检索结果-内蒙古大学图书馆

Enhanced quadratic video interpolation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Yihao Xie, Liangbin Siyao, Li Sun, Wenxiu Qiao, Yu Dong, Chao ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China SenseTime Research

With the prosperity of digital video industry, video frame interpolation has arisen continuous attention in computer vision community and become a new upsurge in industry. Many learning-based methods have been proposed and achieved progressive results. Among them, a recent algorithm named quadratic video interpolation (QVI) achieves appealing performance. It exploits higher-order motion information (e.g. acceleration) and successfully models the estimation of interpolated flow. However, its produced intermediate frames still contain some unsatisfactory ghosting, artifacts and inaccurate motion, especially when large and complex motion occurs. In this work, we further improve the performance of QVI from three facets and propose an enhanced quadratic video interpolation (EQVI) model. In particular, we adopt a rectified quadratic flow prediction (RQFP) formulation with least squares method to estimate the motion more accurately. Complementary with image pixel-level blending, we introduce a residual contextual synthesis network (RCSN) to employ contextual information in high-dimensional feature space, which could help the model handle more complicated scenes and motion patterns. Moreover, to further boost the performance, we devise a novel multi-scale fusion network (MS-Fusion) which can be regarded as a learnable augmentation process. The proposed EQVI model won the first place in the AIM2020 Video Temporal Super-Resolution Challenge. Codes are available at https://***/lyh-18/EQVI. Copyright © 2020, The Authors. All rights reserved.

关键词： Least squares approximations

Face recognition - A one-shot learning perspective 15

学校读者我要写书评

暂无评论

Face recognition - A one-shot learning perspective

15th International Conference on Signal Image Technology and Internet Based Systems, SISITS 2019

作者： Chanda, Sukalpa Gv, Asish Chakrapani Brun, Anders Hast, Anders Pal, Umapada Doermann, David Department of Information Technology Østfold University College Norway Computer Vision and Pattern Recognition Unit Indian Statistical Institute India Centre for Image Analysis Uppsala University Sweden Computer Science and Engineering University at Buffalo United States

ISBN: (纸本)9781728156866

Ability to learn from a single instance is something unique to the human species and One-shot learning algorithms try to mimic this special capability. On the other hand, despite the fantastic performance of Deep Learning-based methods on various image classification problems, performance often depends having on a huge number of annotated training samples per class. This fact is certainly a hindrance in deploying deep neural network-based systems in many real-life applications like face recognition. Furthermore, an addition of a new class to the system will require the need to re-train the whole system from scratch. Nevertheless, the prowess of deep learned features could also not be ignored. This research aims to combine the best of deep learned features with a traditional One-Shot learning framework. Results obtained on 2 publicly available datasets are very encouraging achieving over 90% accuracy on 5-way One-Shot tasks, and 84% on 50-way One-Shot problems. © 2019 IEEE.

关键词： Face recognition

Smallbignet: Integrating core and contextual views for video classification

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Li, Xianhang Wang, Yali Zhou, Zhipeng Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society

Temporal convolution has been widely used for video classification. However, it is performed on spatio-temporal contexts in a limited view, which often weakens its capacity of learning video representation. To alleviate this problem, we propose a concise and novel SmallBig network, with the cooperation of small and big views. For the current time step, the small view branch is used to learn the core semantics, while the big view branch is used to capture the contextual semantics. Unlike traditional temporal convolution, the big view branch can provide the small view branch with the most activated video features from a broader 3D receptive field. Via aggregating such big-view contexts, the small view branch can learn more robust and discriminative spatio-temporal representations for video classification. Furthermore, we propose to share convolution in the small and big view branch, which improves model compactness as well as alleviates overfitting. As a result, our SmallBigNet achieves a comparable model size like 2D CNNs, while boosting accuracy like 3D CNNs. We conduct extensive experiments on the large-scale video benchmarks, e.g., Kinetics400, Something-Something V1 and V2. Our SmallBig network outperforms a number of recent state-of-the-art approaches, in terms of accuracy and/or efficiency. The codes and models will be available on https://***/xhl-video/SmallBigNet. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution

Learning Attentive Pairwise Interaction for Fine-Grained Classification

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhuang, Peiqin Wang, Yali Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society

Fine-grained classification is a challenging problem, due to subtle differences among highly-confused categories. Most approaches address this difficulty by learning discriminative representation of individual input image. On the other hand, humans can effectively identify contrastive clues by comparing image pairs. Inspired by this fact, this paper proposes a simple but effective Attentive Pairwise Interaction Network (API-Net), which can progressively recognize a pair of fine-grained images by interaction. Specifically, API-Net first learns a mutual feature vector to capture semantic differences in the input pair. It then compares this mutual vector with individual vectors to generate gates for each input image. These distinct gate vectors inherit mutual context on semantic differences, which allow API-Net to attentively capture contrastive clues by pairwise interaction between two images. Additionally, we train API-Net in an end-to-end manner with a score ranking regularization, which can further generalize API-Net by taking feature priorities into account. We conduct extensive experiments on five popular benchmarks in fine-grained classification. API-Net outperforms the recent SOTA methods, i.e., CUB-200-2011 (90.0%), Aircraft (93.9%), Stanford Cars (95.3%), Stanford Dogs (90.3%), and NABirds (88.1%). Copyright © 2020, The Authors. All rights reserved.

关键词： Vectors

Detach and Enhance: Learning Disentangled Cross-modal Latent Representation for Efficient Face-Voice Association and Matching

学校读者我要写书评

暂无评论

Detach and Enhance: Learning Disentangled Cross-modal Latent...

IEEE International Conference on Data Mining (ICDM)

作者： Zhenning Yu Xin Liu Yiu-Ming Cheung Minghang Zhu Xing Xu Nannan Wang Taihao Li Dept. of Comput. Sci. & Fujian Key Lab. of Big Data Intelligence and Security Huaqiao University Xiamen China Zhejiang Lab Hangzhou China Dept. of Comput. Sci. and Institute of Research and Continuing Education HK Baptist University Hong Kong SAR China Xiamen Key Lab. of Computer Vision and Pattern Recognition Huaqiao University Xiamen China Dept. of Computer Sci. and Eng. University of Electronic Science and Technology of China Chengdu China State Key Lab. of Integrated Services Networks & School of Telecommun. Eng. Xidian University Xi’an China

Many researches in cognitive science have shown that humans often perform face-voice association for various perception tasks, and some recent data mining works have been designed in emulating such ability intelligently. Nevertheless, most methods often suffer from the degraded performance when there exist semantically irrelevant interference factors across different modalities. To alleviate this concern, this paper presents an efficient Disentangled Cross-modal Latent Representation (DCLR) method to adaptively detach the discriminative feature attributes and enhance the face-voice association. To be specific, the proposed DCLR framework consists of two-stage cross-modal disentangling process. First, the former stage employs the supervised contrastive learning to push the representations of face-voice data from the same person closer while pulling those representations of different person away. Then, the latter stage freezes all the parameters of the former stage, and further innovates a multi-layer orthogonal decoupling scheme to learn the disentangled latent representations, while filtering out the modality-dependent irrelevant factors. Besides, the cross-modal reconstruction loss is further utilized to narrow down the semantic gap between heterogeneous feature expressions. Through the joint exploitation of the above, the proposed framework can well associate the face-voice data to benefit various kinds of cross-modal perception tasks. Extensive experiments verify the superiorities of the proposed face-voice association framework and show its competitive performances.

关键词： Representation learning Filtering Semantics Interference Data models Cognitive science Data mining

Fusion of Super-Resolution and Semantic Segmentation Deep Models for Building Footprint Extraction From Aerial Images

学校读者我要写书评

暂无评论

The Photogrammetric Record 2025年第190期40卷

作者： Ziyi Chen Yuhua Luo Jiaying Zhang Ronggang Guo Liai Deng Jinghua Liu Dilong Li Yongtao Yu Ammar Abulibdeh Cheng Wang Department of Computer Science and Technology Fujian Key Laboratory of big Data Intelligence and Security Xiamen Key Laboratory of Computer Vision and Pattern Recognition Huaqiao University Xiamen FJ China Guojiao Spatial Information Technology (Beijing) co. Ltd Beijing China Faculty of Computer and Software Engineering Huaiyin Institute of Technology Huaian JS China Department of Humanities College of Arts and Sciences Qatar University Doha Qatar School of Informatics Xiamen University Xiamen FJ China

The spatial resolution of remotely sensed images has seen significant improvements; higher resolution facilitates the understanding of remote sensing images and improves the accuracy of building footprint extraction. Thus, this paper introduces a novel approach that combines super-resolution reconstruction with semantic segmentation deep models for building footprint extraction. To begin, a super-resolution reconstruction deep model is employed to enhance the resolution of the target images. Subsequently, training samples are generated using various data augmentation techniques based on the reconstructed images. Finally, a semantic segmentation deep model is trained to perform the final building footprint extraction. For validation, our proposed framework was tested on two publicly available aerial image datasets: the WHU building dataset and the Massachusetts building dataset. The results obtained from these datasets demonstrated the effectiveness of our method, achieving high Intersection over Union (IoU) scores of 90.57% and 75.02%, respectively. Furthermore, our approach outperformed seven other competing methods, showcasing its superior performance.

关键词： aerial image building footprint extraction deep learning semantic segmentation super-resolution

Weakly Supervised Temporal Sentence Grounding via Positive Sample Mining

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Dong, Lu Zhang, Haiyu Zhang, Hongjie Huang, Yifei Ling, Zhen-Hua Qiao, Yu Wang, Limin Wang, Yali University of Science and Technology of China Hefei230027 China Shanghai Artificial Intelligence Laboratory Shanghai202150 China Beihang University Beijing100191 China State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China Shenzhen Key Laboratory of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China

The task of weakly supervised temporal sentence grounding (WSTSG) aims to detect temporal intervals corresponding to a language description from untrimmed videos with only video-level video-language correspondence. For an anchor sample, most existing approaches generate negative samples either from other videos or within the same video for contrastive learning. However, some training samples are highly similar to the anchor sample, directly regarding them as negative samples leads to difficulties for optimization and ignores the correlations between these similar samples and the anchor sample. To address this, we propose Positive Sample Mining (PSM), a novel framework that mines positive samples from the training set to provide more discriminative supervision. Specifically, for a given anchor sample, we partition the remaining training set into semantically similar and dissimilar subsets based on the similarity of their text queries. To effectively leverage these correlations, we introduce a PSM-guided contrastive loss to ensure that the anchor proposal is closer to similar samples and further from dissimilar ones. Additionally, we design a PSM-guided rank loss to ensure that similar samples are closer to the anchor proposal than to the negative intra-video proposal, aiming to distinguish the anchor proposal and the negative intra-video proposal. Experiments on the WSTSG and grounded VideoQA tasks demonstrate the effectiveness and superiority of our method. © 2025, CC BY.

关键词： Contrastive Learning

Attention in Attention: Modeling Context Correlation for Efficient Video Classification

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Hao, Yanbin Wang, Shuo Cao, Pei Gao, Xinjian Xu, Tong Wu, Jinmeng He, Xiangnan The CCCD Key Lab of Ministry of Culture and Tourism School of Data Science School of Information Science and Technology University of Science and Technology of China Anhui 230026 China The Wuhan Research Institute of Posts and Telecommunications Hubei Wuhan430205 China The School of Computer Science and Information Engineering School of Artificial Intelligence Hefei University of Technology Anhui 230009 China The School of Data Science School of Computer Science and Technology University of Science and Technology of China Anhui 230026 China The Hubei Key Laboratory of Optical Information and Pattern Recognition Wuhan Institute of Technology Hubei Wuhan430070 China

Attention mechanisms have significantly boosted the performance of video classification neural networks thanks to the utilization of perspective contexts. However, the current research on video attention generally focuses on adopting a specific aspect of contexts (e.g., channel, spatial/temporal, or global context) to refine the features and neglects their underlying correlation when computing attentions. This leads to incomplete context utilization and hence bears the weakness of limited performance improvement. To tackle the problem, this paper proposes an efficient attention-in-attention (AIA) method for element-wise feature refinement, which investigates the feasibility of inserting the channel context into the spatio-temporal attention learning module, referred to as CinST, and also its reverse variant, referred to as STinC. Specifically, we instantiate the video feature contexts as dynamics aggregated along a specific axis with global average and max pooling operations. The workflow of an AIA module is that the first attention block uses one kind of context information to guide the gating weights calculation of the second attention that targets at the other context. Moreover, all the computational operations in attention units act on the pooled dimension, which results in quite few computational cost increase ( Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

An intelligent clustering scheme based on whale optimization algorithm in flying ad hoc networks

学校读者我要写书评

暂无评论

Vehicular Communications 2024年 49卷

作者： Hosseinzadeh, Mehdi Tanveer, Jawad Alanazi, Faisal Aurangzeb, Khursheed Yousefpoor, Mohammad Sadegh Yousefpoor, Efat Darwesh, Aso Lee, Sang-Woong Rahmani, Amir Masoud Institute of Research and Development Duy Tan University Da Nang Viet Nam School of Medicine and Pharmacy Duy Tan University Da Nang Viet Nam Department of Computer Science and Engineering Sejong University Seoul 05006 South Korea Department of Electrical Engineering College of Engineering Prince Sattam bin Abdulaziz University Al-Kharj 11942 Saudi Arabia Department of Computer Engineering College of Computer and Information Sciences King Saud University P. O. Box 51178 Riyadh 11543 Saudi Arabia Center of Research and Strategic Studies Lebanese French University Kurdistan Region Iraq Department of Information Technology University of Human Development Kurdistan Region Sulaymaniyah Iraq Pattern Recognition and Machine Learning Lab Gachon University 1342 Seongnamdaero Sujeonggu Seongnam 13120 South Korea Future Technology Research Center National Yunlin University of Science and Technology Yunlin Taiwan

Due to the progress of unmanned aerial vehicles (UAVs), this new technology is widely applied in military and civilian areas. Multi-UAV networks are often known as flying ad hoc networks (FANETs). Due to these applications, FANET must ensure communication stability and have high scalability. These goals are achieved by presenting clustering techniques in FANETs. However, the characteristics of these networks, like high-mobility nodes, limited energy, and dynamic topology, have created great challenges in two important processes of clustering protocols, namely cluster construction and the selection of cluster heads. In this paper, an intelligent clustering scheme based on the whale optimization algorithm called ICW is suggested in flying ad hoc networks. Firstly, each UAV specifies its hello interval based on the lifespan of adjacent links to guarantee the adaptability of ICW to FANET. Then, a centralized clustering process is done using a whale optimization algorithm (WOA) to find the best cluster centers on the network. To determine the membership of each UAV in a cluster, ICW employs a new criterion, i.e. closeness ratio, so that each UAV joins a cluster with the best closeness ratio. In addition, the evaluation of each whale is carried out based on a fitness function, consisting of three components, namely the number of isolated clusters, the ratio of inter-cluster distance to intra-cluster distance, and cluster size. Then, a cluster head is selected for each cluster based on a score value. This score is dependent on the weighted sum of four metrics, namely remaining energy, the average link lifespan between each UAV and its neighbors, neighbor degree, and the average distance between each UAV and its neighbors. In the last step, two routing processes, namely intra-cluster routing and inter-cluster routing, are introduced in FANET. Then, the evaluation and implementation of ICW is performed through the NS2 simulator. After completing the simulation process, ICW i

关键词： Artificial Intelligence (AI) Clustering Flying ad hoc networks (FANETs) Nature-inspired algorithms Unmanned aerial vehicles (UAVs)