A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
UDVD uses deep learning to denoise videos without supervision.
Efficiently detects anomalies in videos with reduced computation.
Rolling Diffusion improves video prediction by progressively corrupting frames based on their temporal position.
Video classification is a challenging task in computer vision. Although Deep Neural Networks (DNNs) have achieved excellent performance in video classification, recent research shows adding imperceptible perturbations to clean videos can make the well-trained models output wrong labels with high confidence. In this pap…
New method tackles video inverse problems using image diffusion models.
Paper presents a new video generation model using diffusion probabilistic methods.
This work presents a novel approach for robust PCA with total variation regularization for foreground-background separation and denoising on noisy, moving camera video. Our proposed algorithm registers the raw (possibly corrupted) frames of a video and then jointly processes the registered frames to produce a decomposi…
In big data image/video analytics, we encounter the problem of learning an overcomplete dictionary for sparse representation from a large training dataset, which can not be processed at once because of storage and computational constraints. To tackle the problem of dictionary learning in such scenarios, we propose an a…
Sparsity and low-rank models have been popular for reconstructing images and videos from limited or corrupted measurements. Dictionary or transform learning methods are useful in applications such as denoising, inpainting, and medical image reconstruction. This paper proposes a framework for online (or time-sequential)…
Simplified explanation of DDPMs for machine learning.
We study \emph{TV regularization}, a widely used technique for eliciting structured sparsity. In particular, we propose efficient algorithms for computing prox-operators for -norm TV. The most important among these is -norm TV, for whose prox-operator we present a new geometric analysis which unveils a …
New method speeds up diffusion models without sacrificing quality.
Ground-A-Video edits videos without training, preserving intended changes.
Paper compares optimal denoising methods for generative models, finding different results based on data regularity.
CB-GLNs learn video data's complex dependencies via graph representation.
Efficiently learns deep factor graphs using Gaussian belief propagation.
RaMViD uses diffusion models for video prediction and infilling.
Current deep learning results on video generation are limited while there are only a few first results on video prediction and no relevant significant results on video completion. This is due to the severe ill-posedness inherent in these three problems. In this paper, we focus on human action videos, and propose a gene…
Paper improves video categorization using temporal coherence.
Improves video search by balancing text and visual modalities.
A new video prediction model treats videos as continuous processes, reducing sampling steps and improving efficiency.
SummaryNet automates video summarisation using deep learning.
Paper proposes SMFN for high-res spherical video super-resolution.
Unified method for simultaneous denoising and clustering.
Paper proposes new principles and framework for AVC learning from user-generated videos.
The extension of image generation to video generation turns out to be a very difficult task, since the temporal dimension of videos introduces an extra challenge during the generation process. Besides, due to the limitation of memory and training stability, the generation becomes increasingly challenging with the incre…
DDPD separates generation into planning and denoising for improved efficiency.
Recent advances in deep generative models have lead to remarkable progress in synthesizing high quality images. Following their successful application in image processing and representation learning, an important next step is to consider videos. Learning generative models of video is a much harder task, requiring a mod…
Lower-dimensional video discriminators improve GAN performance.
Improved self-supervised denoising for Poisson-Gaussian noise.
Conventional sequential learning methods such as Recurrent Neural Networks (RNNs) focus on interactions between consecutive inputs, i.e. first-order Markovian dependency. However, most of sequential data, as seen with videos, have complex temporal dependencies that imply variable-length semantic flows and their composi…
With the growth of user-generated content, we observe the constant rise of the number of companies, such as search engines, content aggregators, etc., that operate with tremendous amounts of web content not being the services hosting it. Thus, aiming to locate the most important content and promote it to the users, the…
We consider the problem of estimating a low-rank matrix from a noisy observed matrix. Previous work has shown that the optimal method depends crucially on the choice of loss function. In this paper, we use a family of weighted loss functions, which arise naturally for problems such as submatrix denoising, denoising wit…
Image denoising is an important pre-processing step in medical image analysis. Different algorithms have been proposed in past three decades with varying denoising performances. More recently, having outperformed all conventional methods, deep learning based models have shown a great promise. These methods are however …
Paper proposes graph-based separable transforms for video coding.
Total variation denoising improves image quality adaptively.
Jointly trains images and videos using residual vectors.
Finding compact representation of videos is an essential component in almost every problem related to video processing or understanding. In this paper, we propose a generative model to learn compact latent codes that can efficiently represent and reconstruct a video sequence from its missing or under-sampled measuremen…
Paper introduces adversarial lossy compression for video artifacts reduction.
Advanced video classification systems decode video frames to derive the necessary texture and motion representations for ingestion and analysis by spatio-temporal deep convolutional neural networks (CNNs). However, when considering visual Internet-of-Things applications, surveillance systems and semantic crawlers of la…
Gen-CUDE is a neural network for denoising noisy channels.
Generative models of natural images have progressed towards high fidelity samples by the strong leveraging of scale. We attempt to carry this success to the field of video modeling by showing that large Generative Adversarial Networks trained on the complex Kinetics-600 dataset are able to produce video samples of subs…
Human communication takes many forms, including speech, text and instructional videos. It typically has an underlying structure, with a starting point, ending, and certain objective steps between them. In this paper, we consider instructional videos where there are tens of millions of them on the Internet. We propose a…
GDiff tackles blind denoising with Gibbs sampling and Monte Carlo inference.
C3 compresses images and videos with low complexity and high performance.
Researchers create a flickering attack to fool video recognition networks.
AMS improves video inference on edge devices by adapting a small model with online knowledge distillation.
While it is believed that denoising is not always necessary in many big data applications, we show in this paper that denoising is helpful in urban traffic analysis by applying the method of bounded total variation denoising to the urban road traffic prediction and clustering problem. We propose two easy-to-implement m…