In one-stage methods for video moment retrieval,the common representations indirectly supervised by boundary prediction fail to fully preserve the inherent characteristic of the video and query,which limits the retrie...
详细信息
ISBN:
(数字)9789887581536
ISBN:
(纸本)9781665482561
In one-stage methods for video moment retrieval,the common representations indirectly supervised by boundary prediction fail to fully preserve the inherent characteristic of the video and query,which limits the retrieval *** solve this problem,an Adversarial Video Moment Retrieval(AVMR) algorithm is proposed to learn the common representations with modality invariance and cross-modal *** is implemented through the process of adversarial learning between a feature projector and a modality *** feature projector tries to generate a modality-invariant common representation and to confuse the modality *** modality classifier tries to discriminate between different modalities based on the generated representation by the feature *** triplet constraints are further imposed on the feature projector to preserve the underlying cross-modal semantic structure of *** experimental results show that AVMR surpasses the baseline Attentive Cross-modal Relevance Matching(ACRM) by 1.10% and 1.73% in the "mIoU" metric on two public datasets Charades-STA and TACoS,respectively.
A Multimodal Emotion Perception model with Audio and Visual modalities(MEP-AV) is proposed to detect the individual emotions in public *** framework of MEP-AV model consists of four parts,i.e.,data collection module,a...
详细信息
ISBN:
(数字)9789887581536
ISBN:
(纸本)9781665482561
A Multimodal Emotion Perception model with Audio and Visual modalities(MEP-AV) is proposed to detect the individual emotions in public *** framework of MEP-AV model consists of four parts,i.e.,data collection module,audio expression analysis module,visual expression analysis module and multimodal fusion *** order to ensure that the emotion perception results meet the requirement of short-term continuity,a Context-Aware Decision-Level Fusion(CADLF) model is proposed and applied in multimodal fusion *** CADLF model estimates the affective status by using context information of multimodal *** short-term continuity is considered to improve the accuracy of the emotion perception *** experiment results evaluated by various metrics demonstrate that the performance of the multimodal structure is improved compared with that of unimodal emotion *** MEP-AV model using multimodal fusion algorithm provides the accuracies of70.89% and 77.07% in valence and arousal *** F1-scores reaches 70.2% and 75.6% respectively,indicating the boost performance on emotion perception.
This paper is aimed at the second-order linear multi-agent formation *** to the failure of the actuator in a node,the wrong interactive information is transmitted between nodes,so that the entire system cannot complet...
详细信息
ISBN:
(数字)9789887581536
ISBN:
(纸本)9781665482561
This paper is aimed at the second-order linear multi-agent formation *** to the failure of the actuator in a node,the wrong interactive information is transmitted between nodes,so that the entire system cannot complete the expected task.A distributed adaptive fault isolation and fault tolerance method based on consistency theory is *** the consistency error variable is designed according to the connection relationship between nodes and the faulty node,which eliminates the influence of the faulty node on the neighbor ***,an overall distributed adaptive fault isolation and fault tolerance approach is designed according to the local information of neighbor *** stability of the designed approach is proved by constructing a reasonable Lyapunov *** results show that the proposed adaptive control approach has good robustness.
In recent years, underwater vehicle-manipulator systems(UVMSs) have captured researchers' attention. Inspired by fish, bionic mechanisms were introduced into a *** underwater biomimetic vehicle-manipulator system(...
详细信息
In recent years, underwater vehicle-manipulator systems(UVMSs) have captured researchers' attention. Inspired by fish, bionic mechanisms were introduced into a *** underwater biomimetic vehicle-manipulator system(UBVMS) is actuated by two symmetrically arranged biomimetic undulatory fin propulsors [1]. Based on the UBVMS, some topics have been researched, such as freefloating autonomous operation [2, 3], three-dimensional helical path following [4], and underwater video processing [5].
The inter-class similarity of facial expressions is one of the key challenges in Facial Expression Recognition(FER).In this manuscript,a Latent Facial Action Units Network(LAUNet) is proposed for the problem of inter-...
详细信息
ISBN:
(数字)9789887581536
ISBN:
(纸本)9781665482561
The inter-class similarity of facial expressions is one of the key challenges in Facial Expression Recognition(FER).In this manuscript,a Latent Facial Action Units Network(LAUNet) is proposed for the problem of inter-class similarity of facial expressions in *** proposed method recognizes subtle differences between facial expressions by learning Latent Facial Action Units Features(LAUFs).Specifically,LAUNet is composed of two parts:the Latent Facial Action Units Features Extraction Network(LEN) and the Latent Facial Action Units Selection Network(LSN).Firstly,LEN extracts LAUFs from the feature map of the backbone using the spatial attention ***,taking advantage of the channel attention mechanism,LSN captures the latent relationships between features from LAUFs to select effective features for *** are performed on the dataset after removing the invalid data of non-face images from the original FER2013 *** with some previous state-of-the-art methods,LAUNet achieves the highest accuracy rate of 71.31%.Depending on the backbone,LAUNet can improve the accuracy by up to 5.46% compared to the original architecture of the backbone.
As one of the most effective vehicles for ocean development and exploration,underwater gliding robots(UGRs)have the unique characteristics of low energy consumption and strong ***,by borrowing the motion principles of...
详细信息
As one of the most effective vehicles for ocean development and exploration,underwater gliding robots(UGRs)have the unique characteristics of low energy consumption and strong ***,by borrowing the motion principles of current underwater robots,a variety of novel UGRs have emerged with improving their maneuverability,concealment,and environmental friendliness,which significantly broadens the ocean *** this paper,we provide a comprehensive review of underwater gliding robots,including prototype design and their key *** the perspective of motion characteristics,we categorize the underwater gliding robots in terms of traditional underwater gliders(UGs),hybrid-driven UGs,bio-inspired UGs,thermal UGs,and ***,their buoyancy driven system,dynamic and energy model,and motion control are concluded with detailed ***,we have discussed the current critical issues and future *** review offers valuable insight into the development of next-generation underwater robots well-suited for various oceanic applications,and aims to gain more attention of researchers and engineers to this growing field.
The accurate prediction of behaviors of surrounding traffic participants is critical for autonomous vehicles (AV). How to fully encode both explicit (e.g., map structure and road geometry) and implicit scene context i...
详细信息
The accurate prediction of behaviors of surrounding traffic participants is critical for autonomous vehicles (AV). How to fully encode both explicit (e.g., map structure and road geometry) and implicit scene context information (e.g., traffic rules) within complex scenarios is still challenging. In this work, we propose an implicit scene context-aware trajectory prediction framework (the PRISC-Net, Prediction with Implicit Scene Context) for accurate and interactive behavior forecasting. The novelty of the proposed approach includes: 1) development of a behavior prediction framework that takes advantage of both model- and learning-based approaches to fully encode scene context information while modeling complex interactions;2) development of a candidate path target predictor that utilizes explicit and implicit scene context information for candidate path target prediction, along with a motion planning-based generator that generates kinematic feasible candidate trajectories;3) integration of the proposed target predictor and trajectory generator with a learning-based evaluator to capture complex agent-agent and agent-scene interactions and output accurate predictions. Experiment results based on vehicle behavior datasets and real-world road tests show that the proposed approaches outperform state-of-the-art methods in terms of prediction accuracy and scene context compliance. IEEE
Smart soft dielectric elastomer actuators(SSDEAs)possess wide applications in soft robotics due to their properties similar to natural muscles,including large deformation ratio,high energy density,and fast response **...
详细信息
Smart soft dielectric elastomer actuators(SSDEAs)possess wide applications in soft robotics due to their properties similar to natural muscles,including large deformation ratio,high energy density,and fast response ***,the complicated asymmetric and rate-dependent hysteresis property,creep property and quadratic input property of the SSDEA pose enormous challenges to its dynamic modeling and motion *** this paper,first,we construct the dynamic model of the SSDEA by connecting a square module,a one-sided Prandtl–Ishlinskii(OSPI)model and a linear system in series to describe the above *** key and innovative aspect of the dynamic modeling lies in cascading the square module in series with the OSPI model to construct the asymmetric hysteresis ***,a PI-funnel and inverse hysteresis compensation(PIFIHC)cascade control method of the SSDEA is proposed to actualize its tracking control *** performing the inversion operation on the asymmetric hysteresis model,the inverse hysteresis compensation controller(IHCC)is designed to compensate the asymmetric hysteresis property and quadratic input property of the *** addition,a PI-funnel controller is designed to cascade with the IHCC to construct the PIFIHC cascade controller to obtain a good tracking ***,the stability analysis of the PIFIHC cascade control system of the SSDEA is performed to theoretically prove that the tracking error can be controlled within the performance funnel and the steady-state error converges to ***,several practical tracking control experiments of the SSDEA are conducted,and RRMSEs are less than 2.30%for all *** experimental results indicate the effectiveness and feasibility of the proposed PIFIHC cascade control method of the SSDEA.
Automating complex industrial robots requires precise nonlinear control and efficient energy management. This paper introduces a data-driven nonlinear model predictive control (NMPC) framework to optimize control unde...
详细信息
We present a highly synchronized multi-view hardware acquisition system that simultaneously enables real-time multi-person pose estimation. We design a hardware synchronizer to achieve multi camera synchronous shootin...
详细信息
ISBN:
(数字)9798350379228
ISBN:
(纸本)9798350390780
We present a highly synchronized multi-view hardware acquisition system that simultaneously enables real-time multi-person pose estimation. We design a hardware synchronizer to achieve multi camera synchronous shooting, with a synchronization latency rate of only 10
−8
seconds. Based on this, we construct a multi-view hardware synchronous acquisition system. This system can be flexibly deployed in various environments to capture moving targets, such as bodies, clothing, hands, etc. Leveraging the distributed computing capabilities of the system, we further develop a multi-view multi-person pose estimation algorithm framework that fulfills real-time requirements and achieves an average frame rate of 40FPS in experimental settings while demonstrating robustness against human motion and occlusion.
暂无评论