检索结果-内蒙古大学图书馆

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Yuan, Zhaoquan Peng, Xiao Wu, Xiao Bao, Bing-Kun Xu, Changsheng School of Computing and Artificial Intelligence Southwest Jiaotong University China Nanjing University of Posts and Telecommunications China National Lab of Pattern Recognition Institute of Automation Chinese Academy of Sciences China

ISBN: (纸本)9781665438643

Conventional predictive models in machine learning are based on I.I.D. hypothesis between training and testing data. However, such a hypothesis is fragile in the real world, and the model minimizing empirical errors on training data does not perform well on testing data, which makes the prediction unstable. This instability can be found widely in domain generalization, active learning, and transfer learning, etc. In this paper, we propose a novel Meta-learning Causal Feature Selection (MCFS) model for general Non-I.I.D. image classification. In MCFS, we jointly optimize a convolutional network and a causal parameter for identifying causal variables on meta-training and meta-testing data which simulate the distribution shifts in Non-I.I.D. problems. Extensive experiments conducted on public VLCS and NICO datasets demonstrate the effectiveness of the proposed MCFS, which outperforms the state-of-the-art methods. © 2021 IEEE

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

First Steps on Gamification of Lung Fluid Cells Annotations in the Flower Domain

First Steps on Gamification of Lung Fluid Cells Annotations ...

引用

German Workshop on Medical Image Computing, 2022

作者： Kunzmann, Sonja Marzahl, Christian Denzinger, Felix Bertram, Christof Klopfleisch, Robert Breininger, Katharina Christlein, Vincent Maier, Andreas Pattern Recognition Lab FAU Erlangen-Nürnberg Erlangen Germany Department Artificial Intelligence in Biomedical Engineering FAU Erlangen-Nürnberg Erlangen Germany Institute of Pathology University of Verterinary Medicine Vienna Austria Institute of Veterinary Pathology Freie Universität Berlin Berlin Germany

来源：评论

学校读者我要写书评

暂无评论

Multimodal Corpus Analysis of Autoblog 2020: Lecture Videos in Machine Learning 23rd

Multimodal Corpus Analysis of Autoblog 2020: Lecture Videos ...

引用

23rd International Conference on Speech and Computer, SPECOM 2021

作者： Hernandez, Abner Yang, Seung Hee Pattern Recognition Lab Friedrich Alexander University Erlangen-Nürnberg Erlangen Germany Department of Artificial Intelligence in Biomedical Engineering Friedrich Alexander University Erlangen-Nürnberg Erlangen Germany

ISBN: (纸本)9783030878016

This paper introduces a lecture video corpus, Autoblog 2020. With the increase of online learning in universities, there is a demand for a systematic toolchain development for lecture video processing. However, the existing lecture video corpus does not satisfy the requirement for such tasks, and lecture transcription and analyses are relatively unexplored areas in speech and natural language research. Autoblog 2020 Corpus is developed towards the end goal of free video-to-blog post conversion software that supports making video presentations more accessible. It will include automatic editing of disfluencies, automatic speech recognition (ASR), and spoken term extraction so that researchers can process and share their contents more efficiently. In this paper, we present a description of the corpus, linguistic analyses and preliminary experiment results regarding ASR, keyword extraction, and segmentation. The results will be used in future work to develop a video-to-blog post conversion. © 2021, Springer Nature Switzerland AG.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

TowardsWeakly Supervised Segmentation of Orthopaedic X-ray Images Using Constrained-CNN Losses

TowardsWeakly Supervised Segmentation of Orthopaedic X-ray I...

引用

German Workshop on Medical Image Computing, 2022

作者： Arbogast, Nikolaus Kunze, Holger Kordon, Florian Swartman, Benedict Barbari, Jan S. El Breininger, Katharina Department Artificial Intelligence in Biomedical Engineering FAU Erlangen-Nürnberg Erlangen Germany Siemens Healthineers AG Erlangen Germany Pattern Recognition Lab FAU Erlangen-Nürnberg Erlangen Germany FAU Erlangen-Nürnberg 5 Erlangen Germany BG Trauma Center Ludwigshafen Erlangen Germany

来源：评论

学校读者我要写书评

暂无评论

OSRT: Omnidirectional Image Super-Resolution with Distortion-aware Transformer

OSRT: Omnidirectional Image Super-Resolution with Distortion...

引用

Conference on Computer Vision and pattern recognition (CVPR)

作者： Fanghua Yu Xintao Wang Mingdeng Cao Gen Li Ying Shan Chao Dong ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences ARC Tencent PCG The University of Tokyo Platform Technologies Tencent Online Video Shanghai Artificial Intelligence Laboratory

Omnidirectional images (ODIs) have obtained lots of research interest for immersive experiences. Although ODIs require extremely high resolution to capture details of the entire scene, the resolutions of most ODIs are insufficient. Previous methods attempt to solve this issue by image super-resolution (SR) on equirectangular projection (ERP) images. However, they omit geometric properties of ERP in the degradation process, and their models can hardly generalize to real ERP images. In this paper, we propose Fisheye downsampling, which mimics the real-world imaging process and synthesizes more realistic low-resolution samples. Then we design a distortion-aware Transformer (OSRT) to modulate ERP distortions continuously and self-adaptively. Without a cumbersome process, OSRT outperforms previous methods by about 0.2dB on PSNR. Moreover, we propose a convenient data augmentation strategy, which synthesizes pseudo ERP images from plain images. This simple strategy can alleviate the over-fitting problem of large networks and significantly boost the performance of ODISR. Extensive experiments have demonstrated the state-of-the-art performance of our OSRT.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Activating More Pixels in Image Super-Resolution Transformer

Activating More Pixels in Image Super-Resolution Transformer

引用

Conference on Computer Vision and pattern recognition (CVPR)

作者： Xiangyu Chen Xintao Wang Jiantao Zhou Yu Qiao Chao Dong State Key Laboratory of Internet of Things for Smart City University of Macau Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shanghai Artificial Intelligence Laboratory ARC Lab Tencent PCG

Transformer-based methods have shown impressive performance in low-level vision tasks, such as image super-resolution. However, we find that these networks can only utilize a limited spatial range of input information through attribution analysis. This implies that the potential of Transformer is still not fully exploited in existing networks. In order to activate more input pixels for better reconstruction, we propose a novel Hybrid Attention Transformer (HAT). It combines both channel attention and window-based self-attention schemes, thus making use of their complementary advantages of being able to utilize global statistics and strong local fitting capability. Moreover, to better aggregate the cross-window information, we introduce an overlapping cross-attention module to enhance the interaction between neighboring window features. In the training stage, we additionally adopt a same-task pre-training strategy to exploit the potential of the model for further improvement. Extensive experiments show the effectiveness of the proposed modules, and we further scale up the model to demonstrate that the performance of this task can be greatly improved. Our overall method significantly outperforms the state-of-the-art methods by more than 1dB.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Three-dimensional ATUM-SEM reconstruction and analysis of hepatic endoplasmic reticulum-organelle interactions

引用

Journal of Molecular Cell Biology 2021年第9期13卷 636-645页

作者： Yi Jiang Linlin Li Xi Chen Jiazheng Liu Jingbin Yuan Qiwei Xie Hua Han National Laboratory of Pattern Recognition Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 101408China School of Future Technology University of Chinese Academy of SciencesBeijing 101408China Data Mining Lab Beijing University of TechnologyBeijing 100124China CAS Center for Excellence in Brain Science and Intelligence Technology Shanghai 200031China

The endoplasmic reticulum(ER)is a contiguous and complicated membrane network in eukaryotic cells,and membrane contact sites(MCSs)between the ER and other organelles perform vital cellular functions,including lipid homeostasis,metabolite exchange,calcium level regulation,and organelle ***,we establish a whole pipeline to reconstruct all ER,mitochondria,lipid droplets,lysosomes,peroxisomes,and nuclei by automated tape-collecting ultramicrotome scanning electron microscopy and deep learning techniques,which generates an unprecedented 3D model for mapping liver ***,the morphology of various organelles and the MCSs between the ER and other organelles are systematically *** found that the ER presents with predominantly flat cisternae and is knitted tightly all throughout the intracellular space and around other *** addition,the ER has a smaller volume-to-membrane surface area ratio than other organelles,which suggests that the ER could be more suited for functions that require a large membrane surface *** data also indicate that ER-mitochondria contacts are particularly abundant,especially for branched *** study provides 3D reconstructions of various organelles in liver samples together with important fundamental information for biochemical and functional studies in the liver.

关键词： 3D reconstruction ATUM-SEM deep learning liver ER MCSs

来源：评论

学校读者我要写书评

暂无评论

LVAgent: Long Video Understanding by Multi-Round Dynamical Collaboration of MLLM Agents

arXiv

引用

arXiv 2025年

作者： Chen, Boyu Yue, Zhengrong Chen, Siran Wang, Zikang Liu, Yang Li, Peng Wang, Yali Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Tsinghua University Beijing China Dept. of Comp. Sci. & Tech. Institute for AI Tsinghua University Beijing China Shanghai Artificial Intelligence Laboratory China Shanghai Jiao Tong University China

Existing Multimodal Large Language Models (MLLMs) encounter significant challenges in modeling the temporal context within long videos. Currently, mainstream Agent-based methods use external tools (e.g., search engine, memory banks, OCR, retrieval models) to assist a single MLLM in answering long video questions. Despite such tool-based support, a solitary MLLM still offers only a partial understanding of long videos, resulting in limited performance. In order to better address long video tasks, we introduce LVAgent, the first framework enabling multi-round dynamic collaboration of MLLM agents in long video understanding. Our methodology consists of four key steps: 1) Selection: We pre-select appropriate agents from the model library to form optimal agent teams based on different tasks. 2) Perception: We design an effective retrieval scheme for long videos, improving the coverage of critical temporal segments while maintaining computational efficiency. 3) Action: Agents answer long video-related questions and exchange reasons. 4) Reflection: We evaluate each agent’s performance in each round of discussion and optimize the agent team for dynamic collaboration. The agents iteratively refine their answers by multi-round dynamical collaboration of MLLM agents. LVAgent is the first agent system method that outperforms all closed-source models (including GPT-4o) and open-source models (including InternVL-2.5 and Qwen2-VL) in the long video understanding tasks. Our LVAgent achieves an accuracy of 80% on four mainstream long video understanding tasks. Notably, on the LongVideoBench dataset, LVAgent improves accuracy by up to 13.3% compared with SOTA. © 2025, CC BY-NC-SA.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

Towards End-to-End Speech Articulation and Spoken Language Analysis Using Deep Learning

引用

Human-Centric Intelligent Systems 2025年第1期5卷 103-122页

作者： Weise, Tobias Demir, Kubilay Can Pérez-Toro, Paula Andrea Arias-Vergara, Tomas Maier, Andreas Nöth, Elmar Schuster, Maria Heismann, Björn Yang, Seung Hee Artificial Intelligence in Biomedical Engineering Department Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany Pattern Recognition Laboratory Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany GITA Lab Faculty of Engineering Universidad de Antioquia Medellín Colombia Department of Otorhinolaryngology Head and Neck Surgery Ludwig-Maximilians University Munich Germany

This study presents a speech and spoken language analysis framework, leveraging a robust, end-to-end deep learning model developed in our prior work. The framework represents a foundational step towards a comprehensive solution for analyzing speech articulation and spoken language. Unlike traditional approaches that rely on separate specialized models, our architecture integrates multiple prediction tasks into a single multi-task learning setup: nine articulatory trajectories, a phoneme sequence, and phoneme alignment. While conceptually distinct, these outputs share a strong underlying relation: phonemes, as the fundamental building blocks of language, emerge from specific articulatory configurations, and phoneme alignment provides crucial temporal structure. We bridge the gap between abstract linguistic representations and their physical realizations by integrating phoneme recognition, articulatory trajectory prediction, and phoneme alignment within a single deep learning framework. Phonemes, as abstract speech units, manifest as concrete articulatory gestures, which can be precisely captured through EMA and analyzed using deep learning methods. This integration lays the foundation for diverse applications, including intelligibility assessment and therapeutic feedback. Extensive experiments validate the model’s capabilities and demonstrate its potential in real-world contexts. These include evaluations of articulatory and phoneme-related metrics, intelligibility estimation using phoneme error rates, and open vocabulary keyword spotting. A case study on stroke-related datasets highlights how the framework provides detailed articulatory feedback and supports therapy progress tracking. While not a complete solution, this work shows that an integrated, end-to-end deep learning approach can effectively address multiple facets of speech analysis. Ultimately, it serves as a foundation for developing scalable and robust frameworks to tackle challenges in speech and langua

关键词：

来源：评论

学校读者我要写书评

暂无评论

Developmental Trajectory of Cerebral Lateralization 23

Developmental Trajectory of Cerebral Lateralization

引用

15th International Conference on Bioinformatics and Biomedical Technology, ICBBT 2023

作者： Li, Wen Shi, Weiyang Jiang, Tianzi Brainnetome Center and National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China CAS Center for Excellence in Brain Science and Intelligence Technology Institute of Automation Chinese Academy of Sciences Beijing100190 China The Clinical Hospital of Chengdu Brain Science Institute MOE Key Lab for Neuroinformation University of Electronic Science and Technology of China Chengdu625014 China The Queensland Brain Institute University of Queensland BrisbaneQLD4072 Australia

ISBN: (纸本)9798400700385

The pattern of lateralization in the developing brain partly reveals the maturation of the brain and provides a reliable reference for researchers to assess whether the brain is developing normally. Functions associated with distinct patterns of brain lateralization related to functions such as language and visuospatial ability have attracted the attention of researchers for a long time, while the trajectories of developmental lateralization patterns in various brain regions across the brain is still poorly understood. In this study, we divided the resting-state functional magnetic resonance imaging (rs-fMRI) data of subjects aged 8-21 years from Lifespan Human Connectome Project Development (HCP-D) into different groups according to their age and used the support vector machine (SVM) to investigate the distinguishability of the lateralization patterns in different age groups by classification accuracy. We found that the changing rate of lateralization patterns slows down with age and the onset age of maturation of lateralization patterns varies across brain regions. © 2023 Owner/Author.

关键词： Support vector machines

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：