检索结果-内蒙古大学图书馆

Proceedings of the 37th International Conference on Neural information Processing Systems

作者： Ziyi Bai Ruiping Wang Xilin Chen Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China and University of Chinese Academy of Sciences Beijing China

Video Question Answering (VideoQA) has emerged as a vital tool to evaluate agents' ability to understand human daily behaviors. Despite the recent success of large vision language models in many multi-modal tasks, complex situation reasoning over videos involving multiple human-object interaction events still remains challenging. In contrast, humans can easily tackle it by using a series of episode memories as anchors to quickly locate question-related key moments for reasoning. To mimic this effective reasoning strategy, we propose the Glance-Focus model. One simple way is to apply an action detection model to predict a set of actions as key memories. However, these actions within a closed set vocabulary are hard to generalize to various video domains. Instead of that, we train an Encoder-Decoder to generate a set of dynamic event memories at the glancing stage. Apart from using supervised bipartite matching to obtain the event memories, we further design an unsupervised memory generation method to get rid of dependence on event annotations. Next, at the focusing stage, these event memories act as a bridge to establish the correlation between the questions with high-level event concepts and low-level lengthy video content. Given the question, the model first focuses on the generated key event memory, then focuses on the most relevant moment for reasoning through our designed multi-level cross-attention mechanism. We conduct extensive experiments on four Multi-Event VideoQA benchmarks including STAR, EgoTaskQA, AGQA, and NExT-QA. Our proposed model achieves state-of-the-art results, surpassing current large models in various challenging reasoning tasks. The code and models are available at https://***/ByZ0e/Glance-Focus.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Multiscale Dynamic Temporal Convolution Network For Continuous Dimensional Emotion Recognition

A Multiscale Dynamic Temporal Convolution Network For Contin...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Min Hu Jialu Sun Xiaohua Wang Ning An Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine School of Computer Science and Information Hefei University of Technology Hefei China School of Computer Science and Information Engineering Hefei University of Technology Hefei China

Video-based dimensional emotion recognition, especially long sequence modeling, is a challenging task. This paper proposes a Multiscale Dynamic Temporal Convolution Network(MDTCN) for long sequence modeling of dimensional emotion recognition. Although Temporal Convolution Network(TCN) has performed well in sequence modeling, there are still some limitations that the feature scale of each layer is single and the receptive field of the upper layer is too large to capture the short-term dependence. Therefore, Dynamic Dilated Block(DDB) is constructed to better capture the temporal dependence by using dilated convolutions of different kernel size. In order to obtain both long-term and short-term temporal features, Multiscale TCN Structure is proposed. Extensive experiments are conducted on the AFFWILD2 and SEWA Dataset and the competitive result is shown compared to state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Integrated Bifunctional Pressure‒Temperature Sensing System Fabricated on a Breathable Nanofiber and Powered by Rechargeable Zinc–Air Battery for Long‑Term Comfortable Health Care Monitoring

引用

Advanced Fiber Materials 2024年第4期6卷 1037-1052页

作者： Peng Wang Gengsheng Liu Guifen Sun Chuizhou Meng Guozhen Shen Yang Li School of Mechanical Engineering University of JinanJinan 250022China State Key Laboratory for Reliability and Intelligence of Electrical Equipment Engineering Research Center of Ministry of Education for Intelligent Rehabilitation Device and Detection TechnologyHebei Key Laboratory of Smart Sensing and Human‑Robot InteractionSchool of Mechanical EngineeringHebei University of TechnologyTianjin 300401China School of Integrated Circuits and Electronics Beijing Institute of TechnologyBeijing 100081China Shandong Provincial Key Laboratory of Network Based Intelligent Computing School of Information Science and EngineeringUniversity of JinanJinan 250022China School of Microelectronics Shandong UniversityJinan 250101China

Bulky external power supplies largely limit the continuous long-term application and miniaturization development of smart sensing ***,we fabricate a flexible and wearable integrated sensing system on an electrospun all-nanofiber *** three parts of the sensing system are all obtained by a facile ink-based direct writing *** resistive pressure sensor is realized by decorating MXene sheets on TPU ***,the resistive temperature sensor is prepared by compositing MXene sheets into poly(3,4-ethylenedioxythiophene):poly(styrene sulfonate)(PEDOT:PSS).The thin-film zinc–air battery(ZAB)includes an interdigital zinc–air electrode that is bonded with a gel polymer *** can supply a high open-circuit voltage of 1.39 V and a large areal capacity of 18.2 mAh cm^(-2) for stable and reliable power-supplying sensing parts *** to the hydrophobic nature of TPU and open-ended micropores in the TPU nanofiber,the sensing system is waterproof,self-cleaning,and air and moisture *** application,the above-mentioned functional components are seamlessly integrated into an intelligent electronic wristband,which is comfortably worn on a human wrist to monitor pulse and body temperature in real time with continuous operation of up to 4 *** the novel design and remarkable performance,the proposed integrated all-nanofiber sensing system presents a promising solution for developing advanced multifunctional wearable electronics.

关键词： Pressure‒temperature sensor Rechargeable zinc–air battery Electrospun nanofibers Permeable electronic Integrated sensing system

来源：评论

学校读者我要写书评

暂无评论

Facial Expression Recognition With Vision Transformer Using Fused Shifted Windows

引用

IEEE Transactions on Affective computing 2024年

作者： Sun, Xiao Wang, Rui Chen, Shaokai Wang, Meng Hefei University of Technology Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machines School of Computer Science and Information Engineering China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China University of Science and Technology of China Institute of Advanced Technology China Hefei University of Technology School of Computer Science and Information Engineering Hefei China

Facial expressions contain massive affective information. Previous methods have focused on using diverse models based on CNN or Transformer to handle the facial expression recognition(FER) task. However, most of them treat the FER task as a general image classification task and neglect the impact of regions of interest (ROIs) for the performance of FER. To verify the influence of different ROIs, in this paper, we propose a vision Transformer based on Fused Shifted windows (FSwin), called FSwin Transformer. The semantic information of the face, obtained by ROIs, guides the FSwin Transformer to focus more on the key regions. The fused shifted windows enable the model to perform global semantic interactions, allowing it to concentrate on key regions without losing the topological structural information of the entire face. Additionally, learnable parameters are introduced to learn the feature weights expressed by each ROI, helping the model dynamically adjust the attention distribution. We have conducted controlled experiments to quantitatively verify the impact of ROIs. And the experimental results show that with the increase of the number of ROIs, the accuracy of FER is significantly improved, demonstrating that the key ROIs play an important role in feature extraction. The results on Jaffe, CK+, FER2013, AffectNet have reached 99.8%, 99.0%, 74.8%, and 68.9%, respectively, which all set new state-of-the-art. Extensive cross-dataset experiments also show that the FSwin Transformer has good generalization ability, proving that our proposed model has a beneficial effect on FER tasks. © 2010-2012 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Temsa:Text Enhanced Modal Representation Learning for Multimodal Sentiment Analysis

SSRN

引用

SSRN 2025年

作者： Chen, Jingwen Song, Shuxiang Tan, Yumei Xia, Haiying The Key Lab of Education Blockchain and Intelligent Technology Ministry of Education China Guangxi Key Laboratory of Brain-inspired Computing and Intelligent Chips School of Electronic and Information Engineering Guangxi Normal University Guilin China Education Department of Guangxi Zhuang Autonomous Region Guilin China

Multimodal sentiment analysis aims to identify human emotions by leveraging multimodal information, including language, visual, and audio data. Different modalities contribute unequally to sentiment analysis, with text being more effective than non-linguistic modalities in multimodal sentiment analysis (MSA) due to its intuitive emotional expressiveness. A major challenge lies in leveraging the strengths of text to create fused representations that capture rich emotional content while preserving both inter-modal and intra-modal relationships. To address this challenge, we propose a Text-Enhanced Modal Representation Learning Model (TEMSA), which builds robust and unified multimodal representations through the design of text-guided pairwise cross-modal mapping modules. Specifically, TEMSA employs a text-guided multi-head cross-attention mechanism to embed linguistic information into the emotion-related representation learning of non-linguistic modalities, thereby enhancing the representations of visual and audio modalities. In addition to preserving consistent information through cross-modal mapping, TEMSA also incorporates text-guided reconstruction modules, which leverage text-enhanced non-linguistic modal features to decouple modality-specific representations from non-linguistic modalities. This dual representation learning framework captures inter-modal consistent information through cross-modal mapping, and extracts modal difference information through intra-modal decoupling, thus improving the understanding of cross-modal affective associations. The experimental results on the CMU-MOSI, CMU-MOSEI, and CH-SIMS datasets demonstrate that TEMSA achieves state-of-the-art performance, highlighting the critical role of text-guided cross-modal and intra-modal representation learning in multimodal sentiment analysis. © 2025, The Authors. All rights reserved.

关键词： Linguistics

来源：评论

学校读者我要写书评

暂无评论

PostoMETRO: Pose Token Enhanced Mesh Transformer for Robust 3D Human Mesh Recovery

PostoMETRO: Pose Token Enhanced Mesh Transformer for Robust ...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Wendi Yang Zihang Jiang Shang Zhao S. Kevin Zhou Division of Life Sciences and Medicine School of Biomedical Engineering University of Science and Technology of China (USTC) Hefei Anhui China Center for Medical Imaging Robotics Analytic Computing & Learning (MIRACLE) Suzhou Institute for Advance Research USTC Suzhou Jiangsu China Key Laboratory of Precision and Intelligent Chemistry USTC Hefei Anhui China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

With the recent advancements in single-image-based 3D human pose and shape estimation (3DHPSE), there is a growing amount of works that can achieve good results on standard benchmarks but struggle to yield accurate hu-man mesh in extreme scenarios like occlusion. Previous works propose to leverage 2D poses to help 3D HPSE model improve performance under occlusion, but usually rely on manual design to integrate 2D poses and only aim for specific kinds of occlusion. In this paper, we present PostoMETRO (Pose token enhanced MEsh TRansfOrmer), which integrates 2D pose prior knowledge as tokens into transformers to improve model's performance under occlusion. Using a VQ- VAE-based pose tokenizer; we efficiently represent 2D poses as tokens andfeed them to transformers together with image tokens. Subsequently, these tokens are queried by vertex andJoint tokens to decode 3D coordinates of mesh vertices and human Joints. Our proposed 2D poses integration strategy is manual-design-free and suitable for various kinds of occlusion. Experiments on both standard and occlusion-specific benchmarks demonstrate the effectiveness of PostoMETRO. Code will be made available 1 1 https://***/PostoMETRO/PostoMETRO-Paper.

关键词： Solid modeling Computer vision Three-dimensional displays Shape Estimation Manuals Benchmark testing Transformers Robustness Standards

来源：评论

学校读者我要写书评

暂无评论

An Encoder-Decoder Model Based On Spiking Neural Networks For Address Event Representation Object Recognition

引用

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Du, Sichun Zhu, Haodi Zhang, Yang Hong, Qinghui Hunan University College of Computer Science and Electronic Engineering Changsha418002 China Shenzhen University Computer Vision Institute School of Computer Science and Software Engineering National Engineering Laboratory for Big Data System Computing Technology Guangdong Key Laboratory of Intelligent Information Processing Shenzhen518060 China

Address event representation (AER) object recognition task has attracted extensive attention in neuromorphic vision processing. The spike-based and event-driven computation inherent in the spiking neural network (SNN) provides an energy-saving solution for AER object recognition. However, SNN with spike timing dependent plasticity (STDP) learning rule has not achieved satisfying AER object recognition performance. This work proposes an SNN-based encoder-decoder model to improve the recognition performance of AER objects. An STDP-based locally connected spiking neural network (LC-SNN) is proposed as an encoder to extract rich spatiotemporal features from AER event flows more flexibly. After the encoder extracts and learns primary features, we propose a fully connected spiking neural network (FC-SNN) based on the reward-modulated spike-timing-dependent plasticity (R-STDP) learning rule as a decoder to learn higher-level features for classification. In addition, we improved the winner-take-all (WTA) mechanisms and R-STDP learning rule in the decoder based on the reward and punish decision, enabling the network to perform better. The experiments are performed on the N-MNIST, MNIST-DVS, and the DVS Gesture datasets, improving the accuracy of the best existing plasticity-based SNN by 0.19%, 0.27% and 1.35%, respectively. © 2016 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Beyond MLE: convex learning for text generation 23

Beyond MLE: convex learning for text generation

引用

Proceedings of the 37th International Conference on Neural information Processing Systems

作者： Chenze Shao Zhengrui Ma Min Zhang Yang Feng Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences School of Future Science and Engineering Soochow University

Maximum likelihood estimation (MLE) is a statistical method used to estimate the parameters of a probability distribution that best explain the observed data. In the context of text generation, MLE is often used to train generative language models, which can then be used to generate new text. However, we argue that MLE is not always necessary and optimal, especially for closed-ended text generation tasks like machine translation. In these tasks, the goal of model is to generate the most appropriate response, which does not necessarily require it to estimate the entire data distribution with MLE. To this end, we propose a novel class of training objectives based on convex functions, which enables text generation models to focus on highly probable outputs without having to estimate the entire data distribution. We investigate the theoretical properties of the optimal predicted distribution when applying convex functions to the loss, demonstrating that convex functions can sharpen the optimal distribution, thereby enabling the model to better capture outputs with high probabilities. Experiments on various text generation tasks and models show the effectiveness of our approach. It enables autoregressive models to bridge the gap between greedy and beam search, and facilitates the learning of non-autoregressive models with a maximum improvement of 9+ BLEU points. Moreover, our approach also exhibits significant impact on large language models (LLMs), substantially enhancing their generative capability on various tasks. Source code is available at https://***/ictnlp/Convex-Learning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TEMSA:Text enhanced modal representation learning for multimodal sentiment analysis

引用

Computer Vision and Image Understanding 2025年 258卷

Multimodal sentiment analysis aims to identify human emotions by leveraging multimodal information, including language, visual, and audio data. Most existing models focus on extracting common features across modalities or simply integrating heterogeneous multimodal data. However, such approaches often overlook the unique representation advantages of individual modalities, as they treat all modalities equally and use bidirectional information transfer mechanisms. This can lead to information redundancy and feature conflicts. To address this challenge, we propose a Text-Enhanced Modal Representation Learning Model (TEMSA), which builds robust and unified multimodal representations through the design of text-guided pairwise cross-modal mapping modules. Specifically, TEMSA employs a text-guided multi-head cross-attention mechanism to embed linguistic information into the emotion-related representation learning of non-linguistic modalities, thereby enhancing the representations of visual and audio modalities. In addition to preserving consistent information through cross-modal mapping, TEMSA also incorporates text-guided reconstruction modules, which leverage text-enhanced non-linguistic modal features to decouple modality-specific representations from non-linguistic modalities. This dual representation learning framework captures inter-modal consistent information through cross-modal mapping, and extracts modal difference information through intra-modal decoupling, thus improving the understanding of cross-modal affective associations. The experimental results on the CMU-MOSI, CMU-MOSEI, and CH-SIMS datasets demonstrate that TEMSA achieves superior performance, highlighting the critical role of text-guided cross-modal and intra-modal representation learning in multimodal sentiment analysis. © 2025 Elsevier Inc.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning with Token-level Feedback for Controllable Text Generation

arXiv

引用

arXiv 2024年

作者： Li, Wendi Wei, Wei Xu, Kaihe Xie, Wenfeng Chen, Dangyang Cheng, Yu Cognitive Computing and Intelligent Information Processing Laboratory School of Computer Science and Technology Huazhong University of Science and Technology China China Ping An Property & Casualty Insurance company of China China The Chinese University of Hong Kong Hong Kong

To meet the requirements of real-world applications, it is essential to control generations of large language models (LLMs). Prior research has tried to introduce reinforcement learning (RL) into controllable text generation while most existing methods suffer from overfitting issues (finetuning-based methods) or semantic collapse (post-processing methods). However, current RL methods are generally guided by coarse-grained (sentence/paragraph-level) feedback, which may lead to suboptimal performance owing to semantic twists or progressions within sentences. To tackle that, we propose a novel reinforcement learning algorithm named TOLE which formulates TOken-LEvel rewards for controllable text generation, and employs a "first-quantize-then-noise" paradigm to enhance the robustness of the RL algorithm. Furthermore, TOLE can be flexibly extended to multiple constraints with little computational expense. Experimental results show that our algorithm can achieve superior performance on both single-attribute and multi-attribute control tasks. We have released our codes at https://***/WindyLee0822/CTG. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

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：