Search

This paper presents a novel deep graph-based learning technique for speech emotion recognition which has been specifically tailored for energy efficient deployment within humanoid robots. Our methodology represents a fusion of scalable graph representations, rooted in the foundational principles of graph signal processing theories. By delving into the utilization of cycle or line graphs as fundamental constituents shaping a robust Graph Convolution Network (GCN)-based architecture, we propose an approach which allows the capture of relationships between speech signals to decode intricate emotional patterns and responses. Our methodology is validated and benchmarked against established databases such as IEMOCAP and MSP-IMPROV. Our model outperforms standard GCNs and prevalent deep graph architectures, demonstrating performance levels that align with state-of-the-art methodologies. Notably, our model achieves this feat while significantly reducing the number of learnable parameters, thereby increasing computational efficiency and bolstering its suitability for resource-constrained environments. This proposed energy-efficient graph-based hybrid learning methodology is applied towards multimodal emotion recognition within humanoid robots. Its capacity to deliver competitive performance while streamlining computational complexity and energy efficiency represents a novel approach in evolving emotion recognition systems, catering to diverse real-world applications where precision in emotion recognition within humanoid robots stands as a pivotal requisite. [ABSTRACT FROM AUTHOR]

A considerable amount of research on link prediction has recently been driven by missing relationships between knowledge graph entities and the problem of the incompleteness of knowledge graphs. Some recent studies have shown that convolutional neural networks based on knowledge embeddings are highly expressive and have good performance in link prediction. However, we found that the convolutional neural network (CNN)-based models do not handle the link between relations and entities well. For this reason, this paper proposes a link prediction model (LPM) based on feature mapping and bi-directional convolution. For the modeling of the task, an encoding layer–mapping layer–decoding layer structure is used. Among these layers, the encoding layer adopts a graph attention network to encode multi-hop triad information and obtains richer encoding of entities and relationships. The mapping layer can realize the mapping transformation between entities and relations and project the entity encoding in the space of relation encoding to capture the subtle connection between entities and relations. The decoding layer adopts bidirectional convolution to merge and decode the triples in a sequential inverse order, which makes the decoding layer model more advantageous in prediction. In addition, the decoding layer also adopts the r-drop training method to effectively reduce the distribution error generated by training between models and enhance the robustness of the model. Our experiments demonstrated the effectiveness of mapping relations, bidirectional convolution, and r-drop, and the accuracy of the proposed model showed significant improvements for each evaluation metric on two datasets, WN18RR and FB15k-237. [ABSTRACT FROM AUTHOR]

Given an observed low frame rate video, video frame interpolation (VFI) aims to generate a high frame rate video, which has smooth video frames with higher frames per second (FPS). Most existing VFI methods often focus on generating one frame at a specific timestep, e.g., 0.5, between every two frames, thus lacking the flexibility to increase the video's FPS by an arbitrary scale, e.g., 3. To better address this issue, in this paper, we propose an arbitrary timestep video frame interpolation (ATVFI) network with time-dependent decoding. Generally, the proposed ATVFI is an encoder–decoder architecture, where the interpolation timestep is an extra input added to the decoder network; this enables ATVFI to interpolate frames at arbitrary timesteps between input frames and to increase the video's FPS at any given scale. Moreover, we propose a data augmentation method, i.e., multi-width window sampling, where video frames can be split into training samples with multiple window widths, to better leverage training frames for arbitrary timestep interpolation. Extensive experiments were conducted to demonstrate the superiority of our model over existing baseline models on several testing datasets. Specifically, our model trained on the GoPro training set achieved 32.50 on the PSNR metric on the commonly used Vimeo90k testing set. [ABSTRACT FROM AUTHOR]