Related papers: Space-Time Attention with Shifted Non-Local Search
The task of semi-supervised video object segmentation (VOS) has been greatly advanced and state-of-the-art performance has been made by dense matching-based methods. The recent methods leverage space-time memory (STM) networks and learn to…
Local search has recently been applied to SMT problems over various arithmetic theories. Among these, nonlinear real arithmetic poses special challenges due to its uncountable solution space and potential need to solve higher-degree…
The attention mechanism provides a sequential prediction framework for learning spatial models with enhanced implicit temporal consistency. In this work, we show a systematic design (from 2D to 3D) for how conventional networks and other…
Recently, several Space-Time Memory based networks have shown that the object cues (e.g. video frames as well as the segmented object masks) from the past frames are useful for segmenting objects in the current frame. However, these methods…
The prediction step is a very important part of hybrid video codecs. In this contribution, a novel spatio-temporal prediction algorithm is introduced. For this, the prediction is carried out in two steps. Firstly, a preliminary temporal…
Video transformers have recently emerged as an effective alternative to convolutional networks for action classification. However, most prior video transformers adopt either global space-time attention or hand-defined strategies to compare…
Previous deep learning-based event denoising methods mostly suffer from poor interpretability and difficulty in real-time processing due to their complex architecture designs. In this paper, we propose window-based event denoising, which…
In this paper, we introduce spatial attention for refining the information in multi-direction neural beamformer for far-field automatic speech recognition. Previous approaches of neural beamformers with multiple look directions, such as the…
Existing state-of-the-art disparity estimation works mostly leverage the 4D concatenation volume and construct a very deep 3D convolution neural network (CNN) for disparity regression, which is inefficient due to the high memory consumption…
The captured images under low light conditions often suffer insufficient brightness and notorious noise. Hence, low-light image enhancement is a key challenging task in computer vision. A variety of methods have been proposed for this task,…
Precise boundary annotations of image regions can be crucial for downstream applications which rely on region-class semantics. Some document collections contain densely laid out, highly irregular and overlapping multi-class region instances…
We propose a novel attention model that can accurately attends to target objects of various scales and shapes in images. The model is trained to gradually suppress irrelevant regions in an input image via a progressive attentive process…
3D point cloud segmentation has a wide range of applications in areas such as autonomous driving, augmented reality, virtual reality and digital twins. The point cloud data collected in real scenes often contain small objects and categories…
Video Denoising is one of the fundamental tasks of any videoprocessing pipeline. It is different from image denoising due to the tem-poral aspects of video frames, and any image denoising approach appliedto videos will result in flickering.…
Many localization algorithms use a spatiotemporal window of sensory information in order to recognize spatial locations, and the length of this window is often a sensitive parameter that must be tuned to the specifics of the application.…
We propose a novel solution for semi-supervised video object segmentation. By the nature of the problem, available cues (e.g. video frame(s) with object masks) become richer with the intermediate predictions. However, the existing methods…
Video compression artifact reduction aims to recover high-quality videos from low-quality compressed videos. Most existing approaches use a single neighboring frame or a pair of neighboring frames (preceding and/or following the target…
This study addresses the challenge of performing visual localization in demanding conditions such as night-time scenarios, adverse weather, and seasonal changes. While many prior studies have focused on improving image-matching performance…
Modern Search Engine Results Pages (SERPs) present complex layouts where multiple elements compete for visibility. Attention modelling is crucial for optimising web design and computational advertising, whereas attention metrics can inform…
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…