检索结果-内蒙古大学图书馆

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis

学校读者我要写书评

暂无评论

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-...

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

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

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Accurately synthesizing talking face videos and capturing fine facial features for individuals with long hair presents a significant challenge. To tackle these challenges in existing methods, we propose a decomposed per-embedding Gaussian fields (DEGSTalk), a 3D Gaussian Splatting (3DGS)-based talking face synthesis method for generating realistic talking faces with long hairs. Our DEGSTalk employs Deformable Pre-Embedding Gaussian Fields, which dynamically adjust pre-embedding Gaussian primitives using implicit expression coefficients. This enables precise capture of dynamic facial regions and subtle expressions. Additionally, we propose a Dynamic Hair-Preserving Portrait Rendering technique to enhance the realism of long hair motions in the synthesized videos. Results show that DEGSTalk achieves improved realism and synthesis quality compared to existing approaches, particularly in handling complex facial dynamics and hair preservation. Our code is available at https://***/CVI-SZU/DEGSTalk.

关键词： Hair Training Three-dimensional displays Dynamics Signal processing Rendering (computer graphics) Noise measurement Speech processing Faces Videos

Few-shot Class-Incremental Semantic Segmentation via Pseudo-Labeling and Knowledge Distillation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Jiang, Chengjia Wang, Tao Li, Sien Wang, Jinyang Wang, Shirui Antoniou, Antonios Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China The Key Laboratory of Cognitive Computing and Intelligent Information Processing of Fujian Education Institutions Wuyi University Wuyishan China College of Computer and Data Science Fuzhou University Fuzhou China Department of Computer Science and Engineering European University Cyprus Nicosia Cyprus

We address the problem of learning new classes for semantic segmentation models from few examples, which is challenging because of the following two reasons. Firstly, it is difficult to learn from limited novel data to capture the underlying class distribution. Secondly, it is challenging to retain knowledge for existing classes and to avoid catastrophic forgetting. For learning from limited data, we propose a pseudo-labeling strategy to augment the few-shot training annotations in order to learn novel classes more effectively. Given only one or a few images labeled with the novel classes and a much larger set of unlabeled images, we transfer the knowledge from labeled images to unlabeled images with a coarse-to-fine pseudo-labeling approach in two steps. Specifically, we first match each labeled image to its nearest neighbors in the unlabeled image set at the scene level, in order to obtain images with a similar scene layout. This is followed by obtaining pseudo-labels within this neighborhood by applying classifiers learned on the few-shot annotations. In addition, we use knowledge distillation on both labeled and unlabeled data to retain knowledge on existing classes. We integrate the above steps into a single convolutional neural network with a unified learning objective. Extensive experiments on the Cityscapes and KITTI datasets validate the efficacy of the proposed approach in the self-driving domain. Code is available from https://***/ChasonJiang/FSCILSS. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation

AN EFFICIENT NULLSPACE-PRESERVING SADDLE SEARCH METHOD FOR PHASE TRANSITIONS INVOLVING TRANSLATIONAL INVARIANCE

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Cui, Gang Jiang, Kai Zhou, Tiejun Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan411105 China

In this work, we propose an efficient nullspace-preserving saddle search (NPSS) method for a class of phase transitions involving translational invariance, where the critical states are often degenerate. The NPSS method includes two stages, escaping from the basin and searching for the index-1 generalized saddle point. The NPSS method climbs upward from the generalized local minimum in segments to overcome the challenges of degeneracy. In each segment, an effective ascent direction is ensured by keeping this direction orthogonal to the nullspace of the initial state in this segment. This method can escape the basin quickly and converge to the transition states. We apply the NPSS method to the phase transitions between crystals, and between crystal and quasicrystal, based on the Landau-Brazovskii and Lifshitz-Petrich free energy functionals. Numerical results show a good performance of the NPSS *** Codes 37M05, 49K35, 37N30 © 2023, CC BY-NC-ND.

关键词： Free energy

Learning Open-vocabulary Semantic Segmentation Models From Natural Language Supervision

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Xu, Jilan Hou, Junlin Zhang, Yuejie Feng, Rui Wang, Yi Qiao, Yu Xie, Weidi School of Computer Science Shanghai Key Lab of Intelligent Information Processing Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University China Shanghai AI Laboratory China Shanghai Jiaotong University China

In this paper, we consider the problem of open-vocabulary semantic segmentation (OVS), which aims to segment objects of arbitrary classes instead of pre-defined, closed-set categories. The main contributions are as follows: First, we propose a transformer-based model for OVS, termed as OVSegmentor, which only exploits web-crawled image-text pairs for pre-training without using any mask annotations. OVSegmentor assembles the image pixels into a set of learnable group tokens via a slot-attention based binding module, and aligns the group tokens to the corresponding caption embedding. Second, we propose two proxy tasks for training, namely masked entity completion and cross-image mask consistency. The former aims to infer all masked entities in the caption given the group tokens, that enables the model to learn fine-grained alignment between visual groups and text entities. The latter enforces consistent mask predictions between images that contain shared entities, which encourages the model to learn visual invariance. Third, we construct CC4M dataset for pre-training by filtering CC12M with frequently appeared entities, which significantly improves training efficiency. Fourth, we perform zero-shot transfer on three benchmark datasets, PASCAL VOC 2012, PASCAL Context, and COCO Object. Our model achieves superior segmentation results over the state-of-the-art method by using only 3% data (4M vs 134M) for pre-training. Code and pre-trained models will be released for future research. © 2023, CC BY.

关键词： Semantics

DanceFix: An Exploration in Group Dance Neatness Assessment Through Fixing Abnormal Challenges of Human Pose 39

学校读者我要写书评

暂无评论

DanceFix: An Exploration in Group Dance Neatness Assessment ...

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Xu, Huangbiao Ke, Xiao Wu, Huanqi Xu, Rui Li, Yuezhou Xu, Peirong Guo, Wenzhong Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou University Fuzhou350116 China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou350116 China

ISBN: (纸本)157735897X

The fair and objective assessment of performances and competitions is a common pursuit and challenge in human society. The application of computer vision technology offers hope for this purpose, but it still faces obstacles such as occlusion and motion blur. To address these hindrances, our DanceFix proposes a bidirectional spatial-temporal context optical flow correction (BOFC) method. This approach leverages the consistency and complementarity of motion information between two modalities: optical flow, which excels at pixel capture, and lightweight skeleton data. It enables the extraction of pixel-level motion changes and the correction of abnormal skeleton data. Furthermore, we propose a part-level dance dataset (Dancer Parts) and part-level motion feature extraction based on task decoupling (PETD). This aims to decouple complex whole-body parts tracking into fine-grained limb-level motion extraction, enhancing the confidence of temporal information and the accuracy of correction for abnormal data. Finally, we present the DNV dataset, which simulates fully neat group dance scenes and provides reliable labels and validation methods for the newly introduced group dance neatness assessment (GDNA). To the best of our knowledge, this is the first work to develop quantitative criteria for assessing limb and joint neatness in group dance. We conduct experiments on DNV and video-based public JHMDB datasets. Our method effectively corrects abnormal skeleton points, flexibly embeds, and improves the accuracy of existing pose estimation algorithms. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

A Local Regression-Based SLA-Aware Energy-Efficient Virtual Machine Consolidation Algorithm in Data Centers

学校读者我要写书评

暂无评论

A Local Regression-Based SLA-Aware Energy-Efficient Virtual ...

International Conference on Big Data computing and Communications (BIGCOM)

作者： Xiaodong Wu Ronghai Wang Guoxin Lin School of Mathmatics and Computer Science Quanzhou Normal University Fujian Provincial Key Laboratory of Data-Intensive Computing Key Laboratory of Intelligent Computing and Information Processing Fujian Province University Fujian Provincial Big Data Research Institute of Intelligent Manufacturing Quanzhou China

Virtual Machine Consolidation (VMC) is an effective means to improve the resource utilization and reduce energy consumption of data centers. However, the VMC optimization that only considers energy consumption may lead to SLA (Service-Level Agreements) violations and thus fail to guarantee the QoS (Quality of Service) provided. Therefore, it is necessary to consider both energy saving and SLA violations in the process of VMC. In this paper, we propose an energy and SLA-aware VMC algorithm that considers both energy saving and SLA violation optimization in data centers. The proposed algorithm uses the local regression method to predict the utilization of virtual machines, based on which it determines whether the host will be overloaded, so as to make the decision of virtual machine migrations. The proposed VMC algorithm is evaluated with CloudSim toolkit. Simulation results demonstrate that our algorithm has good energy saving performance and can effectively reduce SLA violation in cloud data center. Considering energy consumption and SLA violation, the ESV can be reduced by 7.57% on average and 16.36% at most compared with other algorithms.

关键词：

Few-Shot Class-Incremental Semantic Segmentation via Pseudo-Labeling and Knowledge Distillation

学校读者我要写书评

暂无评论

Few-Shot Class-Incremental Semantic Segmentation via Pseudo-...

information science, Parallel and Distributed Systems (ISPDS), International Conference on

作者： Chengjia Jiang Tao Wang Sien Li Jinyang Wang Shirui Wang Antonios Antoniou Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China The Key Laboratory of Cognitive Computing and Intelligent Information Processing Fujian Education Institutions Wuyi University Wuyishan China College of Computer and Data Science Fuzhou University Fuzhou China Department of Computer Science and Engineering European University Cyprus Nicosia Cyprus

关键词：

A Unified Generalization Analysis of Re-Weighting and Logit-Adjustment for Imbalanced Learning 37

学校读者我要写书评

暂无评论

A Unified Generalization Analysis of Re-Weighting and Logit-...

37th Conference on Neural information processing Systems, NeurIPS 2023

作者： Wang, Zitai Xu, Qianqian Yang, Zhiyong He, Yuan Cao, Xiaochun Huang, Qingming SKLOIS Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS China School of Computer Science and Tech. University of Chinese Academy of Sciences China Alibaba Group China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China BDKM University of Chinese Academy of Sciences China

ISBN: (纸本)9781713899921

Real-world datasets are typically imbalanced in the sense that only a few classes have numerous samples, while many classes are associated with only a few samples. As a result, a naïve ERM learning process will be biased towards the majority classes, making it difficult to generalize to the minority classes. To address this issue, one simple but effective approach is to modify the loss function to emphasize the learning on minority classes, such as re-weighting the losses or adjusting the logits via class-dependent terms. However, existing generalization analysis of such losses is still coarse-grained and fragmented, failing to explain some empirical results. To bridge this gap, we propose a novel technique named data-dependent contraction to capture how these modified losses handle different classes. On top of this technique, a fine-grained generalization bound is established for imbalanced learning, which helps reveal the mystery of re-weighting and logit-adjustment in a unified manner. Furthermore, a principled learning algorithm is developed based on the theoretical insights. Finally, the empirical results on benchmark datasets not only validate the theoretical results but also demonstrate the effectiveness of the proposed method. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： Contrastive Learning

Low-rank generalized alternating direction implicit iteration method for solving matrix equations

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Juan Xun, Wenlu Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Hunan Key Laboratory for Computation and Simulation in Science and Engineering School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan China School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan China

This paper presents an effective low-rank generalized alternating direction implicit iteration (R-GADI) method for solving large-scale sparse and stable Lyapunov matrix equations and continuous-time algebraic Riccati matrix equations. The method is based on generalized alternating direction implicit iteration (GADI), which exploits the low-rank property of matrices and utilizes the Cholesky factorization approach for solving. The advantage of the new algorithm lies in its direct and efficient low-rank formulation, which is a variant of the Cholesky decomposition in the Lyapunov GADI method, saving storage space and making it computationally effective. When solving the continuous-time algebraic Riccati matrix equation, the Riccati equation is first simplified to a Lyapunov equation using the Newton method, and then the R-GADI method is employed for computation. Additionally, we analyze the convergence of the R-GADI method and prove its consistency with the convergence of the GADI method. Finally, the effectiveness of the new algorithm is demonstrated through corresponding numerical experiments. Copyright © 2024, The Authors. All rights reserved.

关键词： Riccati equations