相关论文: CapStARE: Capsule-based Spatiotemporal Architectur…
Temporal Graph Neural Networks (TGNNs) are powerful models to capture temporal, structural, and contextual information on temporal graphs. The generated temporal node embeddings outperform other methods in many downstream tasks. Real-world…
The detection of acoustic scenes is a challenging problem in which environmental sound events must be detected from a given audio signal. This includes classifying the events as well as estimating their onset and offset times. We approach…
Spatial-Temporal Graph (STG) forecasting on large-scale networks has garnered significant attention. However, existing models predominantly focus on short-horizon predictions and suffer from notorious computational costs and memory…
The task of human pose estimation (HPE) deals with the ill-posed problem of estimating the 3D position of human joints directly from images and videos. In recent literature, most of the works tackle the problem mostly by using convolutional…
While zero-shot appearance-based 3D gaze estimation offers significant cost-efficiency by directly mapping RGB images to gaze vectors, its reliability in Human-Robot Interaction (HRI) settings remains uncertain. Existing benchmarks…
Category-agnostic pose estimation (CAPE) aims to localize keypoints on query images from arbitrary categories, using only a few annotated support examples for guidance. Recent approaches either treat keypoints as isolated entities or rely…
Eye Tracking (ET) can help to understand visual attention and cognitive processes in interactive environments. In attention tasks, distinguishing between relevant target objects and distractors is crucial for effective performance, yet the…
Gaze and face tracking algorithms have traditionally battled a compromise between computational complexity and accuracy; the most accurate neural net algorithms cannot be implemented in real time, but less complex real-time algorithms…
Purpose: Vision-based robot tool segmentation plays a fundamental role in surgical robots and downstream tasks. CaRTS, based on a complementary causal model, has shown promising performance in unseen counterfactual surgical environments in…
Deep neural networks, especially transformer-based architectures, have achieved remarkable success in semantic segmentation for environmental perception. However, existing models process video frames independently, thus failing to leverage…
Bird's-eye view (BEV) object detection has become important for advanced automotive 3D radar-based perception systems. However, the inherently sparse and non-deterministic nature of radar data limits the effectiveness of traditional…
Fine-grained human action recognition (FHAR) is challenging because visually similar actions differ by subtle spatio-temporal cues. Many recent systems enhance discriminability with extra modalities (e.g., pose, text, optical flow), but…
Using lightweight models as backbone networks in gaze estimation tasks often results in significant performance degradation. The main reason is that the number of feature channels in lightweight networks is usually small, which makes the…
Learning physically meaningful spatiotemporal representations from high-resolution multivariate Earth observation data is challenging due to strong local dynamics, long-range teleconnections, multi-scale interactions, and nonstationarity.…
Learning invariant representations has been the long-standing approach to self-supervised learning. However, recently progress has been made in preserving equivariant properties in representations, yet do so with highly prescribed…
Always-on egocentric cameras are increasingly used as demonstrations for embodied robotics, imitation learning, and assistive AR, but the resulting video streams are dominated by redundant and low-quality frames. Under the storage and…
Deep Neural Networks (DNNs) have been widely deployed for many Machine Learning applications. Recently, CapsuleNets have overtaken traditional DNNs, because of their improved generalization ability due to the multi-dimensional capsules, in…
Traffic flow prediction plays a critical role in the intelligent transportation system, and it is also a challenging task because of the underlying complex Spatio-temporal patterns and heterogeneities evolving across time. However, most…
Video prediction aims to predict future frames by modeling the complex spatiotemporal dynamics in videos. However, most of the existing methods only model the temporal information and the spatial information for videos in an independent…
EEG-based seizure detection models face challenges in terms of inference speed and memory efficiency, limiting their real-time implementation in clinical devices. This paper introduces a novel graph-based residual state update mechanism…