检索结果-内蒙古大学图书馆

NAS-HR:Neural architecture search for heart rate estimation from face videos

学校读者我要写书评

暂无评论

Virtual Reality & intelligent Hardware 2021年第1期3卷 33-42页

作者： Hao LU Hu HAN School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Key Laboratory of Intelligent Information Processing Chinese Academy of Sciences(CAS)Institute of Computing TechnologyBeijing 100080China Peng Cheng Laboratory Shenzhen 518000China

Background In anticipation of its great potential application to natural human-computer interaction and health monitoring,heart-rate(HR)estimation based on remote photoplethysmography has recently attracted increasing research *** the recent deep-learning-based HR estimation methods have achieved promising performance,their computational costs remain high,particularly in mobile-computing *** We propose a neural architecture search approach for HR estimation to automatically search a lightweight network that can achieve even higher accuracy than a complex network while reducing the computational ***,we define the regions of interests based on face landmarks and then extract the raw temporal pulse signals from the R,G,and B channels in each ***,pulse-related signals are extracted using a plane-orthogonal-to-skin algorithm,which are combined with the R and G channel signals to create a spatial-temporal ***,a differentiable architecture search approach is used for the network-structure *** Compared with the state-of-the-art methods on the public-domain VIPL-HR and PURE databases,our method achieves better HR estimation performance in terms of several evaluation metrics while requiring a much lower computational cost1.

关键词： Heart-rate estimation Plane-orthogonal-to-skin STMap Differentiable architecture search

Improving Molecular Graph Generation with Flow Matching and Optimal Transport

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Hou, Xiaoyang Zhu, Tian Ren, Milong Bu, Dongbo Gao, Xin Zhang, Chunming Sun, Shiwei Key Laboratory of Intelligent Information Processing Institute of Computing Technology School of Computer Science and Technology University of Chinese Academy of Sciences China Central China Research Institute for Artificial Intelligence Technologies China Western Institute of Computing Technology Phil Rivers Technology King Abdullah University of Science and Technology Saudi Arabia

Generating molecular graphs is crucial in drug design and discovery but remains challenging due to the complex interdependencies between nodes and edges. While diffusion models have demonstrated their potentiality in molecular graph design, they often suffer from unstable training and inefficient sampling. To enhance generation performance and training stability, we propose GGFlow, a discrete flow matching generative model incorporating optimal transport for molecular graphs and it incorporates an edge-augmented graph transformer to enable the direct communications among chemical bounds. Additionally, GGFlow introduces a novel goal-guided generation framework to control the generative trajectory of our model, aiming to design novel molecular structures with the desired properties. GGFlow demonstrates superior performance on both unconditional and conditional molecule generation tasks, outperforming existing baselines and underscoring its effectiveness and potential for wider application. © 2024, CC BY.

关键词： Molecular docking

Redundant Data Detection and Deletion to Meet Privacy Protection Requirements in Blockchain-Based Edge computing Environment

学校读者我要写书评

暂无评论

China Communications 2024年第3期21卷 149-159页

作者： Zhang Lejun Peng Minghui Su Shen Wang Weizheng Jin Zilong Su Yansen Chen Huiling Guo Ran Sergey Gataullin Cyberspace Institute Advanced Technology Guangzhou UniversityGuangzhou 510006China College of Information Engineering Yangzhou UniversityYangzhou 225127China School Math&Computer Science Quanzhou Normal UniversityQuanzhou 362000China Computer Science Department City University of Hong KongHong Kong 999077China School of Computer and Software Nanjing University of Information Science and TechnologyNanjing 21004China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and TechnologyAnhui UniversityHefei 230601China Department of Computer Science and Artificial Intelligence Wenzhou UniversityWenzhou 325035China Guangzhou University Library Guangzhou UniversityGuangzhou 510006China Central Economic and Mathematics Institute Russian Academy of Sciences MIREA-Russian Technological University Moscow RegionRussia

With the rapid development of information technology,IoT devices play a huge role in physiological health data *** exponential growth of medical data requires us to reasonably allocate storage space for cloud servers and edge *** storage capacity of edge nodes close to users is *** should store hotspot data in edge nodes as much as possible,so as to ensure response timeliness and access hit rate;However,the current scheme cannot guarantee that every sub-message in a complete data stored by the edge node meets the requirements of hot data;How to complete the detection and deletion of redundant data in edge nodes under the premise of protecting user privacy and data dynamic integrity has become a challenging *** paper proposes a redundant data detection method that meets the privacy protection *** scanning the cipher text,it is determined whether each sub-message of the data in the edge node meets the requirements of the hot *** has the same effect as zero-knowledge proof,and it will not reveal the privacy of *** addition,for redundant sub-data that does not meet the requirements of hot data,our paper proposes a redundant data deletion scheme that meets the dynamic integrity of the *** use Content Extraction Signature(CES)to generate the remaining hot data signature after the redundant data is *** feasibility of the scheme is proved through safety analysis and efficiency analysis.

关键词： blockchain data integrity edge computing privacy protection redundant data

Wavelet-Driven Masked Image Modeling: A Path to Efficient Visual Representation 39

学校读者我要写书评

暂无评论

Wavelet-Driven Masked Image Modeling: A Path to Efficient Vi...

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Xiang, Wenzhao Liu, Chang Yu, Hongyang Chen, Xilin Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China Peng Cheng Laboratory China University of Chinese Academy of Sciences China Department of Electronic Engineering Shanghai Jiao Tong University China

ISBN: (纸本)157735897X

Masked Image Modeling (MIM) has garnered significant attention in self-supervised learning, thanks to its impressive capacity to learn scalable visual representations tailored for downstream tasks. However, images inherently contain abundant redundant information, leading the pixel-based MIM reconstruction process to focus excessively on finer details such as textures, thus prolonging training times unnecessarily. Addressing this challenge requires a shift towards a compact representation of features during MIM reconstruction. Frequency domain analysis provides a promising avenue for achieving compact image feature representation. In contrast to the commonly used Fourier transform, wavelet transform not only offers frequency information but also preserves spatial characteristics and multi-level features of the image. Additionally, the multi-level decomposition process of wavelet transformation aligns well with the hierarchical architecture of modern neural networks. In this study, we leverage wavelet transform as a tool for efficient representation learning to expedite the training process of MIM. Specifically, we conduct multi-level decomposition of images using wavelet transform, utilizing wavelet coefficients from different levels to construct distinct reconstruction targets representing various frequencies and scales. These reconstruction targets are then integrated into the MIM process, with adjustable weights assigned to prioritize the most crucial information. Extensive experiments demonstrate that our method achieves comparable or superior performance across various downstream tasks while exhibiting higher training efficiency. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Wavelet decomposition

Wavelet-Driven Masked Image Modeling: A Path to Efficient Visual Representation

学校读者我要写书评

暂无评论

arXiv 2025年

关键词： Frequency domain analysis

R-calculus for post three-valued description logic 7

学校读者我要写书评

暂无评论

R-calculus for post three-valued description logic

7th International Conference on Fuzzy Systems and Data Mining, FSDM 2021

作者： Cao, Cungen Hu, Lanxi Sui, Yuefei Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China School of Computer Science and Technology University of Chinese Academy of Sciences China

ISBN: (纸本)9781643682143

R-calculus is a belief revision operator satisfying AGM postulates, and belief revision in ontology engineering is ontology revision, which based logic is description logics. In Post three-valued description logic, a tableau proof system Tt will be given such that Tt is sound and complete for t-satisfiability, and nonmonotonic, that is, a theory Δis t-satisfiable if and only if Δis deducible in Tt. Based on the tableau proof system, an R-calculus Rt will be given such that a configuration Î"|C(a) is reducible to C(a),Δif and only if C(a) is t-satisfiable with Î", if and only if reduction Î"|C(a) â‡' C(a),Δis deducible in Rt. © 2021 The authors and IOS Press.

关键词： Ontology

Static for Dynamic: Towards a Deeper Understanding of Dynamic Facial Expressions Using Static Expression Data

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen, Yin Li, Jia Zhang, Yu Hu, Zhenzhen Shan, Shiguang Wang, Meng Hong, Richang School of Computer Science and Information Engineering Hefei University of Technology Hefei230601 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

Dynamic facial expression recognition (DFER) infers emotions from the temporal evolution of expressions, unlike static facial expression recognition (SFER), which relies solely on a single snapshot. This temporal analysis provides richer information and promises greater recognition capability. However, current DFER methods often exhibit unsatisfied performance largely due to fewer training samples compared to SFER. Given the inherent correlation between static and dynamic expressions, we hypothesize that leveraging the abundant SFER data can enhance DFER. To this end, we propose Static-for-Dynamic (S4D), a unified dual-modal learning framework that integrates SFER data as a complementary resource for DFER. Specifically, S4D employs dual-modal self-supervised pre-training on facial images and videos using a shared Vision Transformer (ViT) encoder-decoder architecture, yielding improved spatiotemporal representations. The pre-trained encoder is then fine-tuned on static and dynamic expression datasets in a multi-task learning setup to facilitate emotional information interaction. Unfortunately, vanilla multitask learning in our study results in negative transfer. To address this, we propose an innovative Mixture of Adapter Experts (MoAE) module that facilitates task-specific knowledge acquisition while effectively extracting shared knowledge from both static and dynamic expression data. Extensive experiments demonstrate that S4D achieves a deeper understanding of DFER, setting new state-of-the-art performance on FERV39K, MAFW, and DFEW benchmarks, with weighted average recall (WAR) of 53.65%, 58.44%, and 76.68%, respectively. Additionally, a systematic correlation analysis between SFER and DFER tasks is presented, which further elucidates the potential benefits of leveraging SFER. Copyright © 2024, The Authors. All rights reserved.

关键词： Self-supervised learning

A Unified Generalization Analysis of Re-Weighting and Logit-Adjustment for Imbalanced Learning 37

学校读者我要写书评

暂无评论

A Unified Generalization Analysis of Re-Weighting and Logit-...

37th Conference on Neural information processing Systems, NeurIPS 2023

作者： Wang, Zitai Xu, Qianqian Yang, Zhiyong He, Yuan Cao, Xiaochun Huang, Qingming SKLOIS Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS China School of Computer Science and Tech. University of Chinese Academy of Sciences China Alibaba Group China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China BDKM University of Chinese Academy of Sciences China

ISBN: (纸本)9781713899921

Real-world datasets are typically imbalanced in the sense that only a few classes have numerous samples, while many classes are associated with only a few samples. As a result, a naïve ERM learning process will be biased towards the majority classes, making it difficult to generalize to the minority classes. To address this issue, one simple but effective approach is to modify the loss function to emphasize the learning on minority classes, such as re-weighting the losses or adjusting the logits via class-dependent terms. However, existing generalization analysis of such losses is still coarse-grained and fragmented, failing to explain some empirical results. To bridge this gap, we propose a novel technique named data-dependent contraction to capture how these modified losses handle different classes. On top of this technique, a fine-grained generalization bound is established for imbalanced learning, which helps reveal the mystery of re-weighting and logit-adjustment in a unified manner. Furthermore, a principled learning algorithm is developed based on the theoretical insights. Finally, the empirical results on benchmark datasets not only validate the theoretical results but also demonstrate the effectiveness of the proposed method. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： Contrastive Learning

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wen, Zhuofan Gui, Shangtong Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences China Key Laboratory of Al Safety Chinese Academy of Sciences China University of Chinese Academy of Sciences Beijing China

Inference acceleration of large language models (LLMs) has been put forward in many application scenarios and speculative decoding has shown its advantage in addressing inference acceleration. Speculative decoding usually introduces a draft model to assist the base LLM where the draft model produces drafts and the base LLM verifies the draft for acceptance or rejection. In this framework, the final inference speed is decided by the decoding speed of the draft model and the acceptance rate of the draft provided by the draft model. Currently the widely used draft models usually generate draft tokens for the next several positions in a non-autoregressive way without considering the correlations between draft tokens. Therefore, it has a high decoding speed but an unsatisfactory acceptance rate. In this paper, we focus on how to improve the performance of the draft model and aim to accelerate inference via a high acceptance rate. To this end, we propose a CTC-based draft model which strengthens the correlations between draft tokens during the draft phase, thereby generating higher-quality draft candidate sequences. Experiment results show that compared to strong baselines, the proposed method can achieve a higher acceptance rate and hence a faster inference speed. Copyright © 2024, The Authors. All rights reserved.

关键词： Decoding