Safety equipment detection is an important application of object detection, receiving widespread attention in fields such as smart construction sites and video surveillance. Significant progress has been made in objec...
详细信息
Over-the-air computation(AirComp)enables federated learning(FL)to rapidly aggregate local models at the central server using waveform superposition property of wireless *** this paper,a robust transmission scheme for ...
详细信息
Over-the-air computation(AirComp)enables federated learning(FL)to rapidly aggregate local models at the central server using waveform superposition property of wireless *** this paper,a robust transmission scheme for an AirCompbased FL system with imperfect channel state information(CSI)is *** model CSI uncertainty,an expectation-based error model is *** main objective is to maximize the number of selected devices that meet mean-squared error(MSE)requirements for model broadcast and model *** problem is formulated as a combinatorial optimization problem and is solved in two ***,the priority order of devices is determined by a sparsity-inducing ***,a feasibility detection scheme is used to select the maximum number of devices to guarantee that the MSE requirements are *** alternating optimization(AO)scheme is used to transform the resulting nonconvex problem into two convex *** results illustrate the effectiveness and robustness of the proposed scheme.
Recently,Generative Adversarial Networks(GANs)have become the mainstream text-to-image(T2I)***,a standard normal distribution noise of inputs cannot provide sufficient information to synthesize an image that approache...
详细信息
Recently,Generative Adversarial Networks(GANs)have become the mainstream text-to-image(T2I)***,a standard normal distribution noise of inputs cannot provide sufficient information to synthesize an image that approaches the ground-truth image ***,the multistage generation strategy results in complex T2I ***,this study proposes a novel feature-grounded single-stage T2I model,which considers the“real”distribution learned from training images as one input and introduces a worst-case-optimized similarity measure into the loss function to enhance the model's generation *** results on two benchmark datasets demonstrate the competitive performance of the proposed model in terms of the Frechet inception distance and inception score compared to those of some classical and state-of-the-art models,showing the improved similarities among the generated image,text,and ground truth.
Multi-hop reasoning for incomplete Knowledge Graphs(KGs)demonstrates excellent interpretability with decent *** Learning(RL)based approaches formulate multi-hop reasoning as a typical sequential decision *** intractab...
详细信息
Multi-hop reasoning for incomplete Knowledge Graphs(KGs)demonstrates excellent interpretability with decent *** Learning(RL)based approaches formulate multi-hop reasoning as a typical sequential decision *** intractable shortcoming of multi-hop reasoning with RL is that sparse reward signals make performance *** mainstream methods apply heuristic reward functions to counter this ***,the inaccurate rewards caused by heuristic functions guide the agent to improper inference paths and unrelated object *** this end,we propose a novel adaptive Inverse Reinforcement Learning(IRL)framework for multi-hop reasoning,called AInvR.(1)To counter the missing and spurious paths,we replace the heuristic rule rewards with an adaptive rule reward learning mechanism based on agent’s inference trajectories;(2)to alleviate the impact of over-rewarded object entities misled by inaccurate reward shaping and rules,we propose an adaptive negative hit reward learning mechanism based on agent’s sampling strategy;(3)to further explore diverse paths and mitigate the influence of missing facts,we design a reward dropout mechanism to randomly mask and perturb reward parameters for the reward learning *** results on several benchmark knowledge graphs demonstrate that our method is more effective than existing multi-hop approaches.
As an important task in emotion analysis, Multimodal Emotion-Cause Pair Extraction in conversations (MECPE) aims to extract all the emotion-cause utterance pairs from a conversation. However, there are two shortcoming...
详细信息
As an important task in emotion analysis, Multimodal Emotion-Cause Pair Extraction in conversations (MECPE) aims to extract all the emotion-cause utterance pairs from a conversation. However, there are two shortcomings in the MECPE task: 1) it ignores emotion utterances whose causes cannot be located in the conversation but require contextualized inference;2) it fails to locate the exact causes that occur in vision or audio modalities beyond text. To address these issues, in this paper, we introduce a new task named Multimodal Emotion-Cause Pair Generation in Conversations (MECPG), which aims to identify the emotion utterances with their emotion categories and generate their corresponding causes in a conversation. To tackle the MECPG task, we construct a dataset based on a benchmark corpus for MECPE. We further propose a generative framework named MONICA, which jointly performs emotion recognition and emotion cause generation with a sequence-to-sequence model. Experiments on our annotated dataset show the superiority of MONICA over several competitive systems. Our dataset and source codes will be publicly released. IEEE
Deepfake-generated fake faces,commonly utilized in identity-related activities such as political propaganda,celebrity impersonations,evidence forgery,and familiar fraud,pose new societal *** current deepfake generator...
详细信息
Deepfake-generated fake faces,commonly utilized in identity-related activities such as political propaganda,celebrity impersonations,evidence forgery,and familiar fraud,pose new societal *** current deepfake generators strive for high realism in visual effects,they do not replicate biometric signals indicative of cardiac *** this gap,many researchers have developed detection methods focusing on biometric *** methods utilize classification networks to analyze both temporal and spectral domain features of the remote photoplethysmography(rPPG)signal,resulting in high detection ***,in the spectral analysis,existing approaches often only consider the power spectral density and neglect the amplitude spectrum—both crucial for assessing cardiac *** introduce a novel method that extracts rPPG signals from multiple regions of interest through remote photoplethysmography and processes them using Fast Fourier Transform(FFT).The resultant time-frequency domain signal samples are organized into matrices to create Matrix Visualization Heatmaps(MVHM),which are then utilized to train an image classification ***,we explored various combinations of time-frequency domain representations of rPPG signals and the impact of attention *** experimental results show that our algorithm achieves a remarkable detection accuracy of 99.22%in identifying fake videos,significantly outperforming mainstream algorithms and demonstrating the effectiveness of Fourier Transform and attention mechanisms in detecting fake faces.
Person identification is one of the most vital tasks for network security. People are more concerned about theirsecurity due to traditional passwords becoming weaker or leaking in various attacks. In recent decades, f...
详细信息
Person identification is one of the most vital tasks for network security. People are more concerned about theirsecurity due to traditional passwords becoming weaker or leaking in various attacks. In recent decades, fingerprintsand faces have been widely used for person identification, which has the risk of information leakage as a resultof reproducing fingers or faces by taking a snapshot. Recently, people have focused on creating an identifiablepattern, which will not be reproducible falsely by capturing psychological and behavioral information of a personusing vision and sensor-based techniques. In existing studies, most of the researchers used very complex patternsin this direction, which need special training and attention to remember the patterns and failed to capturethe psychological and behavioral information of a person properly. To overcome these problems, this researchdevised a novel dynamic hand gesture-based person identification system using a Leap Motion sensor. Thisstudy developed two hand gesture-based pattern datasets for performing the experiments, which contained morethan 500 samples, collected from 25 subjects. Various static and dynamic features were extracted from the handgeometry. Randomforest was used to measure feature importance using the Gini Index. Finally, the support vectormachinewas implemented for person identification and evaluate its performance using identification accuracy. Theexperimental results showed that the proposed system produced an identification accuracy of 99.8% for arbitraryhand gesture-based patterns and 99.6% for the same dynamic hand gesture-based patterns. This result indicatedthat the proposed system can be used for person identification in the field of security.
Federated learning (FL) is widely used in various fields because it can guarantee the privacy of the original data source. However, in data-sensitive fields such as Internet of Vehicles (IoV), insecure communication c...
详细信息
Federated learning (FL) is widely used in various fields because it can guarantee the privacy of the original data source. However, in data-sensitive fields such as Internet of Vehicles (IoV), insecure communication channels, semi-trusted RoadSide Unit (RSU), and collusion between vehicles and the RSU may lead to leakage of model parameters. Moreover, when aggregating data, since different vehicles usually have different computing resources, vehicles with relatively insufficient computing resources will affect the data aggregation efficiency. Therefore, in order to solve the privacy leakage problem and improve the data aggregation efficiency, this paper proposes a privacy-preserving data aggregation protocol for IoV with FL. Firstly, the protocol is designed based on methods such as shamir secret sharing scheme, pallier homomorphic encryption scheme and blinding factor protection, which can guarantee the privacy of model parameters. Secondly, the protocol improves the data aggregation efficiency by setting dynamic training time windows. Thirdly, the protocol reduces the frequent participations of Trusted Authority (TA) by optimizing the fault-tolerance mechanism. Finally, the security analysis proves that the proposed protocol is secure, and the performance analysis results also show that the proposed protocol has high computation and communication efficiency. IEEE
Cantonese opera, a key facet of Chinese traditional opera, boasts profound cultural and artistic value and has been designated as intangible cultural heritage. The use of certain roles is a basic concept in Cantonese ...
详细信息
Data hierarchy,as a hidden property of data structure,exists in a wide range of machine learning applications.A common practice to classify such hierarchical data is first to encode the data in the Euclidean space,and...
详细信息
Data hierarchy,as a hidden property of data structure,exists in a wide range of machine learning applications.A common practice to classify such hierarchical data is first to encode the data in the Euclidean space,and then train a Euclidean ***,such a paradigm leads to a performance drop due to distortion of data embedding in the Euclidean *** relieve this issue,hyperbolic geometry is investigated as an alternative space to encode the hierarchical data for its higher ability to capture the hierarchical *** methods cannot explore the full potential of the hyperbolic geometry,in the sense that such methods define the hyperbolic operations in the tangent plane,causing the distortion of data *** this paper,we develop two novel kernel formulations in the hyperbolic space,with one being positive definite(PD)and another one being indefinite,to solve the classification tasks in hyperbolic *** PD one is defined via mapping the hyperbolic data to the Drury-Arveson(DA)space,which is a special reproducing kernel Hilbert space(RKHS).To further increase the discrimination of the classifier,an indefinite kernel is further defined in the Krein ***,we design a 2-layer nested indefinite kernel which first maps hyperbolic data into the DA spaces,followed by a mapping from the DA spaces to the Krein *** experiments on real-world datasets demonstrate the superiority ofthe proposed kernels.
暂无评论