Related papers: Adaptive joint spatio-temporal error concealment f…
In magnetic-recording systems, consecutive sections experience different signal to noise ratios (SNRs). To perform error correction over these systems, one approach is to use an individual block code for each section. However, the…
Signal extrapolation is an important task in digital signal processing for extending known signals into unknown areas. The Selective Extrapolation is a very effective algorithm to achieve this. Thereby, the extrapolation is obtained by…
This paper introduces the concept of adaptive temporal compressive sensing (CS) for video. We propose a CS algorithm to adapt the compression ratio based on the scene's temporal complexity, computed from the compressed data, without…
Although the distributed machine learning methods can speed up the training of large deep neural networks, the communication cost has become the non-negligible bottleneck to constrain the performance. To address this challenge, the gradient…
Over the last decade, different technologies to visualize 3D scenes have been introduced and improved. These technologies include stereoscopic, multi-view, integral imaging and holographic types. Despite increasing consumer interest; poor…
Despite the success of deep learning for static image understanding, it remains unclear what are the most effective network architectures for the spatial-temporal modeling in videos. In this paper, in contrast to the existing CNN+RNN or…
By converting low-frame-rate, low-resolution videos into high-frame-rate, high-resolution ones, space-time video super-resolution techniques can enhance visual experiences and facilitate more efficient information dissemination. We propose…
Unsupervised multi-object scene decomposition is a fast-emerging problem in representation learning. Despite significant progress in static scenes, such models are unable to leverage important dynamic cues present in video. We propose a…
Video deblurring relies on leveraging information from other frames in the video sequence to restore the blurred regions in the current frame. Mainstream approaches employ bidirectional feature propagation, spatio-temporal transformers, or…
Recently, the spatial modulation (SM) technique has been proposed for visible light communication (VLC). This paper investigates the average symbol error rate (SER) for the VLC using adaptive spatial modulation (ASM). In the system, the…
Distributed stochastic gradient descent (SGD) is essential for scaling the machine learning algorithms to a large number of computing nodes. However, the infrastructures variability such as high communication delay or random node slowdown…
Long-range temporal alignment is critical yet challenging for video restoration tasks. Recently, some works attempt to divide the long-range alignment into several sub-alignments and handle them progressively. Although this operation is…
In this paper we address a fundamental question in communication, that is, in the presence of various noise scenarios such as white/colored Gaussian noise and impulsive -type noises, how to efficiently and accurately transmit a set of…
We consider two less-emphasized temporal properties of video: 1. Temporal cues are fine-grained; 2. Temporal modeling needs reasoning. To tackle both problems at once, we exploit approximated bilinear modules (ABMs) for temporal modeling.…
Fueled by recent advances of self-supervised models, pre-trained speech representations proved effective for the downstream speech emotion recognition (SER) task. Most prior works mainly focus on exploiting pre-trained representations and…
We explore spatiotemporal data augmentation using video foundation models to diversify both camera viewpoints and scene dynamics. Unlike existing approaches based on simple geometric transforms or appearance perturbations, our method…
Efficiently computing attention maps for videos is challenging due to the motion of objects between frames. While a standard non-local search is high-quality for a window surrounding each query point, the window's small size cannot…
Learning to synthesize high frame rate videos via interpolation requires large quantities of high frame rate training videos, which, however, are scarce, especially at high resolutions. Here, we propose unsupervised techniques to synthesize…
Surveying wide areas with only one camera is a typical scenario in surveillance and automotive applications. Ultra wide-angle fisheye cameras employed to that end produce video data with characteristics that differ significantly from…
Deep learning methods achieve remarkable predictive performance in modeling complex, large-scale data. However, assessing the quality of derived models has become increasingly challenging, as more classical statistical assumptions may no…