检索结果-内蒙古大学图书馆

An Improved Differential Evolution Algorithm Integrating the Plant Evolutionary Strategy

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Zhang, Xiaoming Cheng, Hongwei Li, Jun Li, Tingjuan Zhang, Panpan Tian, Ye Institutes of Physical Science and Information Technology Anhui University Hefei230601 China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei230601 China Qinghai Institute of Science and Technology Information Xining810008 China School of Computer Science and Technology Anhui University Hefei230601 China

Differential evolution algorithm (DE) and their variants often encounter a decrease in population diversity and convergence rate along with the evolution, resulting in local optima and premature convergence. To address this issue, this paper proposes an improved differential evolution integrating the plant evolutionary strategy, named DEPES, leveraging the exploitation capability of DE and the exploration capability of the plant population distribution evolutionary strategy. First, a tri-subpopulation optimization framework with a mutation strategy is introduced to cope with diversity maintenance, convergence enhancement, and local optima a Cauchy mutation operator based on plant population distribution evolutionary model is employed to enhance the exploration capability of the mutation strategy. Second, a parameter control strategy is performed on the superior and inferior solutions to balance the exploitation and exploration of the population. Third, a covariance matrix-based crossover strategy is designed to minimize interference from local population information, consequently generating high-quality solutions. The superior efficiency of DEPES is fully verified by comparing it with advanced DE-based variants and other algorithms on the IEEE CEC2020 test suite and engineering design problems. © 2024, The Authors. All rights reserved.

关键词： Covariance matrix

Uncertainty-boosted Robust Video Activity Anticipation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Qi, Zhaobo Wang, Shuhui Zhang, Weigang Huang, Qingming The School of Computer Science and Technology Harbin Institute of Technology Weihai264209 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Peng Cheng Laboratory Shenzhen518066 China The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China

Video activity anticipation aims to predict what will happen in the future, embracing a broad application prospect ranging from robot vision and autonomous driving. Despite the recent progress, the data uncertainty issue, reflected as the content evolution process and dynamic correlation in event labels, has been somehow ignored. This reduces the model generalization ability and deep understanding on video content, leading to serious error accumulation and degraded performance. In this paper, we address the uncertainty learning problem and propose an uncertainty-boosted robust video activity anticipation framework, which generates uncertainty values to indicate the credibility of the anticipation results. The uncertainty value is used to derive a temperature parameter in the softmax function to modulate the predicted target activity distribution. To guarantee the distribution adjustment, we construct a reasonable target activity label representation by incorporating the activity evolution from the temporal class correlation and the semantic relationship. Moreover, we quantify the uncertainty into relative values by comparing the uncertainty among sample pairs and their temporal-lengths. This relative strategy provides a more accessible way in uncertainty modeling than quantifying the absolute uncertainty values on the whole dataset. Experiments on multiple backbones and benchmarks show our framework achieves promising performance and better robustness/interpretability. Source codes are available at https://***/qzhb/UbRV2A. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

Contrastive Learning of Person-independent Representations for Facial Action Unit Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Yong Shan, Shiguang The Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China The Key Laboratory of Intelligent Information Processing Chinese Academy of Sciences Institute of Computing Technology CAS Beijing100190 China The University of Chinese Academy of Sciences Beijing100049 China Peng Cheng Laboratory Shenzhen518055 China

Facial action unit (AU) detection, aiming to classify AU present in the facial image, has long suffered from insufficient AU annotations. In this paper, we aim to mitigate this data scarcity issue by learning AU representations from a large number of unlabelled facial videos in a contrastive learning paradigm. We formulate the self-supervised AU representation learning signals in two-fold: (1) AU representation should be frame-wisely discriminative within a short video clip;(2) Facial frames sampled from different identities but show analogous facial AUs should have consistent AU representations. As to achieve these goals, we propose to contrastively learn the AU representation within a video clip and devise a cross-identity reconstruction mechanism to learn the person-independent representations. Specially, we adopt a margin-based temporal contrastive learning paradigm to perceive the temporal AU coherence and evolution characteristics within a clip that consists of consecutive input facial frames. Moreover, the cross-identity reconstruction mechanism facilitates pushing the faces from different identities but show analogous AUs close in the latent embedding space. Experimental results on three public AU datasets demonstrate that the learned AU representation is discriminative for AU detection. Our method outperforms other contrastive learning methods and significantly closes the performance gap between the self-supervised and supervised AU detection approaches. © 2024, CC BY.

关键词： Learning systems

Dual Encoders for Diffusion-based Image Inpainting

学校读者我要写书评

暂无评论

Dual Encoders for Diffusion-based Image Inpainting

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Dezhi Zheng Kaijun Deng Jinbao Wang Linlin Shen Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Current diffusion-based inpainting models struggle to preserve unmasked regions or generate highly coherent content. Additionally, it is hard for them to generate meaningful content for 3D inpainting. To tackle these challenges, we design a plug-and-play branch that runs through the entire generation process to enhance existing models. Specifically, we utilize dual encoders - a Convolutional Neural Network (CNN) encoder and the pre-trained Variational AutoEncoder (VAE) encoder, to encode masked images. The latent code and the feature map from the dual encoders are fed to diffusion models simultaneously. In addition, we apply Zero-padded initialization to solve the problem of mode collapse caused by this branch. Experiments on BrushBench and EditBench demonstrate that models with our plug-and-play branch can improve the coherence of inpainting, and our model achieves new state-of-the-art results.

关键词： Visualization Three-dimensional displays Codes Autoencoders Coherence Signal processing Diffusion models Decoding Convolutional neural networks Speech processing

DISC: Learning from Noisy labels via Dynamic Instance-Specific Selection and Correction

学校读者我要写书评

暂无评论

DISC: Learning from Noisy Labels via Dynamic Instance-Specif...

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yifan Li Hu Han Shiguang Shan Xilin Chen Key Laboratory of Intelligent Information Processing Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China University of the Chinese Academy of Sciences Beijing China Peng Cheng Laboratory Shenzhen China

Existing studies indicate that deep neural networks (DNNs) can eventually memorize the label noise. We observe that the memorization strength of DNNs towards each instance is different and can be represented by the confidence value, which becomes larger and larger during the training process. Based on this, we propose a Dynamic Instance-specific Selection and Correction method (DISC) for learning from noisy labels (LNL). We first use a two- view-based backbone for image classification, obtaining confidence for each image from two views. Then we propose a dynamic threshold strategy for each instance, based on the momentum of each instance's memorization strength in previous epochs to select and correct noisy labeled data. Benefiting from the dynamic threshold strategy and two-view learning, we can effectively group each instance into one of the three subsets (i.e., clean, hard, and purified) based on the prediction consistency and discrepancy by two views at each epoch. Finally, we employ different regularization strategies to conquer subsets with different degrees of label noise, improving the whole network's robustness. Comprehensive evaluations on three controllable and four real-world LNL benchmarks show that our method outperforms the state-of-the-art (SOTA) methods to leverage useful information in noisy data while alleviating the pollution of label noise. Code is available at https://***/JackYFL/DISC.

关键词：

From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videos

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Chen, Yin Li, Jia 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) in the wild is still hindered by data limitations, e.g., insufficient quantity and diversity of pose, occlusion and illumination, as well as the inherent ambiguity of facial expressions. In contrast, static facial expression recognition (SFER) currently shows much higher performance and can benefit from more abundant high-quality training data. Moreover, the appearance features and dynamic dependencies of DFER remain largely unexplored. Recognizing the potential in leveraging SFER knowledge for DFER, we introduce a novel Static-to-Dynamic model (S2D) that leverages existing SFER knowledge and dynamic information implicitly encoded in extracted facial landmark-aware features, thereby significantly improving DFER performance. Firstly, we build and train an image model for SFER, which incorporates a standard Vision Transformer (ViT) and Multi-View Complementary Prompters (MCPs) only. Then, we obtain our video model (i.e., S2D), for DFER, by inserting Temporal-Modeling Adapters (TMAs) into the image model. MCPs enhance facial expression features with landmark-aware features inferred by an off-the-shelf facial landmark detector. And the TMAs capture and model the relationships of dynamic changes in facial expressions, effectively extending the pre-trained image model for videos. Notably, MCPs and TMAs only increase a fraction of trainable parameters (less than +10%) to the original image model. Moreover, we present a novel Emotion-Anchors (i.e., reference samples for each emotion category) based Self-Distillation Loss to reduce the detrimental influence of ambiguous emotion labels, further enhancing our S2D. Experiments conducted on popular SFER and DFER datasets show that we have achieved a new state of the art. Copyright © 2023, The Authors. All rights reserved.

关键词： Face recognition

SFDA-rPPG: Source-Free Domain Adaptive Remote Physiological Measurement with Spatio-Temporal Consistency

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xie, Yiping Yu, Zitong Wu, Bingjie Xie, Weicheng Shen, Linlin Computer Vision Institute School of Computer Science & Software Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Singapore

Remote Photoplethysmography (rPPG) is a non-contact method that uses facial video to predict changes in blood volume, enabling physiological metrics measurement. Traditional rPPG models often struggle with poor generalization capacity in unseen domains. Current solutions to this problem is to improve its generalization in the target domain through Domain Generalization (DG) or Domain Adaptation (DA). However, both traditional methods require access to both source domain data and target domain data, which cannot be implemented in scenarios with limited access to source data, and another issue is the privacy of accessing source domain data. In this paper, we propose the first Source-free Domain Adaptation benchmark for rPPG measurement (SFDA-rPPG), which overcomes these limitations by enabling effective domain adaptation without access to source domain data. Our framework incorporates a Three-Branch Spatio-Temporal Consistency Network (TSTC-Net) to enhance feature consistency across domains. Furthermore, we propose a new rPPG distribution alignment loss based on the Frequency-domain Wasserstein Distance (FWD), which leverages optimal transport to align power spectrum distributions across domains effectively and further enforces the alignment of the three branches. Extensive cross-domain experiments and ablation studies demonstrate the effectiveness of our proposed method in source-free domain adaptation settings. Our findings highlight the significant contribution of the proposed FWD loss for distributional alignment, providing a valuable reference for future research and applications. The source code is available at https://***/XieYiping66/SFDA-rPPG. Copyright © 2024, The Authors. All rights reserved.

关键词： Photoplethysmography

学校读者我要写书评

暂无评论

Hand and gesture

Virtual Reality & intelligent Hardware 2021年第3期3卷 I0001-I0002页

作者： Xilin CHEN Key Lab of Intelligent Information Processing of Chinese Academy of Sciences(CAS) Institute of Computing TechnologyCASBeijing 100190China

Hands play an important role in our daily *** use our hands for manipulation in working,emphasis in speaking,communication in non-verbal environment,*** gesture not only uses for simple commands in traffic control,but also extends as a kind of language-sign *** the areas of VR/AR and HCI,understanding hand and its action can greatly improve user *** covers a broad topics related to hands,including hand detection,tracking,hand pose estimation,gesture recognition,and sign language *** papers are collected in this *** cover different topics related to hand and gesture.

关键词： verbal language. hands

DFTR: Depth-supervised Fusion Transformer for Salient Object Detection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhu, Heqin Sun, Xu Li, Yuexiang Ma, Kai Zhou, S. Kevin Zheng, Yefeng Key Lab of Intelligent Information Processing Chinese Academy of Sciences Institute of Computing Technology Beijing100190 China Tencent Jarvis Lab Shenzhen China University of Science and Technology of China Suzhou215123 China

Automated salient object detection (SOD) plays an increasingly crucial role in many computer vision applications. By reformulating the depth information as supervision rather than as input, depth-supervised convolutional neural networks (CNN) have achieved promising results on both RGB and RGB-D SOD scenarios with the merits of no requirements for extra depth networks and depth inputs in the inference stage. This paper, for the first time, seeks to expand the applicability of depth supervision to the Transformer architecture. Specifically, we develop a Depth-supervised Fusion TRansformer (DFTR), to further improve the accuracy of both RGB and RGB-D SOD. The proposed DFTR involves three primary features: 1) DFTR, to the best of our knowledge, is the first pure Transformer-based model for depth-supervised SOD;2) A multi-scale feature aggregation (MFA) module is proposed to fully exploit the multi-scale features encoded by the Swin Transformer in a coarse-to-fine manner;3) To enable bidirectional information flow across different streams of features, a novel multi-stage feature fusion (MFF) module is further integrated into our DFTR with the emphasis on salient regions at different network learning stages. We extensively evaluate the proposed DFTR on ten benchmarking datasets. Experimental results show that our DFTR consistently outperforms the existing state-of-the-art methods for both RGB and RGB-D SOD tasks. The code and model will be made publicly available. © 2022, CC BY-NC-SA.

关键词： Object detection