Related papers: A Comparative Study of Controllability, Explainabi…

Understanding the link between urban planning and commuting flows is crucial for guiding urban development and policymaking. This research, bridging computer science and urban studies, addresses the challenge of integrating these fields…

Various studies among side-channel attacks have tried to extract information through leakages from electronic devices to reach the instruction flow of some appliances. However, previous methods highly depend on the resolution of traced…

Helmet detection is crucial for advancing protection levels in public road traffic dynamics. This problem statement translates to an object detection task. Therefore, this paper compares recent You Only Look Once (YOLO) models in the…

Machine learning techniques have been applied to enhance turbulence modeling in recent years. However, the "black box" nature of most machine learning techniques poses significant interpretability challenges in improving turbulence models.…

Latent Diffusion Models (LDMs) have emerged as powerful generative models, known for delivering remarkable results under constrained computational resources. However, deploying LDMs on resource-limited devices remains a complex issue,…

Efficient computation in deep neural networks is crucial for real-time object detection. However, recent advancements primarily result from improved high-performing hardware rather than improving parameters and FLOP efficiency. This is…

This paper introduces Smooth-Distill, a novel self-distillation framework designed to simultaneously perform human activity recognition (HAR) and sensor placement detection using wearable sensor data. The proposed approach utilizes a…

Change detection plays a fundamental role in Earth observation for analyzing temporal iterations over time. However, recent studies have largely neglected the utilization of multimodal data that presents significant practical and technical…

While self-supervised representation learning (SSL) has received widespread attention from the community, recent research argue that its performance will suffer a cliff fall when the model size decreases. The current method mainly relies on…

Semantic Textual Similarity (STS) is a crucial component of many Natural Language Processing (NLP) applications. However, existing approaches typically reduce semantic nuances to a single score, limiting interpretability. To address this,…

This paper introduces StutterNet, a novel deep learning based stuttering detection capable of detecting and identifying various types of disfluencies. Most of the existing work in this domain uses automatic speech recognition (ASR) combined…

Existing approaches in disfluency detection focus on solving a token-level classification task for identifying and removing disfluencies in text. Moreover, most works focus on leveraging only contextual information captured by the linear…

Knowledge distillation has emerged as an effective strategy for compressing large language models' (LLMs) knowledge into smaller, more efficient student models. However, standard one-shot distillation methods often produce suboptimal…

This work analyzes trajectories obtained by YOLO and DeepSORT algorithms of dense emulsion systems simulated by Lattice Boltzmann methods. The results indicate that the individual droplet's moving direction is influenced more by the…

Knowledge distillation (KD) is a widely adopted and effective method for compressing models in object detection tasks. Particularly, feature-based distillation methods have shown remarkable performance. Existing approaches often ignore the…

Hardware acceleration in modern networks creates monitoring blind spots by offloading flows to a non-observable state, hindering real-time service degradation (SD) detection. To address this, we propose and formalize a novel inter-flow…

Autonomous driving requires the model to perceive the environment and (re)act within a low latency for safety. While past works ignore the inevitable changes in the environment after processing, streaming perception is proposed to jointly…

Outlier detection and concept drift detection represent two challenges in data analysis. Most studies address these issues separately. However, joint detection mechanisms in regression remain underexplored, where the continuous nature of…

Vision-language models (VLMs) could power real-time assistants and autonomous agents, but they face a critical challenge: understanding near-infinite video streams without escalating latency and memory usage. Processing entire videos with…

Explainability for Deep Learning Models is especially important for clinical applications, where decisions of automated systems have far-reaching consequences. While various post-hoc explainable methods, such as attention visualization and…