检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhang, Dingwen Li, Hao He, Diqi Liu, Nian Cheng, Lechao Wang, Jingdong Han, Junwei The Brain and Artificial Intelligence Lab. Northwestern Polytechnical University Shaanxi Xi’an710000 China The Inception Institute of Artificial Intelligence United Kingdom The School of Computer Science and Information Engineering Hefei University of Technology Hefei230601 China Department of Computer Vision Baidu Inc. China

In recent times, following the paradigm of DETR (DEtection TRansformer), query-based end-to-end instance segmentation (QEIS) methods have exhibited superior performance compared to CNN-based models, particularly when trained on large-scale datasets. Nevertheless, the effectiveness of these QEIS methods diminishes significantly when confronted with limited training data. This limitation arises from their reliance on substantial data volumes to effectively train the pivotal queries/kernels that are essential for acquiring localization and shape priors. To address this problem, we propose a novel method for unsupervised pre-training in low-data regimes. Inspired by the recently successful prompting technique, we introduce a new method, Unsupervised Pre-training with Language-vision Prompts (UPLVP), which improves QEIS models’ instance segmentation by bringing language-vision prompts to queries/kernels. Our method consists of three parts: (1) Masks Proposal: Utilizes language-vision models to generate pseudo masks based on unlabeled images. (2) Prompt-Kernel Matching: Converts pseudo masks into prompts and injects the best-matched localization and shape features to their corresponding kernels. (3) Kernel Supervision: Formulates supervision for pre-training at the kernel level to ensure robust learning. With the help of our pre-training method, QEIS models can converge faster and perform better than CNN-based models in low-data regimes. Experimental evaluations conducted on MS COCO, Cityscapes, and CTW1500 datasets indicate that the QEIS models’ performance can be significantly improved when pre-trained with our method. Code will be available at: https://***/lifuguan/UPLVP. Copyright © 2024, The Authors. All rights reserved.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Causal Discovery via Conditional Independence Testing with Proxy Variables 41

Causal Discovery via Conditional Independence Testing with P...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Liu, Mingzhou Sun, Xinwei Qiao, Yu Wang, Yizhou School of Computer Science Peking University China Peking University China Sch. of Data Science Fudan University China Dep. of Automation Shanghai Jiao Tong University China Inst. for Artificial Intelligence Peking University China Nat'l Eng. Research Center of Visual Technology Peking University China Nat'l Key Lab of General Artificial Intelligence Peking University China

Distinguishing causal connections from correlations is important in many scenarios. However, the presence of unobserved variables, such as the latent confounder, can introduce bias in conditional independence testing commonly employed in constraint-based causal discovery for identifying causal relations. To address this issue, existing methods introduced proxy variables to adjust for the bias caused by unobserveness. However, these methods were either limited to categorical variables or relied on strong parametric assumptions for identification. In this paper, we propose a novel hypothesis-testing procedure that can effectively examine the existence of the causal relationship over continuous variables, without any parametric constraint. Our procedure is based on discretization, which under completeness conditions, is able to asymptotically establish a linear equation whose coefficient vector is identifiable under the causal null hypothesis. Based on this, we introduce our test statistic and demonstrate its asymptotic level and power. We validate the effectiveness of our procedure using both synthetic and real-world data. Code is publicly available at https://***/lmz123321/proxy_causal_discovery. Copyright 2024 by the author(s)

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analyzing Pulmonary Abnormality with Superpixel Based Graph Neural Network in Chest X-Ray 6th

Analyzing Pulmonary Abnormality with Superpixel Based Graph...

引用

6th International Conference on Recent Trends in Image Processing and Pattern Recognition, RTIP2R 2023

作者： Pradhan, Ronaj Santosh, Kc Applied Artificial Intelligence Research Lab Department of Computer Science University of South Dakota VermillionSD57069 United States

ISBN: (纸本)9783031530845

In recent years, the utilization of graph-based deep learning has gained prominence, yet its potential in the realm of medical diagnosis remains relatively unexplored. The challenge arises from the inherent irregular and unordered nature of physiological data, making it challenging to depict intricate patterns using conventional methods. Our research focuses on abnormality screening: classification of Chest X-Ray (CXR) as Tuberculosis positive or negative, using Graph Neural Networks (GNN) that uses Region Adjacency Graphs (RAGs) and each superpixel serves as a dedicated graph node. By integrating residual and concatenation structures, our approach effectively captures crucial features and relationships among superpixels, facilitating advancements in tuberculosis identification. Through the amalgamation of state-of-the-art neural network architectures and innovative graph-based representations, our work introduces a new perspective to medical image analysis. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Effects on Hand Gesture Recognition Accuracy after Severe Cranial Trauma

Effects on Hand Gesture Recognition Accuracy after Severe Cr...

引用

IEEE Ecuador Technical Chapters Meeting (ETCM)

作者： Jonathan A. Zea Luis Gabriel Macias Santillán Lorena Isabel Barona López Ángel Leonardo Valdivieso Caraguay Marco E. Benalcázar Departamento de Informática y Ciencias de la Computación Escuela Politécnica Nacional Artificial Intelligence and Computer Vision Research Lab Quito Ecuador

This study examines the impact of severe cranial trauma on the accuracy of Hand Gesture Recognition (HGR) models based on electromyography (EMG) signals. The study focuses on a single subject, who suffered left-sided hemiplegia, and exhibits limited mobility and spasticity in the left hand. EMG samples corresponding to six hand gestures from his both forearms were collected using the Myo Armband. The 2023HGR5-CNN-LSTM HGR model was used to evaluate the recognition accuracy of these samples. Results showed significantly lower HGR performance in the left side (10.67% recognition accuracy) compared to the right side (56% recognition accuracy). As the selected model was trained with EMG data only from right arms, a channel mapping to adapt the EMG signals from the left side was also developed. Unfortunately, the channel mapping implemented did not improve the recognition accuracy (9.33%). These findings highlight the challenges in achieving high performance HGR for individuals with cranial injuries. It might also point out that developing myoelectric prostheses using datasets from unaffected individuals may be inadequate for training robust models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MTVCrafter: 4D Motion Tokenization for Open-World Human Image Animation

arXiv

引用

arXiv 2025年

作者： Ding, Yanbo Hu, Xirui Guo, Zhizhi Wang, Yali Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China China Telecom China School of Computer Science and Technology Xi’an Jiaotong University China School of Artificial Intelligence University of Chinese Academy of Sciences China Shanghai Artificial Intelligence Laboratory China

Human image animation has gained increasing attention and developed rapidly due to its broad applications in digital humans. However, existing methods rely largely on 2D-rendered pose images for motion guidance, which limits generalization and discards essential 3D information for open-world animation. To tackle this problem, we propose MTVCrafter (Motion Tokenization Video Crafter), the first framework that directly models raw 3D motion sequences (i.e., 4D motion) for human image animation. Specifically, we introduce 4DMoT (4D motion tokenizer) to quantize 3D motion sequences into 4D motion tokens. Compared to 2D-rendered pose images, 4D motion tokens offer more robust spatio-temporal cues and avoid strict pixel-level alignment between pose image and character, enabling more flexible and disentangled control. Then, we introduce MV-DiT (Motion-aware Video DiT). By designing unique motion attention with 4D positional encodings, MV-DiT can effectively leverage motion tokens as 4D compact yet expressive context for human image animation in the complex 3D world. Hence, it marks a significant step forward in this field and opens a new direction for pose-guided human video generation. Experiments show that our MTVCrafter achieves state-of-the-art results with an FID-VID of 6.98, surpassing the second-best by 65%. Powered by robust motion tokens, MTVCrafter also generalizes well to diverse open-world characters (single/multiple, full/half-body) across various styles and scenarios. Our video demos and code are on: https://***/DINGYANB/MTVCrafter. Copyright © 2025, The Authors. All rights reserved.

关键词： Three dimensional computer graphics

来源：评论

学校读者我要写书评

暂无评论

A Multimodal Spatio-temporal Model for Micro-Video Emotion Classification 24

A Multimodal Spatio-temporal Model for Micro-Video Emotion C...

引用

24th IEEE International Conference on Mobile Data Management, MDM 2023

作者： Xue, Junxiao Wang, Jie Zheng, Yuanxun Wang, Ke Zhengzhou University School of Cyber Science and Engineering Zhengzhou450002 China Research Institute of Artificial Intelligence Zhejiang Lab Hangzhou311121 China Zhengzhou University Yellow River Laboratory Zhengzhou450001 China Zhengzhou University School of Water Conservancy Engineering Zhengzhou450001 China Zhengzhou University School of Computer and Artificial Intelligence Zhengzhou450001 China

ISBN: (纸本)9798350341010

Spatio-temporal features are information unique to video compared to images, and are an important source of features for video content analysis. The introduction of spatio-temporal features has brought a significant change to affective computing, which is no longer limited to single-image and ignores temporal affective changes. However, existing affective computing models still do not introduce spatio-temporal features. For example, facial emotion classification still uses single-image as input to the model and ignores spatio-temporal features. Therefore, we propose a novel neural network that takes video as the input of the model and extracts feature information containing spatio-temporal features in it. The extracted feature information consists of two modalities, which are audio spatio-temporal feature information and image spatio-temporal feature information. Decision-level fusion of the two modal information is performed to achieve emotion classification. Where a feature extractor based on VGG implementation is used as the audio emotion feature extraction module, which extracts the spectrogram feature information while focusing on its temporal feature information. And using the feature extractor implemented based on I3D as the image emotion feature extraction module, which consists of 3D convolutional blocks. Compared with 2D convolutional blocks, it not only focuses on image features, but also performs convolutional extraction for both spatial features and temporal features of the images within the blocks to obtain image features containing spatio-temporal features. By fusing multiple spatio-temporal feature classifiers in the best way, our model achieves an accuracy of 62.41%. The experimental results show that feature information containing spatio-temporal features is more effective in sentiment classifiers than feature information containing only image features. © 2023 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

CNNRF-Ensemble: A Multifaced Approach For Predicting White Spot Syndrome Virus In Shrimp Farming 4

CNNRF-Ensemble: A Multifaced Approach For Predicting White S...

引用

4th International Conference on Robotics, Electrical and Signal Processing Techniques, ICREST 2025

作者： Tanvir, Kazi Al Huda, Sadi Opee, Shaiful Ajam Kabir, Sayem Ali, Asraf Bhuiyan, Touhid School of Advanced Sciences Vellore Institute of Technology Department of Mathematics Tamil Nadu Vellore India Department of Computer Science Dhaka Bangladesh Artificial Intelligence Research and Innovation Lab Dhaka Bangladesh School of Information Technology Washington University of Science and Technology AlexandriaVA22314 United States

ISBN: (纸本)9798331530938

Shrimp farming has traditionally served as a crucial source of seafood and revenue for coastal countries, filling the rapid growth demand, especially in Bangladesh. However, the White Spot Syndrome Virus(WSSV) creates and constantly threatens the global shrimp population, impacting the economic and ecological systems. Recently, researchers have tried to predict disease, but no studies have achieved significant accuracy using ML and DL algorithms. In this study, we have proposed an optimized CNNRF-Ensemble model for predicting WSSV using multifaceted data, including geographical features, environmental attributes, farm characteristics, operational practices, and socioeconomic indicators. Our proposed model achieved 95.714% accuracy in sequential model and afterwards, combining with RandomForestClassifier in Ensemble learning we obtained 99.99% accuracy. Our study suggested deep learning as an accurate, easy and low-cost method to predict shrimp WSSV, which helps to predict viruses and create awareness of shrimp firming. © 2025 IEEE.

关键词： Shellfish

来源：评论

学校读者我要写书评

暂无评论

MUSES: 3D-Controllable Image Generation via Multi-Modal Agent Collaboration

arXiv

引用

arXiv 2024年

作者： Ding, Yanbo Zhuang, Shaobin Li, Kunchang Yue, Zhengrong Qiao, Yu Wang, Yali Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Shanghai Artificial Intelligence Laboratory China Shanghai Jiao Tong University China

Despite recent advancements in text-to-image generation, most existing methods struggle to create images with multiple objects and complex spatial relationships in the 3D world. To tackle this limitation, we introduce a generic AI system, namely MUSES, for 3D-controllable image generation from user queries. Specifically, our MUSES develops a progressive workflow with three key components, including (1) Layout Manager for 2D-to-3D layout lifting, (2) Model Engineer for 3D object acquisition and calibration, (3) Image Artist for 3D-to-2D image rendering. By mimicking the collaboration of human professionals, this multi-modal agent pipeline facilitates the effective and automatic creation of images with 3D-controllable objects, through an explainable integration of top-down planning and bottom-up generation. Additionally, existing benchmarks lack detailed descriptions of complex Copyright © 2024, The Authors. All rights reserved.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

Neural Transformation Fields for Arbitrary-Styled Font Generation

Neural Transformation Fields for Arbitrary-Styled Font Gener...

引用

Conference on computer vision and Pattern Recognition (CVPR)

作者： Bin Fu Junjun He Jianjun Wang Yu Qiao ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shanghai Artificial Intelligence Laboratory

Few-shot font generation (FFG), aiming at generating font images with a few samples, is an emerging topic in recent years due to the academic and commercial values. Typically, the FFG approaches follow the style-content disentanglement paradigm, which transfers the target font styles to characters by combining the content representations of source characters and the style codes of reference samples. Most existing methods attempt to increase font generation ability via exploring powerful style representations, which may be a sub-optimal solution for the FFG task due to the lack of modeling spatial transformation in transferring font styles. In this paper, we model font generation as a continuous transformation process from the source character image to the target font image via the creation and dissipation of font pixels, and embed the corresponding transformations into a neural transformation field. With the estimated transformation path, the neural transformation field generates a set of intermediate transformation results via the sampling process, and a font rendering formula is developed to accumulate them into the target font image. Extensive experiments show that our method achieves state-of-the-art performance on few-shot font generation task, which demonstrates the effectiveness of our proposed model. Our implementation is available at: https://***/fubinfb/NTF.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Linear Projections of Teacher Embeddings for Few-Class Distillation

arXiv

引用

arXiv 2024年

作者： Loo, Noel Iliopoulos, Fotis Hu, Wei Vee, Erik MIT Computer Science Artificial Intelligence Lab United States Google Research United States University of Michigan Department of Computer Science and Engineering United States

Knowledge Distillation (KD) has emerged as a promising approach for transferring knowledge from a larger, more complex teacher model to a smaller student model. Traditionally, KD involves training the student to mimic the teacher's output probabilities, while more advanced techniques have explored guiding the student to adopt the teacher's internal representations. Despite its widespread success, the performance of KD in binary classification and few-class problems has been less satisfactory. This is because the information about the teacher model's generalization patterns scales directly with the number of classes. Moreover, several sophisticated distillation methods may not be universally applicable or effective for data types beyond computer vision. Consequently, effective distillation techniques remain elusive for a range of key real-world applications, such as sentiment analysis, search query understanding, and advertisement-query relevance assessment. Taking these observations into account, we introduce a novel method for distilling knowledge from the teacher model's representations, which we term Learning Embedding Linear Projections (LELP). Inspired by recent findings about the structure of final-layer representations, LELP works by identifying informative linear subspaces in the teacher's embedding space, and splitting them into pseudo-subclasses. The student model is then trained to replicate these pseudo-subclasses. Our experimental evaluations on large-scale NLP benchmarks like Amazon Reviews and Sentiment140 demonstrate that LELP is consistently competitive with, and typically superior to, existing state-of-the-art distillation algorithms for binary and few-class problems, where most KD methods suffer. Copyright © 2024, The Authors. All rights reserved.

关键词： Embeddings

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：