IEEE transactions on neural networks and learning systems最新文献

TransXNet: Learning Both Global and Local Dynamics With a Dual Dynamic Token Mixer for Visual Recognition

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-04-03 DOI: 10.1109/tnnls.2025.3550979

Meng Lou, Shu Zhang, Hong-Yu Zhou, Sibei Yang, Chuan Wu, Yizhou Yu

引用次数: 0

Learning Sequential Variation Information for Dynamic Facial Expression Recognition.

IF 10.2 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-04-02 DOI: 10.1109/TNNLS.2025.3548669

Bei Pan, Kaoru Hirota, Yaping Dai, Zhiyang Jia, Shuai Shao, Jinhua She

{"title":"Learning Sequential Variation Information for Dynamic Facial Expression Recognition.","authors":"Bei Pan, Kaoru Hirota, Yaping Dai, Zhiyang Jia, Shuai Shao, Jinhua She","doi":"10.1109/TNNLS.2025.3548669","DOIUrl":"https://doi.org/10.1109/TNNLS.2025.3548669","url":null,"abstract":"A multiscale sequence information fusion (MSSIF) method is presented for dynamic facial expression recognition (DFER) in video sequences. It exploits multiscale information by integrating features from individual frames, subsequences, and entire sequences through a transformer-based architecture. This hierarchical feature fusion process includes deep feature extraction at the frame level to capture intricate visual details, intrasubsequence fusion using self-attention mechanisms for analyzing adjacent frames, and intersubsequence fusion to synthesize long-term emotional dynamics across time scales. The efficacy of MSSIF is demonstrated through extensive evaluation on three video datasets: eNTERFACE'05, BAUM-1s, and AFEW, where it achieves overall recognition accuracies of 60.1%, 60.7%, and 58.8%, respectively. These results substantiate MSSIF's superior performance in accurately recognizing facial expressions by managing short and long-term dependencies within video sequences, making it a potent tool for real-world applications requiring nuanced dynamic facial expression detection.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"PP ","pages":""},"PeriodicalIF":10.2,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143772229","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Exploring Dynamic Transformer for Efficient Object Tracking.

IF 10.2 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-04-02 DOI: 10.1109/TNNLS.2025.3545752

Jiawen Zhu, Xin Chen, Haiwen Diao, Shuai Li, Jun-Yan He, Chenyang Li, Bin Luo, Dong Wang, Huchuan Lu

{"title":"Exploring Dynamic Transformer for Efficient Object Tracking.","authors":"Jiawen Zhu, Xin Chen, Haiwen Diao, Shuai Li, Jun-Yan He, Chenyang Li, Bin Luo, Dong Wang, Huchuan Lu","doi":"10.1109/TNNLS.2025.3545752","DOIUrl":"https://doi.org/10.1109/TNNLS.2025.3545752","url":null,"abstract":"The speed-precision tradeoff is a critical problem in visual object tracking, as it typically requires low latency and is deployed on resource-constrained platforms. Existing solutions for efficient tracking primarily focus on lightweight backbones or modules, which, however, come at a sacrifice in precision. In this article, inspired by dynamic network routing, we propose DyTrack, a dynamic transformer framework for efficient tracking. Real-world tracking scenarios exhibit varying levels of complexity. We argue that a simple network is sufficient for easy video frames, while more computational resources should be assigned to difficult ones. DyTrack automatically learns to configure proper reasoning routes for different inputs, thereby improving the utilization of the available computational budget and achieving higher performance at the same running speed. We formulate instance-specific tracking as a sequential decision problem and incorporate terminating branches to intermediate layers of the model. Furthermore, we propose a feature recycling mechanism to maximize computational efficiency by reusing the outputs of predecessors. Additionally, a target-aware self-distillation strategy is designed to enhance the discriminating capabilities of early-stage predictions by mimicking the representation patterns of the deep model. Extensive experiments demonstrate that DyTrack achieves promising speed-precision tradeoffs with only a single model. For instance, DyTrack obtains 64.9% area under the curve (AUC) on LaSOT with a speed of 256fps.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"PP ","pages":""},"PeriodicalIF":10.2,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143772227","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Survey on Self-Supervised Monocular Depth Estimation Based on Deep Neural Networks

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-04-01 DOI: 10.1109/tnnls.2025.3552598

Qiulei Dong, Zhengming Zhou, Xiaolan Qiu, Liting Zhang

引用次数: 0

Data-Based Model-Free Predictive Control System Under the Design Philosophy of MPC and Zeroing Neurodynamics for Robotic Arm Pose Tracking

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-04-01 DOI: 10.1109/tnnls.2025.3553195

Mengrui Cao, Lin Xiao, Qiuyue Zuo, Linju Li, Xieping Gao

引用次数: 0

Assisting Training of Deep Spiking Neural Networks With Parameter Initialization

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-04-01 DOI: 10.1109/tnnls.2025.3547774

Jianhao Ding, Jiyuan Zhang, Tiejun Huang, Jian K. Liu, Zhaofei Yu

引用次数: 0

Robust Reconstructed Neural Network Based on Spectral Elastic Activation

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-04-01 DOI: 10.1109/tnnls.2025.3548439

Zecheng Tang, Xiaolong Wu, Honggui Han

引用次数: 0

Pseudo-Supervision Affinity Propagation for Efficient and Scalable Multiview Clustering

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-04-01 DOI: 10.1109/tnnls.2025.3545465

Xinxin Wang, Yongshan Zhang, Yicong Zhou

引用次数: 0

Reinforcement Learning-Based Fault-Tolerant Control of Uncertain Strict-Feedback Nonlinear Systems With Intermittent Actuator Faults

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-04-01 DOI: 10.1109/tnnls.2025.3550527

Qinmin Yang, Huaying Li, Zhengwei Ruan, Bo Fan, Shuzhi Sam Ge

引用次数: 0

Self-Organizing Stacked Type-2 Fuzzy Neural Network With Rule Generalization 具有规则泛化功能的自组织堆叠式 2 型模糊神经网络

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-04-01 DOI: 10.1109/tnnls.2025.3544495

Honggui Han, Chenxuan Sun, Xiaolong Wu, Hongyan Yang, Dezheng Zhao

引用次数: 0