The video grounding(VG) task aims to locate the queried action or event in an untrimmed video based on rich linguistic descriptions. Existing proposal-free methods are trapped in the complex interaction between video ...
详细信息
The video grounding(VG) task aims to locate the queried action or event in an untrimmed video based on rich linguistic descriptions. Existing proposal-free methods are trapped in the complex interaction between video and query, overemphasizing cross-modal feature fusion and feature correlation for VG. In this paper, we propose a novel boundary regression paradigm that performs regression token learning in a transformer. Particularly, we present a simple but effective proposal-free framework, namely video grounding transformer(ViGT), which predicts the temporal boundary using a learnable regression token rather than multi-modal or cross-modal features. In ViGT, the benefits of a learnable token are manifested as follows.(1) The token is unrelated to the video or the query and avoids data bias toward the original video and query.(2) The token simultaneously performs global context aggregation from video and query ***, we employed a sharing feature encoder to project both video and query into a joint feature space before performing cross-modal co-attention(i.e., video-to-query attention and query-to-video attention) to highlight discriminative features in each modality. Furthermore, we concatenated a learnable regression token [REG] with the video and query features as the input of a vision-language transformer. Finally, we utilized the token [REG] to predict the target moment and visual features to constrain the foreground and background probabilities at each timestamp. The proposed ViGT performed well on three public datasets:ANet-Captions, TACoS, and YouCookⅡ. Extensive ablation studies and qualitative analysis further validated the interpretability of ViGT.
Space-Air-Ground integrated Vehicular Network(SAGVN)aims to achieve ubiquitous connectivity and provide abundant computational resources to enhance the performance and efficiency of the vehicular ***,there are still c...
详细信息
Space-Air-Ground integrated Vehicular Network(SAGVN)aims to achieve ubiquitous connectivity and provide abundant computational resources to enhance the performance and efficiency of the vehicular ***,there are still challenges to overcome,including the scheduling of multilayered computational resources and the scarcity of spectrum *** address these problems,we propose a joint Task Offloading(TO)and Resource Allocation(RA)strategy in SAGVN(namely JTRSS).This strategy establishes an SAGVN model that incorporates air and space networks to expand the options for vehicular TO,and enhances the edge-computing resources of the system by deploying edge *** minimize the system average cost,we use the JTRSS algorithm to decompose the original problem into a number of subproblems.A maximum rate matching algorithm is used to address the channel allocation and the Lagrangian multiplier method is employed for computational *** acquire the optimal TO decision,a differential fusion cuckoo search algorithm is *** simulation results demonstrate the significant superiority of the JTRSS algorithm in optimizing the system average cost.
A double low-density parity-check (D-LDPC) coding system was proposed in[1]as a typical joint source-channel coding(JSCC) scheme[1–5].In this system,two LDPC coding matrices perform source and channel coding,*** impo...
详细信息
A double low-density parity-check (D-LDPC) coding system was proposed in[1]as a typical joint source-channel coding(JSCC) scheme[1–5].In this system,two LDPC coding matrices perform source and channel coding,*** important concept in a D-LDPC coding system is the introduction of a linking matrix between the check nodes (CNs)of the source coding matrix and the variable nodes (VNs) of the channel LDPC coding matrix.
In order to achieve ultra-low emissions of SO_(2)and NO_(x),the oxygen blast furnace with sintering flue gas injection is presented as a promising novel *** CO_(2)emission was examined,and a cost analysis of the proce...
详细信息
In order to achieve ultra-low emissions of SO_(2)and NO_(x),the oxygen blast furnace with sintering flue gas injection is presented as a promising novel *** CO_(2)emission was examined,and a cost analysis of the process was *** results show that in the cases when the top gas is not circulated(Cases 1–3),and the volume of injected sintering flue gas per ton of hot metal is below about 1250 m^(3),the total CO_(2)emissions decrease first and then increase as the oxygen content of the blast *** the volume of injected sintering flue gas per ton of hot metal exceeds approximately 1250 m^(3),the total CO_(2)emissions gradually *** the recirculating top gas and the vacuum pressure swing adsorption are considered,the benefits of recovered gas can make the ironmaking cost close to or even lower than that of the ordinary blast ***,the implementation of this approach leads to a substantial reduction in total CO_(2)emissions,with reductions of 69.13%(Case 4),70.60%(Case 5),and 71.07%(Case 6),*** integrating previous research and current findings,the reasonable oxygen blast furnace with sintering flue gas injection can not only realize desulfurization and denitrification,but also achieve the goal of reducing CO_(2)emissions and ironmaking cost.
In this study, an adaptive neural network(NN) control is proposed for nonlinear two-degree-offreedom(2-DOF) helicopter systems considering the input constraints and global prescribed ***, radial basis function NN(RBFN...
详细信息
In this study, an adaptive neural network(NN) control is proposed for nonlinear two-degree-offreedom(2-DOF) helicopter systems considering the input constraints and global prescribed ***, radial basis function NN(RBFNN) is employed to estimate the unknown dynamics of the helicopter system. Second, a smooth nonaffine function is exploited to approximate and address nonlinear constraint functions. Subsequently, a new prescribed function is proposed, and an original constrained error is transformed into an equivalent unconstrained error using the error transformation and barrier function transformation methods. The analysis of the established Lyapunov function proves that the controlled system is globally uniformly bounded. Finally, the simulation and experimental results on a constructed Quanser's test platform verify the rationality and feasibility of the proposed control.
Epitaxy is the cornerstone of semiconductor technology, enabling the fabrication of single-crystal *** advancements in van der Waals(vd W) epitaxy have opened new avenues for producing wafer-scale single-crystal 2D ...
详细信息
Epitaxy is the cornerstone of semiconductor technology, enabling the fabrication of single-crystal *** advancements in van der Waals(vd W) epitaxy have opened new avenues for producing wafer-scale single-crystal 2D atomic crystals. However, when it comes to molecular crystals, the overall weak vd W force means that it is a significant challenge for small molecules to form a well-ordered structure during *** we demonstrate that the vd W epitaxy of Sb2O3molecular crystal, where the whole growth process is governed by vd W interactions, can be precisely controlled. The nucleation is deterministically modulated by epilayer–substrate interactions and unidirectional nuclei are realized through designing the lattice and symmetry matching between epilayer and substrate. Moreover, the growth and coalescence of nuclei as well as the layer-by-layer growth mode are kinetically realized via tackling the Schwoebel-Ehrlich barrier. Such precise control of vd W epitaxy enables the growth of single-crystal Sb2O3molecular film with desirable thickness. Using the ultrathin highly oriented Sb2O3film as a gate dielectric, we fabricated MoS2-based field-effect transistors that exhibit superior device performance. The results substantiate the viability of precisely managing molecule alignment in vd W epitaxy, paving the way for large-scale synthesis of single-crystal 2D molecular crystals.
To improve the quality of remote sensing images,a novel on-orbit attitude planning method for Earth observation imaging with star-based geometric calibration is presented in this *** traditional imaging processes,the ...
详细信息
To improve the quality of remote sensing images,a novel on-orbit attitude planning method for Earth observation imaging with star-based geometric calibration is presented in this *** traditional imaging processes,the proposed method includes both pre-calibration and post-calibration stages to enhance the accuracy of satellite geometric positioning.A multiple-constraint attitude planning algorithm was developed to ensure star-based calibration,wherein the satellite camera and star sensors simultaneously capture the images of *** integration of cameras and multiple star sensors enables effective attitude *** the Earth imaging stage,a fast on-orbit attitude planning algorithm was developed to determine the satellite attitude and the optimal imaging times for ground *** with existing methods,the fast on-orbit attitude planning algorithm can significantly reduce computational time and resource consumption via initial value selection and *** demonstrate the effectiveness of the proposed attitude planning method,which was successfully applied to Wuhan 1 satellite.
Detection of maneuvering small targets has always been an important yet challenging task for radar signal *** primary reason is that target variable motions within coherent processing interval generate energy migratio...
详细信息
Detection of maneuvering small targets has always been an important yet challenging task for radar signal *** primary reason is that target variable motions within coherent processing interval generate energy migrations across multiple resolution bins,which severely deteriorate the parameter estimation performance.A coarse-to-fine strategy for the detection of maneuvering small targets is *** of small points segmented coherently is performed first,and then an optimal inter-segment integration is utilized to derive the coarse estimation of the chirp *** fractional Fourier transform(FrFT)is then employed to refine the coarse estimation at a significantly reduced computational *** results verify the proposed scheme that achieves an efficient and reliable maneuvering target detection with-16dB input signal-to-noise ratio(SNR),while requires no exact a priori knowledge on the motion parameters.
It is a challenging task to create realistic 3D avatars that accurately replicate individuals' speech and unique talking styles for speech-driven facial animation. Existing techniques have made remarkable progress...
详细信息
It is a challenging task to create realistic 3D avatars that accurately replicate individuals' speech and unique talking styles for speech-driven facial animation. Existing techniques have made remarkable progress but still struggle to achieve lifelike mimicry. This paper proposes “TalkingStyle”, a novel method to generate personalized talking avatars while retaining the talking style of the person. Our approach uses a set of audio and animation samples from an individual to create new facial animations that closely resemble their specific talking style, synchronized with speech. We disentangle the style codes from the motion patterns, allowing our method to associate a distinct identifier with each person. To manage each aspect effectively, we employ three separate encoders for style, speech, and motion, ensuring the preservation of the original style while maintaining consistent motion in our stylized talking avatars. Additionally, we propose a new style-conditioned transformer decoder, offering greater flexibility and control over the facial avatar styles. We comprehensively evaluate TalkingStyle through qualitative and quantitative assessments, as well as user studies demonstrating its superior realism and lip synchronization accuracy compared to current state-of-the-art methods. To promote transparency and further advancements in the field, we also make the source code publicly available at https://***/wangxuanx/TalkingStyle. IEEE
Recent advances in organ transplantation,regenerative medicine,and drug discovery have emphasized the critical importance of effective preservation techniques for *** these advances,current preservation techniques hav...
详细信息
Recent advances in organ transplantation,regenerative medicine,and drug discovery have emphasized the critical importance of effective preservation techniques for *** these advances,current preservation techniques have significant limitations in maintaining the viability and functional efficacy of organs over the long *** a result,there is a pressing need to develop reliable and efficient preser-vation strategies for ***,the clinical standard for organ preservation involves the use of sta-tic cold storage and organ machine perfusion,but these methods can only preserve organs for a couple of days or even a few ***,the development of cryobiology has yielded promising *** this review,we aim to provide a comprehensive overview of the progression of organ preservation meth-ods,while emphasizing the limitations of traditional ***,we evaluate advanced preservation techniques for organs,including kidneys,livers,hearts,lungs,and ***,we share a progress perspective on the future of organ preservation,with the ultimate goal of achieving viable long-term preservation to address the pressing issue of organ shortage.
暂无评论