Related papers: Learning Long-Range Action Representation by Two-S…
Human activity recognition (HAR) from inertial sensors is essential for ubiquitous computing, mobile health, and ambient intelligence. Conventional deep models such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs),…
Video event detection has become a cornerstone of modern sports analytics, powering automated performance evaluation, content generation, and tactical decision-making. Recent advances in deep learning have driven progress in related tasks…
Effectively constructing context information with long-term dependencies from video sequences is crucial for object tracking. However, the context length constructed by existing work is limited, only considering object information from…
Transformer-based methods have achieved remarkable performance in event-based object detection, owing to the global modeling ability. However, they neglect the influence of non-event and noisy regions and process them uniformly, leading to…
Motor imagery (MI) classification is key for brain-computer interfaces (BCIs). Until recent years, numerous models had been proposed, ranging from classical algorithms like Common Spatial Pattern (CSP) to deep learning models such as…
Mamba has demonstrated excellent performance in various time series forecasting tasks due to its superior selection mechanism. Nevertheless, conventional Mamba-based models encounter significant challenges in accurately predicting stock…
Deep learning models like Convolutional Neural Networks and transformers have shown impressive capabilities in speech verification, gaining considerable attention in the research community. However, CNN-based approaches struggle with…
A comprehensive understanding of molecular structures is important for the prediction of molecular ground-state conformation involving property information. Meanwhile, state space model (e.g., Mamba) has recently emerged as a promising…
Deep visual odometry has demonstrated great advancements by learning-to-optimize technology. This approach heavily relies on the visual matching across frames. However, ambiguous matching in challenging scenarios leads to significant errors…
Understanding the inter-relations and interactions between tasks is crucial for multi-task dense prediction. Existing methods predominantly utilize convolutional layers and attention mechanisms to explore task-level interactions. In this…
Transformers have become dominant in large-scale deep learning tasks across various domains, including text, 2D and 3D vision. However, the quadratic complexity of their attention mechanism limits their efficiency as the sequence length…
Multimodal Large Language Models (MLLMs) have shown strong performance in video understanding tasks. However, they continue to struggle with long-form videos because of an inefficient perception of temporal intervals. Unlike humans, who can…
Intelligent sports video analysis demands a comprehensive understanding of temporal context, from micro-level actions to macro-level game strategies. Existing end-to-end models often struggle with this temporal hierarchy, offering solutions…
Tooth segmentation is a pivotal step in modern digital dentistry, essential for applications across orthodontic diagnosis and treatment planning. Despite its importance, this process is fraught with challenges due to the high noise and low…
Temporal action localization is a recently-emerging task, aiming to localize video segments from untrimmed videos that contain specific actions. Despite the remarkable recent progress, most two-stage action localization methods still suffer…
While the Mamba architecture demonstrates superior inference efficiency and competitive performance on short-context natural language processing (NLP) tasks, empirical evidence suggests its capacity to comprehend long contexts is limited…
Emotion Recognition in Conversations (ERCs) is a vital area within multimodal interaction research, dedicated to accurately identifying and classifying the emotions expressed by speakers throughout a conversation. Traditional ERC approaches…
Sequential recommendation aims to estimate the dynamic user preferences and sequential dependencies among historical user behaviors. Although Transformer-based models have proven to be effective for sequential recommendation, they suffer…
Image restoration requires simultaneously preserving fine-grained local structures and maintaining long-range spatial coherence. While convolutional networks struggle with limited receptive fields, and Transformers incur quadratic…
Forecasting CPU performance, which involves estimating performance scores based on hardware characteristics during operation, is crucial for computational system design and resource management. This research field currently faces two…