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
In task offloading,the movement of vehicles causes the switching of connected RSUs and servers,which may lead to task offloading failure or high service *** this paper,we analyze the impact of vehicle movements on tas...
详细信息
In task offloading,the movement of vehicles causes the switching of connected RSUs and servers,which may lead to task offloading failure or high service *** this paper,we analyze the impact of vehicle movements on task offloading and reveal that data preparation time for task execution can be minimized via forward-looking ***,a Bi-LSTM-based model is proposed to predict the trajectories of *** service area is divided into several equal-sized *** the actual position of the vehicle and the predicted position by the model belong to the same grid,the prediction is considered correct,thereby reducing the difficulty of vehicle trajectory ***,we propose a scheduling strategy for delay optimization based on the vehicle trajectory *** the inevitable prediction error,we take some edge servers around the predicted area as candidate execution servers and the data required for task execution are backed up to these candidate servers,thereby reducing the impact of prediction deviations on task offloading and converting the modest increase of resource overheads into delay reduction in task *** results show that,compared with other classical schemes,the proposed strategy has lower average task offloading delays.
Connected and Autonomous Vehicles (CAVs) hold great promise to transform our current transportation system to a safer, more resilient and efficient Cyber Transportation System (CTS) that integrates advanced sensing, c...
详细信息
Federated learning is widely used to solve the problem of data decentralization and can provide privacy protectionfor data owners. However, since multiple participants are required in federated learning, this allows a...
详细信息
Federated learning is widely used to solve the problem of data decentralization and can provide privacy protectionfor data owners. However, since multiple participants are required in federated learning, this allows attackers tocompromise. Byzantine attacks pose great threats to federated learning. Byzantine attackers upload maliciouslycreated local models to the server to affect the prediction performance and training speed of the global model. Todefend against Byzantine attacks, we propose a Byzantine robust federated learning scheme based on backdoortriggers. In our scheme, backdoor triggers are embedded into benign data samples, and then malicious localmodels can be identified by the server according to its validation dataset. Furthermore, we calculate the adjustmentfactors of local models according to the parameters of their final layers, which are used to defend against datapoisoning-based Byzantine attacks. To further enhance the robustness of our scheme, each localmodel is weightedand aggregated according to the number of times it is identified as malicious. Relevant experimental data showthat our scheme is effective against Byzantine attacks in both independent identically distributed (IID) and nonindependentidentically distributed (non-IID) scenarios.
Palmprint recognition is an emerging biometrics technology that has attracted increasing attention in recent years. Many palmprint recognition methods have been proposed, including traditional methods and deep learnin...
详细信息
Palmprint recognition is an emerging biometrics technology that has attracted increasing attention in recent years. Many palmprint recognition methods have been proposed, including traditional methods and deep learning-based methods. Among the traditional methods, the methods based on directional features are mainstream because they have high recognition rates and are robust to illumination changes and small noises. However, to date, in these methods, the stability of the palmprint directional response has not been deeply studied. In this paper, we analyse the problem of directional response instability in palmprint recognition methods based on directional feature. We then propose a novel palmprint directional response stability measurement (DRSM) to judge the stability of the directional feature of each pixel. After filtering the palmprint image with the filter bank, we design DRSM according to the relationship between the maximum response value and other response values for each pixel. Using DRSM, we can judge those pixels with unstable directional response and use a specially designed encoding mode related to a specific method. We insert the DRSM mechanism into seven classical methods based on directional feature, and conduct many experiments on six public palmprint databases. The experimental results show that the DRSM mechanism can effectively improve the performance of these methods. In the field of palmprint recognition, this work is the first in-depth study on the stability of the palmprint directional response, so this paper has strong reference value for research on palmprint recognition methods based on directional features.
With continuous expansion of satellite applications,the requirements for satellite communication services,such as communication delay,transmission bandwidth,transmission power consumption,and communication coverage,ar...
详细信息
With continuous expansion of satellite applications,the requirements for satellite communication services,such as communication delay,transmission bandwidth,transmission power consumption,and communication coverage,are becoming *** paper first presents an overview of the current development status of Low Earth Orbit(LEO)satellite constellations,and then conducts a demand analysis for multi-satellite data transmission based on LEO satellite *** problem is described,and the challenges and difficulties of the problem are analyzed *** this basis,a multi-satellite data-transmission mathematical model is then *** classical heuristic allocating strategies on the features of the proposed model,with the reinforcement learning algorithm Deep Q-Network(DQN),a two-stage optimization framework based on heuristic and DQN is ***,by taking into account the spatial and temporal distribution characteristics of satellite and facility resources,a multi-satellite scheduling instance dataset is *** results validate the rationality and correctness of the DQN algorithm in solving the collaborative scheduling problem of multi-satellite data transmission.
The success of vision transformer demonstrates that the transformer structure is also suitable for various vision tasks, including high-level classification tasks and low-level dense prediction tasks. Salient object d...
详细信息
The growing dependence on deep learning models for medical diagnosis underscores the critical need for robust interpretability and transparency to instill trust and ensure responsible usage. This study investigates th...
详细信息
Since the preparation of labeled datafor training semantic segmentation networks of pointclouds is a time-consuming process, weakly supervisedapproaches have been introduced to learn fromonly a small fraction of data....
详细信息
Since the preparation of labeled datafor training semantic segmentation networks of pointclouds is a time-consuming process, weakly supervisedapproaches have been introduced to learn fromonly a small fraction of data. These methods aretypically based on learning with contrastive losses whileautomatically deriving per-point pseudo-labels from asparse set of user-annotated labels. In this paper, ourkey observation is that the selection of which samplesto annotate is as important as how these samplesare used for training. Thus, we introduce a methodfor weakly supervised segmentation of 3D scenes thatcombines self-training with active learning. Activelearning selects points for annotation that are likelyto result in improvements to the trained model, whileself-training makes efficient use of the user-providedlabels for learning the model. We demonstrate thatour approach leads to an effective method that providesimprovements in scene segmentation over previouswork and baselines, while requiring only a few userannotations.
The paper addresses the critical problem of application workflow offloading in a fog environment. Resource constrained mobile and Internet of Things devices may not possess specialized hardware to run complex workflow...
详细信息
暂无评论