scholarly journals Hierarchical Video Frame Sequence Representation with Deep Convolutional Graph Network

2019 ◽  
pp. 262-270 ◽  
Author(s):  
Feng Mao ◽  
Xiang Wu ◽  
Hui Xue ◽  
Rong Zhang
Keyword(s):  
Video Frame ◽  
Frame Sequence ◽  
Sequence Representation

Continuous Bidirectional Optical Flow for Video Frame Sequence Interpolation

2019 ◽  
Author(s):  
Donghao Gu ◽  
ZhaoJing Wen ◽  
Wenxue Cui ◽  
Rui Wang ◽  
Feng Jiang ◽  
...  
Keyword(s):  
Optical Flow ◽  
Video Frame ◽  
Frame Sequence

scholarly journals Learning Transferable Self-Attentive Representations for Action Recognition in Untrimmed Videos with Weak Supervision

2019 ◽  
Vol 33 ◽  
pp. 9227-9234 ◽  
Author(s):  
Xiao-Yu Zhang ◽  
Haichao Shi ◽  
Changsheng Li ◽  
Kai Zheng ◽  
Xiaobin Zhu ◽  
...  
Keyword(s):  
Action Recognition ◽  
Ground Truth ◽  
Classification Performance ◽  
Video Frame ◽  
Weak Supervision ◽  
The Past ◽  
Frame Sequence ◽  
Benchmark Datasets ◽  
Weakly Supervised ◽  
Action Frame

Action recognition in videos has attracted a lot of attention in the past decade. In order to learn robust models, previous methods usually assume videos are trimmed as short sequences and require ground-truth annotations of each video frame/sequence, which is quite costly and time-consuming. In this paper, given only video-level annotations, we propose a novel weakly supervised framework to simultaneously locate action frames as well as recognize actions in untrimmed videos. Our proposed framework consists of two major components. First, for action frame localization, we take advantage of the self-attention mechanism to weight each frame, such that the influence of background frames can be effectively eliminated. Second, considering that there are trimmed videos publicly available and also they contain useful information to leverage, we present an additional module to transfer the knowledge from trimmed videos for improving the classification performance in untrimmed ones. Extensive experiments are conducted on two benchmark datasets (i.e., THUMOS14 and ActivityNet1.3), and experimental results clearly corroborate the efficacy of our method.

Video-microscopic measurement of cell-substratum traction forces generated by locomoting keratocytes

1993 ◽  
Vol 51 ◽  
pp. 188-189
Author(s):  
Tim Oliver ◽  
Michelle Leonard ◽  
Juliet Lee ◽  
Akira Ishihara ◽  
Ken Jacobson
Keyword(s):  
Silicone Rubber ◽  
Molecular Motors ◽  
Video Frame ◽  
Traction Forces ◽  
Cell Traction Forces ◽  
Latex Beads ◽  
Cell Traction ◽  
Local Cell ◽  
Microscopic Measurement ◽  
Kinetics Of

We are using video-enhanced light microscopy to investigate the pattern and magnitude of forces that fish keratocytes exert on flexible silicone rubber substrata. Our goal is a clearer understanding of the way molecular motors acting through the cytoskeleton co-ordinate their efforts into locomotion at cell velocities up to 1 μm/sec. Cell traction forces were previously observed as wrinkles(Fig.l) in strong silicone rubber films by Harris.(l) These forces are now measureable by two independant means.In the first of these assays, weakly crosslinked films are made, into which latex beads have been embedded.(Fig.2) These films report local cell-mediated traction forces as bead displacements in the plane of the film(Fig.3), which recover when the applied force is released. Calibrated flexible glass microneedles are then used to reproduce the translation of individual beads. We estimate the force required to distort these films to be 0.5 mdyne/μm of bead movement. Video-frame analysis of bead trajectories is providing data on the relative localisation, dissipation and kinetics of traction forces.

Improved prediction of protein crystallization, purification and production propensity using hybrid sequence representation

2013 ◽  
Vol 999 (999) ◽  
pp. 1-6
Author(s):  
Jianzhao Gao ◽  
Gang Hu ◽  
Zhonghua Wu ◽  
Jishou Ruan ◽  
Shiyi Shen ◽  
...  
Keyword(s):  
Protein Crystallization ◽  
Hybrid Sequence ◽  
Sequence Representation

scholarly journals Robust Principal Component Analysis-Based Infrared Small Target Detection

2019 ◽  
Vol 33 ◽  
pp. 9925-9926
Author(s):  
Qiwei Chen ◽  
Cheng Wu ◽  
Yiming Wang
Keyword(s):  
Iteration Process ◽  
Principal Component ◽  
Component Analysis ◽  
Low Rank ◽  
Small Target ◽  
Frame Sequence ◽  
Augmented Lagrange Multiplier ◽  
Small Targets ◽  
Infrared Small Target ◽  
Augmented Lagrange Multiplier Method

A method based on Robust Principle Component Analysis (RPCA) technique is proposed to detect small targets in infrared images. Using the low rank characteristic of background and the sparse characteristic of target, the observed image is regarded as the sum of a low-rank background matrix and a sparse outlier matrix, and then the decomposition is solved by the RPCA. The infrared small target is extracted from the single-frame image or multi-frame sequence. In order to get more efficient algorithm, the iteration process in the augmented Lagrange multiplier method is improved. The simulation results show that the method can detect out the small target precisely and efficiently.

scholarly journals Driver Drowsiness Estimation Based on Factorized Bilinear Feature Fusion and a Long-Short-Term Recurrent Convolutional Network

Information ◽  
2020 ◽  
Vol 12 (1) ◽  
pp. 3
Author(s):  
Shuang Chen ◽  
Zengcai Wang ◽  
Wenxin Chen
Keyword(s):  
Short Term Memory ◽  
Feature Fusion ◽  
Detection Methods ◽  
Video Frame ◽  
Estimation Model ◽  
Short Term ◽  
Convolutional Network ◽  
Drowsiness Detection ◽  
Driver Drowsiness ◽  
Time Information

The effective detection of driver drowsiness is an important measure to prevent traffic accidents. Most existing drowsiness detection methods only use a single facial feature to identify fatigue status, ignoring the complex correlation between fatigue features and the time information of fatigue features, and this reduces the recognition accuracy. To solve these problems, we propose a driver sleepiness estimation model based on factorized bilinear feature fusion and a long- short-term recurrent convolutional network to detect driver drowsiness efficiently and accurately. The proposed framework includes three models: fatigue feature extraction, fatigue feature fusion, and driver drowsiness detection. First, we used a convolutional neural network (CNN) to effectively extract the deep representation of eye and mouth-related fatigue features from the face area detected in each video frame. Then, based on the factorized bilinear feature fusion model, we performed a nonlinear fusion of the deep feature representations of the eyes and mouth. Finally, we input a series of fused frame-level features into a long-short-term memory (LSTM) unit to obtain the time information of the features and used the softmax classifier to detect sleepiness. The proposed framework was evaluated with the National Tsing Hua University drowsy driver detection (NTHU-DDD) video dataset. The experimental results showed that this method had better stability and robustness compared with other methods.

scholarly journals Video Frame Interpolation via Deformable Separable Convolution

2020 ◽  
Vol 34 (07) ◽  
pp. 10607-10614 ◽  
Author(s):  
Xianhang Cheng ◽  
Zhenzhong Chen
Keyword(s):  
State Of The Art ◽  
Video Frame ◽  
Kernel Size ◽  
Frame Interpolation ◽  
Interpolation Methods ◽  
Video Frames ◽  
Convolution Process ◽  
Strong Performance ◽  
Existing Frames ◽  
Better Than

Learning to synthesize non-existing frames from the original consecutive video frames is a challenging task. Recent kernel-based interpolation methods predict pixels with a single convolution process to replace the dependency of optical flow. However, when scene motion is larger than the pre-defined kernel size, these methods yield poor results even though they take thousands of neighboring pixels into account. To solve this problem in this paper, we propose to use deformable separable convolution (DSepConv) to adaptively estimate kernels, offsets and masks to allow the network to obtain information with much fewer but more relevant pixels. In addition, we show that the kernel-based methods and conventional flow-based methods are specific instances of the proposed DSepConv. Experimental results demonstrate that our method significantly outperforms the other kernel-based interpolation methods and shows strong performance on par or even better than the state-of-the-art algorithms both qualitatively and quantitatively.

Auroral Sequence Representation and Classification Using Hidden Markov Models

2012 ◽  
Vol 50 (12) ◽  
pp. 5049-5060 ◽  
Author(s):  
Qiuju Yang ◽  
Jimin Liang ◽  
Zejun Hu ◽  
Heng Zhao
Keyword(s):  
Hidden Markov Models ◽  
Markov Models ◽  
Hidden Markov ◽  
Sequence Representation
Sign in / Sign up

Export Citation Format

Share Document