English
Related papers

Related papers: Real-time Action Recognition with Enhanced Motion …

200 papers

Appearance and motion are two key components to depict and characterize the video content. Currently, the two-stream models have achieved state-of-the-art performances on video classification. However, extracting motion information,…

Computer Vision and Pattern Recognition · Computer Science 2019-06-24 Yongyi Tang , Lin Ma , Lianqiang Zhou

We introduce the concept of "dynamic image", a novel compact representation of videos useful for video analysis, particularly in combination with convolutional neural networks (CNNs). A dynamic image encodes temporal data such as RGB or…

Computer Vision and Pattern Recognition · Computer Science 2017-08-22 Hakan Bilen , Basura Fernando , Efstratios Gavves , Andrea Vedaldi

Human action recognition remains an important yet challenging task. This work proposes a novel action recognition system. It uses a novel Multiple View Region Adaptive Multi-resolution in time Depth Motion Map (MV-RAMDMM) formulation…

Computer Vision and Pattern Recognition · Computer Science 2019-04-15 Mahmoud Al-Faris , John P. Chiverton , Yanyan Yang , David L. Ndzi

Super-resolution (SR) techniques based on deep learning have recently emerged as a promising approach to enhance the spatial resolution of computational fluid dynamics simulations while containing computational cost. In this paper, we…

Fluid Dynamics · Physics 2026-04-13 Armin Sheidani , Michele Girfoglio , Annalisa Quaini , Gianluigi Rozza

Learning to represent videos is a very challenging task both algorithmically and computationally. Standard video CNN architectures have been designed by directly extending architectures devised for image understanding to include the time…

Computer Vision and Pattern Recognition · Computer Science 2020-05-28 Michael S. Ryoo , AJ Piergiovanni , Mingxing Tan , Anelia Angelova

Modern smart vision sensors need on-device intelligence to process video streams, as cloud computing is often impractical due to bandwidth, latency, and privacy constraints. However, these sensory systems typically rely on ultra-low-power…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Luca Bompani , Manuele Rusci , Luca Benini , Daniele Palossi , Francesco Conti

Object detection, one of the three main tasks of computer vision, has been used in various applications. The main process is to use deep neural networks to extract the features of an image and then use the features to identify the class and…

Computer Vision and Pattern Recognition · Computer Science 2022-12-14 Wenshuo Li

The state of the art in video understanding suffers from two problems: (1) The major part of reasoning is performed locally in the video, therefore, it misses important relationships within actions that span several seconds. (2) While there…

Computer Vision and Pattern Recognition · Computer Science 2018-05-08 Mohammadreza Zolfaghari , Kamaljeet Singh , Thomas Brox

Compressed video action recognition has recently drawn growing attention, since it remarkably reduces the storage and computational cost via replacing raw videos by sparsely sampled RGB frames and compressed motion cues (e.g., motion…

Computer Vision and Pattern Recognition · Computer Science 2025-10-06 Bing Li , Jiaxin Chen , Dongming Zhang , Xiuguo Bao , Di Huang

Extracting per-frame features using convolutional neural networks for real-time processing of video data is currently mainly performed on powerful GPU-accelerated workstations and compute clusters. However, there are many applications such…

Computer Vision and Pattern Recognition · Computer Science 2017-11-10 Lukas Cavigelli , Philippe Degen , Luca Benini

Standard video codecs rely on optical flow to guide inter-frame prediction: pixels from reference frames are moved via motion vectors to predict target video frames. We propose to learn binary motion codes that are encoded based on an input…

Image and Video Processing · Electrical Eng. & Systems 2019-12-12 André Nortje , Herman A. Engelbrecht , Herman Kamper

Dynamic scene understanding is one of the most conspicuous field of interest among computer vision community. In order to enhance dynamic scene understanding, pixel-wise segmentation with neural networks is widely accepted. The latest…

Computer Vision and Pattern Recognition · Computer Science 2024-02-15 Ge Shi , Zhili Yang

This paper introduces a novel methodology for generating fast and memory-efficient video continuations. Our method, dubbed FlowC2S, fine-tunes a pre-trained text-to-video flow model to learn a vector field between the current and succeeding…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Hovhannes Margaryan , Quentin Bammey , Christian Sandor

In this paper, we consider the task of unsupervised object discovery in videos. Previous works have shown promising results via processing optical flows to segment objects. However, taking flow as input brings about two drawbacks. First,…

Computer Vision and Pattern Recognition · Computer Science 2022-10-04 Shuangrui Ding , Weidi Xie , Yabo Chen , Rui Qian , Xiaopeng Zhang , Hongkai Xiong , Qi Tian

We investigate two crucial and closely related aspects of CNNs for optical flow estimation: models and training. First, we design a compact but effective CNN model, called PWC-Net, according to simple and well-established principles:…

Computer Vision and Pattern Recognition · Computer Science 2018-09-18 Deqing Sun , Xiaodong Yang , Ming-Yu Liu , Jan Kautz

Motion is a dominant cue in automated driving systems. Optical flow is typically computed to detect moving objects and to estimate depth using triangulation. In this paper, our motivation is to leverage the existing dense optical flow to…

Computer Vision and Pattern Recognition · Computer Science 2019-01-23 Hazem Rashed , Senthil Yogamani , Ahmad El-Sallab , Pavel Krizek , Mohamed El-Helw

In this paper, two simple principal component regression methods for estimating the optical flow between frames of video sequences according to a pel-recursive manner are introduced. These are easy alternatives to dealing with mixtures of…

Computer Vision and Pattern Recognition · Computer Science 2016-11-09 Felipe P. do Carmo , Vania Vieira Estrela , Joaquim Teixeira de Assis

In this paper, we propose an end-to-end 3D CNN for action detection and segmentation in videos. The proposed architecture is a unified deep network that is able to recognize and localize action based on 3D convolution features. A video is…

Computer Vision and Pattern Recognition · Computer Science 2017-12-05 Rui Hou , Chen Chen , Mubarak Shah

In this work, we propose a technique to convert CNN models for semantic segmentation of static images into CNNs for video data. We describe a warping method that can be used to augment existing architectures with very little extra…

Computer Vision and Pattern Recognition · Computer Science 2017-08-11 Raghudeep Gadde , Varun Jampani , Peter V. Gehler

Real-time and online action localization in a video is a critical yet highly challenging problem. Accurate action localization requires the utilization of both temporal and spatial information. Recent attempts achieve this by using…

Computer Vision and Pattern Recognition · Computer Science 2021-11-08 Kalana Abeywardena , Shechem Sumanthiran , Sakuna Jayasundara , Sachira Karunasena , Ranga Rodrigo , Peshala Jayasekara