相关论文: End-to-End Learning of Motion Representation for V…

Learning approaches have shown great success in the task of super-resolving an image given a low resolution input. Video super-resolution aims for exploiting additionally the information from multiple images. Typically, the images are…

Learning reliable motion representation between consecutive frames, such as optical flow, has proven to have great promotion to video understanding. However, the TV-L1 method, an effective optical flow solver, is time-consuming and…

The total variation (TV) flow generates a scale-space representation of an image based on the TV functional. This gradient flow observes desirable features for images, such as sharp edges and enables spectral, scale, and texture analysis.…

Even with the recent advances in convolutional neural networks (CNN) in various visual recognition tasks, the state-of-the-art action recognition system still relies on hand crafted motion feature such as optical flow to achieve the best…

In this work we explore the advantages of end-to-end learning of multilayer maps offered by feed forward neural-networks (FFNN) for learning and predicting dynamics from transient fluid flow data.While machine learning in general depends on…

Existing learning-based video compression methods still face challenges related to inaccurate motion estimates and inadequate motion compensation structures. These issues result in compression errors and a suboptimal rate-distortion…

The FlowNet demonstrated that optical flow estimation can be cast as a learning problem. However, the state of the art with regard to the quality of the flow has still been defined by traditional methods. Particularly on small displacements…

This paper proposes an end-to-end trainable network, SegFlow, for simultaneously predicting pixel-wise object segmentation and optical flow in videos. The proposed SegFlow has two branches where useful information of object segmentation and…

Event cameras are vision sensors that record asynchronous streams of per-pixel brightness changes, referred to as "events". They have appealing advantages over frame-based cameras for computer vision, including high temporal resolution,…

In this paper, we propose a convolutional layer inspired by optical flow algorithms to learn motion representations. Our representation flow layer is a fully-differentiable layer designed to capture the `flow' of any representation channel…

Long-form video understanding is essential for various applications such as video retrieval, summarizing, and question answering. Yet, traditional approaches demand substantial computing power and are often bottlenecked by GPU memory. To…

A great challenge in video-language (VidL) modeling lies in the disconnection between fixed video representations extracted from image/video understanding models and downstream VidL data. Recent studies try to mitigate this disconnection…

The recent success in deep learning has lead to various effective representation learning methods for videos. However, the current approaches for video representation require large amount of human labeled datasets for effective learning. We…

Deep learning has been demonstrated to achieve excellent results for image classification and object detection. However, the impact of deep learning on video analysis (e.g. action detection and recognition) has been limited due to…

End-to-end trained convolutional neural networks have led to a breakthrough in optical flow estimation. The most recent advances focus on improving the optical flow estimation by improving the architecture and setting a new benchmark on the…

Reading text from images remains challenging due to multi-orientation, perspective distortion and especially the curved nature of irregular text. Most of existing approaches attempt to solve the problem in two or multiple stages, which is…

Most of current Convolution Neural Network (CNN) based methods for optical flow estimation focus on learning optical flow on synthetic datasets with groundtruth, which is not practical. In this paper, we propose an unsupervised optical flow…

Many video enhancement algorithms rely on optical flow to register frames in a video sequence. Precise flow estimation is however intractable; and optical flow itself is often a sub-optimal representation for particular video processing…

Video super-resolution (SR) aims to generate a sequence of high-resolution (HR) frames with plausible and temporally consistent details from their low-resolution (LR) counterparts. The generation of accurate correspondence plays a…

From the frame/clip-level feature learning to the video-level representation building, deep learning methods in action recognition have developed rapidly in recent years. However, current methods suffer from the confusion caused by partial…