Related papers: Busy-Quiet Video Disentangling for Video Classific…
We propose a novel and general framework to disentangle video data into its dynamic motion and static content components. Our proposed method is a self-supervised pipeline with less assumptions and inductive biases than previous works: it…
State-of-the-art video deblurring methods use deep network architectures to recover sharpened video frames. Blurring especially degrades high-frequency (HF) information, yet this aspect is often overlooked by recent models that focus more…
Recent advances in single-frame object detection and segmentation techniques have motivated a wide range of works to extend these methods to process video streams. In this paper, we explore the idea of hard attention aimed for…
In this paper, we introduce Coarse-Fine Networks, a two-stream architecture which benefits from different abstractions of temporal resolution to learn better video representations for long-term motion. Traditional Video models process…
Indoor occupancy classification enables privacy-preserving monitoring in settings such as remote elder care, where presence information helps triage alarms without cameras or wearables. Radar suits this role by sensing motion through…
Recurrent neural networks (RNNs) have been used extensively and with increasing success to model various types of sequential data. Much of this progress has been achieved through devising recurrent units and architectures with the…
Video compression is a central feature of the modern internet powering technologies from social media to video conferencing. While video compression continues to mature, for many compression settings, quality loss is still noticeable. These…
Human action recognition has become one of the most active field of research in computer vision due to its wide range of applications, like surveillance, medical, industrial environments, smart homes, among others. Recently, deep learning…
Convolutional Neural Networks (CNNs) has been applied in numerous Internet of Things (IoT) devices for multifarious downstream tasks. However, with the increasing amount of data on edge devices, CNNs can hardly complete some tasks in time…
Understanding the real achievable performance of mobile ad hoc networks (MANETs) under practical network constraints is of great importance for their applications in future highly heterogeneous wireless network environments. This paper…
Video deblurring has achieved remarkable progress thanks to the success of deep neural networks. Most methods solve for the deblurring end-to-end with limited information propagation from the video sequence. However, different frame regions…
Quantized Neural Networks (QNNs), which use low bitwidth numbers for representing parameters and performing computations, have been proposed to reduce the computation complexity, storage size and memory usage. In QNNs, parameters and…
The defocus deblurring raised from the finite aperture size and exposure time is an essential problem in the computational photography. It is very challenging because the blur kernel is spatially varying and difficult to estimate by…
Multi-bit quantization networks enable flexible deployment of deep neural networks by supporting multiple precision levels within a single model. However, existing approaches suffer from significant training overhead as full-dataset updates…
Edge computing allows more computing tasks to take place on the decentralized nodes at the edge of networks. Today many delay sensitive, mission-critical applications can leverage these edge devices to reduce the time delay or even to…
This paper addresses the challenges of power flow calculation in large scale power systems with high renewable penetration, focusing on computational efficiency and generalization. Traditional methods, while accurate, struggle with…
Deep learning-based information processing consumes long time and requires huge computing resources, especially for dense prediction tasks which require an output for each pixel, like semantic segmentation and salient object detection.…
Recently developed generative methods, including invertible rescaling network (IRN) based and generative adversarial network (GAN) based methods, have demonstrated exceptional performance in image rescaling. However, IRN-based methods tend…
The application of machine learning models in quantum information theory has surged in recent years, driven by the recognition of entanglement and quantum states, which are the essence of this field. However, most of these studies rely on…
Very few available individual bandwidth reservation schemes provide efficient and cost-effective bandwidth reservation that is required for safety-critical and time-sensitive vehicular networked applications. These schemes allow vehicles to…