相关论文: STIP: A SpatioTemporal Information-Preserving and …

Effective and Efficient spatio-temporal modeling is essential for action recognition. Existing methods suffer from the trade-off between model performance and model complexity. In this paper, we present a novel Spatio-Temporal Hybrid…

Humans perceive and understand real-world spaces through a stream of visual observations. Therefore, the ability to streamingly maintain and update spatial evidence from potentially unbounded video streams is essential for spatial…

High level understanding of sequential visual input is important for safe and stable autonomy, especially in localization and object detection. While traditional object classification and tracking approaches are specifically designed to…

During and after a course of therapy, imaging is routinely used to monitor the disease progression and assess the treatment responses. Despite of its significance, reliably capturing and predicting the spatial-temporal anatomic changes from…

Spatiotemporal prediction over graphs (STPG) is challenging, because real-world data suffers from the Out-of-Distribution (OOD) generalization problem, where test data follow different distributions from training ones. To address this…

It is challenging to annotate large-scale datasets for supervised video shadow detection methods. Using a model trained on labeled images to the video frames directly may lead to high generalization error and temporal inconsistent results.…

Traffic forecasting in cellular networks is a challenging spatiotemporal prediction problem due to strong temporal dependencies, spatial heterogeneity across cells, and the need for scalability to large network deployments. Traditional…

Video Large Language Models (Video LLMs) incur high inference latency due to a large number of visual tokens provided to LLMs. To address this, training-free visual token pruning has emerged as a solution to reduce computational costs;…

The pursuit of higher compression efficiency continuously drives the advances of video coding technologies. Fundamentally, we wish to find better "predictions" or "priors" that are reconstructed previously to remove the signal dependency…

We propose an approach to learn spatio-temporal features in videos from intermediate visual representations we call "percepts" using Gated-Recurrent-Unit Recurrent Networks (GRUs).Our method relies on percepts that are extracted from all…

Referring Video Object Segmentation (RVOS) aims to segment target objects in videos based on natural language descriptions. However, fixed keyframe-based approaches that couple a vision language model with a separate propagation module…

We present STanHop-Net (Sparse Tandem Hopfield Network) for multivariate time series prediction with memory-enhanced capabilities. At the heart of our approach is STanHop, a novel Hopfield-based neural network block, which sparsely learns…

Spiking Neural Networks (SNNs), as one of the algorithmic models in neuromorphic computing, have gained a great deal of research attention owing to temporal information processing capability, low power consumption, and high biological…

Human perception is at the core of lossy video compression, with numerous approaches developed for perceptual quality assessment and improvement over the past two decades. In the determination of perceptual quality, different…

For neural video codec, it is critical, yet challenging, to design an efficient entropy model which can accurately predict the probability distribution of the quantized latent representation. However, most existing video codecs directly use…

Spatio-temporal graph neural networks (STGNNs) have gained popularity as a powerful tool for effectively modeling spatio-temporal dependencies in diverse real-world urban applications, including intelligent transportation and public safety.…

Although spatio-temporal graph neural networks have achieved great empirical success in handling multiple correlated time series, they may be impractical in some real-world scenarios due to a lack of sufficient high-quality training data.…

Video streaming applications have newly attracted a large number of participants in a distribution network. Traditional client-server based video streaming solutions sustain precious bandwidth provision rate on the server. Recently, several…

Spatio-temporal graphs such as traffic networks or gene regulatory systems present challenges for the existing deep learning methods due to the complexity of structural changes over time. To address these issues, we introduce…

Understanding the thickness and variability of internal ice layers in radar imagery is crucial for monitoring snow accumulation, assessing ice dynamics, and reducing uncertainties in climate models. Radar sensors, capable of penetrating…