Related papers: SEA: State-Exchange Attention for High-Fidelity Ph…
Recently proposed fine-grained 3D visual grounding is an essential and challenging task, whose goal is to identify the 3D object referred by a natural language sentence from other distractive objects of the same category. Existing works…
Most GCN-based methods model interacting individuals as independent graphs, neglecting their inherent inter-dependencies. Although recent approaches utilize predefined interaction adjacency matrices to integrate participants, these matrices…
Computer use agents represent an emerging area in artificial intelligence, aiming to operate computers autonomously to fulfill user tasks, attracting significant attention from both industry and academia. However, the performance of…
Attention mechanisms, which enable a neural network to accurately focus on all the relevant elements of the input, have become an essential component to improve the performance of deep neural networks. There are mainly two attention…
This paper considers a Fluid Antenna (FA) system comprising a single-antenna transmitter that communicates with a receiver equipped with an FA array with $N$ ports. The transmitter is assumed to deploy any of the modulation schemes:…
In the post-deep learning era, the Transformer architecture has demonstrated its powerful performance across pre-trained big models and various downstream tasks. However, the enormous computational demands of this architecture have deterred…
We seek to enable classic processing of continuous ultra-sparse spatiotemporal data generated by event-based sensors with dense machine learning models. We propose a novel hybrid pipeline composed of asynchronous sensing and synchronous…
Attention mechanism has gained great success in vision recognition. Many works are devoted to improving the effectiveness of attention mechanism, which finely design the structure of the attention operator. These works need lots of…
In recent years, speech emotion recognition (SER) has been used in wide ranging applications, from healthcare to the commercial sector. In addition to signal processing approaches, methods for SER now also use deep learning techniques which…
Paradoxically, a Variational Autoencoder (VAE) could be pushed in two opposite directions, utilizing powerful decoder model for generating realistic images but collapsing the learned representation, or increasing regularization coefficient…
In healthcare, medical image segmentation is crucial for accurate disease diagnosis and the development of effective treatment strategies. Early detection can significantly aid in managing diseases and potentially prevent their progression.…
Since context modeling is critical for estimating depth from a single image, researchers put tremendous effort into obtaining global context. Many global manipulations are designed for traditional CNN-based architectures to overcome the…
Evaluating lesion progression and treatment response via longitudinal lesion tracking plays a critical role in clinical practice. Automated approaches for this task are motivated by prohibitive labor costs and time consumption when lesion…
Spiking Transformers have recently emerged as promising architectures for combining the efficiency of spiking neural networks with the representational power of self-attention. However, the lack of standardized implementations, evaluation…
This paper develops an accurate force control algorithm for series elastic actuators (SEAs) based on a novel force estimation scheme, called transmission force observer (TFOB). The proposed method is designed to improve an inferior force…
Simulating the dynamics of open quantum systems with spatial structure and external control is an important challenge in quantum information science. Classical numerical solvers for such systems require integrating coupled master and field…
In this paper, we introduce \texttt{IAFormer}, a novel Transformer-based architecture that efficiently integrates pairwise particle interactions through a dynamic sparse attention mechanism. \texttt{IAFormer} has two new mechanisms within…
Ensemble data from Earth system models has to be calibrated and post-processed. I propose a novel member-by-member post-processing approach with neural networks. I bridge ideas from ensemble data assimilation with self-attention, resulting…
Unsupervised Domain Adaptation (UDA) methods have been successful in reducing label dependency by minimizing the domain discrepancy between a labeled source domain and an unlabeled target domain. However, these methods face challenges when…
Transformers have achieved remarkable success in medical image analysis owing to their powerful capability to use flexible self-attention mechanism. However, due to lacking intrinsic inductive bias in modeling visual structural information,…