Related papers: Spectral Scalpel: Amplifying Adjacent Action Discr…
Spiking neural networks (SNNs) offer energy efficiency over artificial neural networks (ANNs) but suffer from high latency and computational overhead due to their multi-timestep operational nature. While various dynamic computation methods…
Investigating the spectral properties of the neural covariates that underlie spiking activity is an important problem in systems neuroscience, as it allows to study the role of brain rhythms in cognitive functions. While the spectral…
Hyperspectral images with high spectral resolution provide new insights into recognizing subtle differences in similar substances. However, object detection in hyperspectral images faces significant challenges in intra- and inter-class…
Skeleton-based temporal action segmentation is a fundamental yet challenging task, playing a crucial role in enabling intelligent systems to perceive and respond to human activities. While fully-supervised methods achieve satisfactory…
The dynamics of human skeletons have significant information for the task of action recognition. The similarity between trajectories of corresponding joints is an indicating feature of the same action, while this similarity may subject to…
Representation learning of the task-oriented attention while tracking instrument holds vast potential in image-guided robotic surgery. Incorporating cognitive ability to automate the camera control enables the surgeon to concentrate more on…
We introduce Adaptive Spectral Shaping, a data-driven framework for graph filtering that learns a reusable baseline spectral kernel and modulates it with a small set of Gaussian factors. The resulting multi-peak, multi-scale responses…
Spatiotemporal learning is challenging due to the intricate interplay between spatial and temporal dependencies, the high dimensionality of the data, and scalability constraints. These challenges are further amplified in scientific domains,…
In IoT based distributed network of cameras, real-time multi-camera video analytics is challenged by high bandwidth demands and redundant visual data, creating a fundamental tension where reducing data saves network overhead but can degrade…
Human skeleton joints are popular for action analysis since they can be easily extracted from videos to discard background noises. However, current skeleton representations do not fully benefit from machine learning with CNNs. We propose…
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…
Recent advances in Remote Sensing Foundation Models (RSFMs) have led to significant breakthroughs in the field. While many RSFMs have been pretrained with massive optical imagery, more multispectral/hyperspectral data remain lack of the…
Cross-subject generalization in EEG-based brain-computer interfaces (BCIs) remains challenging due to individual variability in neural signals. We investigate whether spectral representations offer more stable features for cross-subject…
Accurate segmentation of tumors and adjacent normal tissues in medical images is essential for surgical planning and tumor staging. Although foundation models generally perform well in segmentation tasks, they often struggle to focus on…
Spectral token mixers based on Fourier transforms provide an efficient way to model global interactions in visual feature maps. Existing designs often either apply filter-wise spectral responses along fixed channel axes, or learn adaptive…
Skeleton-based human action recognition has achieved a great interest in recent years, as skeleton data has been demonstrated to be robust to illumination changes, body scales, dynamic camera views, and complex background. Nevertheless, an…
Learning meaningful graphs from data plays important roles in many data mining and machine learning tasks, such as data representation and analysis, dimension reduction, data clustering, and visualization, etc. In this work, for the first…
Despite the recent progress of fully-supervised action segmentation techniques, the performance is still not fully satisfactory. One main challenge is the problem of spatiotemporal variations (e.g. different people may perform the same…
The self-supervised pretraining paradigm has achieved great success in learning 3D action representations for skeleton-based action recognition using contrastive learning. However, learning effective representations for skeleton-based…
Current state-of-the-art methods for skeleton-based temporal action segmentation are predominantly supervised and require annotated data, which is expensive to collect. In contrast, existing unsupervised temporal action segmentation methods…