as well as various editing tasks such as novel pose synthesis and relighting. The code is available at https://***/iSEE-laboratory/NECA. Copyright © 2024, The Authors. All rights reserved.

关键词： Lighting

Robust Generative Steganography for Image Hiding Using Concatenated Mappings

学校读者我要写书评

暂无评论

IEEE Transactions on Information Forensics and Security 2025年 20卷 5952-5965页

作者： Liyan Chen Bingwen Feng Zhihua Xia Wei Lu Jian Weng College of Cyber Security Jinan University Guangzhou China College of Cyber Security Engineering Research Center of Trustworthy AI Ministry of Education Jinan University Guangzhou China School of Computer Science and Engineering Guangdong Province Key Laboratory of Information Security Technology Ministry of Education Key Laboratory of Machine Intelligence and Advanced Computing Sun Yat-sen University Guangzhou China

Generative steganography stands as a promising technique for information hiding, primarily due to its remarkable resistance to steganalysis detection. Despite its potential, hiding a secret image using existing generative steganographic models remains a challenge, especially in lossy or noisy communication channels. This paper proposes a robust generative steganography model for hiding full-size image. It lies on three reversible concatenated mappings proposed. The first mapping uses VQGAN with an order-preserving codebook to compress an image into a more concise representation. The second mapping incorporates error correction to further convert the representation into a robust binary representation. The third mapping devises a distribution-preserving sampling mapping that transforms the binary representation into the latent representation. This latent representation is then used as input for a text-to-image Diffusion model, which generates the final stego image. Experimental results show that our proposed scheme can freely customize the stego image content. Moreover, it simultaneously attains high stego and recovery image quality, high robustness, and provable security.

关键词： Steganography Robustness Security Image coding Diffusion models Training Transforms Neural networks Gaussian noise Electronic mail

Event-Guided Procedure Planning from Instructional Videos with Text Supervision

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, An-Lan Lin, Kun-Yu Du, Jia-Run Meng, Jingke Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

In this work, we focus on the task of procedure planning from instructional videos with text supervision, where a model aims to predict an action sequence to transform the initial visual state into the goal visual state. A critical challenge of this task is the large semantic gap between observed visual states and unobserved intermediate actions, which is ignored by previous works. Specifically, this semantic gap refers to that the contents in the observed visual states are semantically different from the elements of some action text labels in a procedure. To bridge this semantic gap, we propose a novel event-guided paradigm, which first infers events from the observed states and then plans out actions based on both the states and predicted events. Our inspiration comes from that planning a procedure from an instructional video is to complete a specific event and a specific event usually involves specific actions. Based on the proposed paradigm, we contribute an Event-guided Prompting-based Procedure Planning (E3P) model, which encodes event information into the sequential modeling process to support procedure planning. To further consider the strong action associations within each event, our E3P adopts a mask-and-predict approach for relation mining, incorporating a probabilistic masking scheme for regularization. Extensive experiments on three datasets demonstrate the effectiveness of our proposed model. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

Interlayer sensitized van der Waals heterojunction photodetector with enhanced performance

学校读者我要写书评

暂无评论

Nano Research 2023年第7期16卷 10537-10544页

作者： Huide Wang Yonghong Zeng FanXu Meng Rui Cao Yi Liu Zhinan Guo Tingting Wang Haiguo Hu Sidi Fan Yatao Yang SWageh Omar AAl-Hartomy Abul Kalam Yonghong Shao Yu-Jia Zeng Dianyuan Fan Han Zhang International Collaborative Laboratory of 2D Materials for Optoelectronics Science and Technology Institute of Microscale OptoelectronicsInterdisciplinary Center of High Magnetic Field Physics of Shenzhen UniversityCollege of Physics and Optoelectronic EngineeringShenzhen UniversityShenzhen 518060China Guangzhou Key Laboratory of Sensing Materials and Devices Center for Advanced Analytical ScienceSchool of Chemistry and Chemical EngineeringGuangzhou UniversityGuangzhou 510006China Key Laboratory of Optoelectronic Devices and Systems of Ministry of Education and Guangdong Province College of Physics and Optoelectronic EngineeringShenzhen UniversityShenzhen 518060China College of Electronics and Information Engineering Shenzhen UniversityShenzhen 518060China Center of Characterization and Analysis Jilin Institute of Chemical TechnologyJilin 132022China School of Mathematical&Physical Sciences Wuhan Textile UniversityWuhan 430200China Department of Physics Faculty of ScienceKing Abdulaziz UniversityJeddah 21589Saudi Arabia Research Center for Advanced Materials Science(RCAMS) King Khalid UniversityP.O.Box 9004Abha 61413Saudi Arabia Department of Chemistry College of ScienceKing Khalid UniversityP.O.Box 9004Abha 61413Saudi Arabia

Although photodetection based on two-dimensional(2D)van der Waals(vdWs)P-N heterojunction has attracted extensive attention recently,their low responsivity(R)due to the lack of carrier gain mechanism in reverse bias or zero bias operation hinders their applications in advanced photodetection ***,a black phosphorus/rhodamine 6G/molybdenum disulfide(BP/R6G/MoS_(2))photodiode with high responsivity at reverse bias or zero bias has been achieved by using interfacial charge transfer of R6G molecules assembled between heterojunction *** formed vdWs interface achieves high performance photoresponse by efficiently separating the additional photogenerated electrons and holes generated by R6G *** devices sensitized by the dye molecule R6G exhibit enhanced photodetection performance without sacrificing the photoresponse *** them,the R increased by 14.8-20.4 times,and the specific detectivity(D^(*))increased by 24.9-34.4 *** strategy based on interlayer assembly of dye molecules proposed here may pave a new way for realizing high-performance photodetection based on 2D vdWs heterojunctions with high responsivity and fast response speed.

关键词： heterojunction photodetector interlayer sensitization charge transfer responsivity

Event-Guided Procedure Planning from Instructional Videos with Text Supervision

学校读者我要写书评

暂无评论

Event-Guided Procedure Planning from Instructional Videos wi...

International Conference on Computer Vision (ICCV)

作者： An-Lan Wang Kun-Yu Lin Jia-Run Du Jingke Meng Wei-Shi Zheng School of Computer Science and Engineering Sun Yat-sen University China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

关键词：