Person search aims at localizing and recognizing query persons from raw video frames, which is a combination of two sub-tasks, i.e., pedestrian detection and person re-identification. The dominant fashion is termed as...
详细信息
Person search aims at localizing and recognizing query persons from raw video frames, which is a combination of two sub-tasks, i.e., pedestrian detection and person re-identification. The dominant fashion is termed as the one-step person search that jointly optimizes detection and identification in a unified network, exhibiting higher efficiency. However, there remain major challenges: (i) conflicting objectives of multiple sub-tasks under the shared feature space, (ii) inconsistent memory bank caused by the limited batch size, (iii) underutilized unlabeled identities during the identification learning. To address these issues, we develop an enhanced decoupled and memory-reinforced network (DMRNet++). First, we simplify the standard tightly coupled pipelines and establish a task-decoupled framework (TDF). Second, we build a memory-reinforced mechanism (MRM), with a slow-moving average of the network to better encode the consistency of the memorized features. Third, considering the potential of unlabeled samples, we model the recognition process as semi-supervised learning. An unlabeled-aided contrastive loss (UCL) is developed to boost the identification feature learning by exploiting the aggregation of unlabeled identities. Experimentally, the proposed DMRNet++ obtains the mAP of 94.5% and 52.1% on CUHK-SYSU and PRW datasets, which exceeds most existing methods.
The interpretability of the convolutional neural networks(CNNs) has become a research hotspot. A popular explanation method is based on Class Activation Mapping (CAM), which visualizes the salient regions most relevan...
The interpretability of the convolutional neural networks(CNNs) has become a research hotspot. A popular explanation method is based on Class Activation Mapping (CAM), which visualizes the salient regions most relevant to neural network decisions. However, many CAM methods use the feature maps produced by the final convolution layer to generate the class activation maps, which usually have a low spatial resolution and can only generate coarse-grained visual explanations that provide a rough spatial location of the target object. In this paper, we propose a novel CAM method named Fusion-CAM. It improves traditional CAM methods by combining final class activation map containing semantic information with intermediate layer class activation maps containing fine-grained details, to generate fine-grained visual explanations with high faithfulness. In order to obtain high-quality intermediate layer class activation maps, we utilize Layer-wise Relevance Propagation (LRP) to obtain the weighting components of each channel of the intermediate layer feature maps, and the intermediate layer class activation maps generated by weighted summation are less noisy and have clear fine-grained details, which help to improve the quality of the final class activation map. Qualitative and quantitative experiments show that Fusion-CAM can be easily attached to different CAM methods to improve their performance.
image hashing is an efficient technique of imageprocessing for various applications, such as retrieval, copy detection and authentication. In this paper, we design a novel image hashing algorithm using LRSMD (low-ran...
详细信息
image hashing is an efficient technique of imageprocessing for various applications, such as retrieval, copy detection and authentication. In this paper, we design a novel image hashing algorithm using LRSMD (low-rank sparse matrix decomposition). Firstly, an input image is preprocessed by interpolation, Gaussian blur and color space conversion. Next, the preprocessed image is fed into the LRSMD for learning a low-rank matrix. Then, statistical features of non-overlapping blocks in the low-rank matrix are extracted. Finally, the hash code is obtained by calculating feature distances. Various experiments are done on public datasets to demonstrate the robustness and discrimination of the proposed algorithm. The results show that the proposed algorithm outperforms several advanced algorithms in balancing the performances of robustness and discrimination.
We present 3D Cinemagraphy, a new technique that marries 2D image animation with 3D photography. Given a single still image as input, our goal is to generate a video that contains both visual content animation and cam...
详细信息
ISBN:
(纸本)9798350301298
We present 3D Cinemagraphy, a new technique that marries 2D image animation with 3D photography. Given a single still image as input, our goal is to generate a video that contains both visual content animation and camera motion. We empirically find that naively combining existing 2D image animation and 3D photography methods leads to obvious artifacts or inconsistent animation. Our key insight is that representing and animating the scene in 3D space offers a natural solution to this task. To this end, we first convert the input image into feature-based layered depth images using predicted depth values, followed by unprojecting them to a feature point cloud. To animate the scene, we perform motion estimation and lift the 2D motion into the 3D scene flow. Finally, to resolve the problem of hole emergence as points move forward, we propose to bidirectionally displace the point cloud as per the scene flow and synthesize novel views by separately projecting them into target image planes and blending the results. Extensive experiments demonstrate the effectiveness of our method. A user study is also conducted to validate the compelling rendering results of our method.
Additive manufacturing(AM)has emerged as an advanced technique for the fabrication of complex near-net shaped and lightweight metallic parts with acceptable mechanical *** strength of AM metals has been confirmed comp...
详细信息
Additive manufacturing(AM)has emerged as an advanced technique for the fabrication of complex near-net shaped and lightweight metallic parts with acceptable mechanical *** strength of AM metals has been confirmed comparable or even superior to that of metals manufactured by conventional processes,but the fatigue performance is still a knotty issue that may hinder the substitution of currently used metallic components by AM counterparts when the cyclic loading and thus fatigue failure *** essential complements to high-cost and time-consuming experimental fatigue tests of AM metals,models for fatigue performance prediction are highly *** this review,different models for predicting the fatigue properties of AM metals are summarized in terms of fatigue life,fatigue limit and fatigue crack growth,with a focus on the incorporation of AM characteristics such as AM defect and processing parameters into the *** predicting the fatigue life of AM metals,empirical models and theoretical models(including local characteristic model,continuum damage mechanics model and probabilistic method)are *** terms of fatigue limit,the introduced models involve the Kitagawa–Takahashi model,the Murakami model,the El-Haddad model,*** modeling the fatigue crack growth of AM metals,the summarized methodologies include the Paris equation,the Hartman-Schijve equation,the NASGRO equation,the small-crack growth model,and numerical *** of these models for AM metals are similar to those for conventionally processed materials,but are modified and pay more attention to the AM ***,an outlook for possible directions of the modeling and prediction of fatigue properties of AM metals is provided.
Semi-supervised learning has garnered significant attention, particularly in medical image segmentation, owing to its capacity to leverage a large number of unlabeled data and a limited amount of labeled data to impro...
详细信息
Automatic image cropping algorithms aim to recompose images like human-being photographers by generating the cropping boxes with improved composition quality. Cropping box regression approaches learn the beauty of com...
详细信息
ISBN:
(纸本)9781577358800
Automatic image cropping algorithms aim to recompose images like human-being photographers by generating the cropping boxes with improved composition quality. Cropping box regression approaches learn the beauty of composition from annotated cropping boxes. However, the bias of annotations leads to quasi-trivial recomposing results, which has an obvious tendency to the average location of training samples. The crux of this predicament is that the task is naively treated as a box regression problem, where rare samples might be dominated by normal samples, and the composition patterns of rare samples are not well exploited. Observing that similar composition patterns tend to be shared by the cropping boundaries annotated nearly, we argue to find the beauty of composition from the rare samples by clustering the samples with similar cropping boundary annotations, i.e., similar composition patterns. We propose a novel Contrastive Composition Clustering (C2C) to regularize the composition features by contrasting dynamically established similar and dissimilar pairs. In this way, common composition patterns of multiple images can be better summarized, which especially benefits the rare samples and endows our model with better generalizability to render nontrivial results. Extensive experimental results show the superiority of our model compared with prior arts.
This article proposes a multi-agent deep reinforce-ment learning algorithm to control a fleet of unmanned surface vessels (USVs) that encircle and capture sea targets. First, a simulation environment for USVs is estab...
详细信息
Two goals of multi-objective evolutionary algorithms are effectively improving their convergence and diversity and making the Pareto set evenly distributed and close to the real Pareto front. At present, the challenge...
详细信息
Two goals of multi-objective evolutionary algorithms are effectively improving their convergence and diversity and making the Pareto set evenly distributed and close to the real Pareto front. At present, the challenges to be solved by the multi-objective evolutionary algorithm are to improve the convergence and diversity of the algorithm, and how to better solve functions with complex PF and/or PS shapes. Therefore, this paper proposes a gray wolf optimization-based self-organizing fuzzy multi-objective evolutionary algorithm. Gray wolf optimization algorithm is used to optimize the initial weights of the self-organizing map network. New neighborhood relationships for individuals are built by self-organizing map, which can maintain the invariance of feature distribution and map the structural information of the current population into Pareto sets. Based on this neighborhood relationship, this paper uses the fuzzy differential evolution operator, which constructs a fuzzy inference system to dynamically adjust the weighting parameter in the differential operator, to generate a new initial solution, and the polynomial mutation operator to refine them. Boundary processing is then conducted. Experiments on 15 problems of GLT1-6 and WFG1-9 and the algorithm proposed in this paper achieve the best on 18 values. And the result shows that the convergence and diversity of the proposed algorithm are better than several state-of-the-art multi-objective evolutionary algorithms.
In this paper, the problem of guarding a circular area is proposed and solved using a Stackelberg differential game theoretic approach. The objective of the attacker is to breach the perimeter of the defended area, wh...
详细信息
In this paper, the problem of guarding a circular area is proposed and solved using a Stackelberg differential game theoretic approach. The objective of the attacker is to breach the perimeter of the defended area, while the defenders endeavor to thwart such attempts. The dynamics of the attack-defense game are modeled according to the distance and position relations among defenders, attackers, and the center of defense area. The optimal Stackelberg equilibrium control strategies for both defenders and attackers are designed to guarantee the defense mission's success. Then, the effectiveness of the proposed method is validated through numerical simulation.
暂无评论