Related papers: StableNet: Semi-Online, Multi-Scale Deep Video Sta…
Generative Flow Networks (GFlowNets) learn to sample states proportional to an unnormalized reward. Despite their theoretical promise, practical training is often unstable, exhibiting severe loss spikes and mode collapse. To tackle this, we…
Modeling the processing chain that has produced a video is a difficult reverse engineering task, even when the camera is available. This makes model based video processing a still more complex task. In this paper we propose a fully blind…
Training instability in modern deep learning systems is frequently triggered by rare but extreme gradient-norm spikes, which can induce oversized parameter updates, corrupt optimizer state, and lead to slow recovery or divergence. Widely…
Denoising is a crucial step in many video processing pipelines such as in interactive editing, where high quality, speed, and user control are essential. While recent approaches achieve significant improvements in denoising quality by…
Video deblurring is essential task for autonomous driving, facial recognition, and security surveillance. Traditional methods directly estimate motion blur kernels, often introducing artifacts and leading to poor results. Recent approaches…
Cycling is a promising sustainable mode for commuting and leisure in cities, however, the fear of getting hit or fall reduces its wide expansion as a commuting mode. In this paper, we introduce a novel method called CyclingNet for detecting…
While flow matching is elegant, its reliance on single-sample conditional velocities leads to high-variance training targets that destabilize optimization and slow convergence. By explicitly characterizing this variance, we identify 1) a…
Due to the widespread use of smartphones with high-quality digital cameras and easy access to a wide range of software apps for recording, editing, and sharing videos and images, as well as the deep learning AI platforms, a new phenomenon…
A Recurrent Neural Network (RNN) for Video Super Resolution (VSR) is generally trained with randomly clipped and cropped short videos extracted from original training videos due to various challenges in learning RNNs. However, since this…
Intuitive user interfaces are indispensable to interact with the human centric smart environments. In this paper, we propose a unified framework that recognizes both static and dynamic gestures, using simple RGB vision (without depth…
The purpose of this paper is the detection of salient areas in natural video by using the new deep learning techniques. Salient patches in video frames are predicted first. Then the predicted visual fixation maps are built upon them. We…
This review article surveys the current progresses made toward video-based anomaly detection. We address the most fundamental aspect for video anomaly detection, that is, video feature representation. Much research works have been done in…
The design of deep learning methods for low light video enhancement remains a challenging problem owing to the difficulty in capturing low light and ground truth video pairs. This is particularly hard in the context of dynamic scenes or…
State-of-the-art video deblurring methods are capable of removing non-uniform blur caused by unwanted camera shake and/or object motion in dynamic scenes. However, most existing methods are based on batch processing and thus need access to…
In video compression, most of the existing deep learning approaches concentrate on the visual quality of a single frame, while ignoring the useful priors as well as the temporal information of adjacent frames. In this paper, we propose a…
High-Definition (HD) maps are essential for the safety of autonomous driving systems. While existing techniques employ camera images and onboard sensors to generate vectorized high-precision maps, they are constrained by their reliance on…
While video streaming algorithms are a hot research area, with interesting new approaches proposed every few months, little is known about the behavior of the streaming algorithms deployed across large online streaming platforms that…
When analyzing human motion videos, the output jitters from existing pose estimators are highly-unbalanced with varied estimation errors across frames. Most frames in a video are relatively easy to estimate and only suffer from slight…
It has been shown that perfectly trained networks exhibit drastic reduction in performance when presented with distorted images. Streaming Network (STNet) is a novel architecture capable of robust classification of the distorted images…
Temporal consistency is the key challenge of video depth estimation. Previous works are based on additional optical flow or camera poses, which is time-consuming. By contrast, we derive consistency with less information. Since videos…