Filters








905 Hits in 3.7 sec

2020 Index IEEE Transactions on Image Processing Vol. 29

2020 IEEE Transactions on Image Processing  
., +, TIP 2020 6017-6031 Consistent Video Style Transfer via Relaxation and Regularization. Wang, W., +, TIP 2020 9125-9139 Constrained Design of Deep Iris Networks.  ...  Javed, S., +, TIP 2020 9204-9219 Cellular neural networks Hyperspectral Image Denoising via Matrix Factorization and Deep Prior Regularization.  ... 
doi:10.1109/tip.2020.3046056 fatcat:24m6k2elprf2nfmucbjzhvzk3m

Learning Deep Matrix Representations [article]

Kien Do, Truyen Tran, Svetha Venkatesh
2018 arXiv   pre-print
We also reinterpret existing models for (iii) memory-augmented networks and (iv) graphs using matrix notations.  ...  We present a new distributed representation in deep neural nets wherein the information is represented in native form as a matrix.  ...  consists of 1,965 face images of size 28 × 20, taken from sequential frames of a video.  ... 
arXiv:1703.01454v2 fatcat:otbrqkblzfasnkknoskkaljnse

Table of contents

2020 IEEE Transactions on Image Processing  
Hwang 4130 Point Cloud Denoising via Feature Graph Laplacian Regularization ........... C. Dinesh, G. Cheung, and I. V.  ...  Lu 1879 Graph Sequence Recurrent Neural Network for Vision-Based Freezing of Gait Detection ................................ ............................................................................  ... 
doi:10.1109/tip.2019.2940372 fatcat:h23ul2rqazbstcho46uv3lunku

Table of Contents

2020 IEEE Signal Processing Letters  
Zhang 1270 Graph Regularized Deep Discrete Hashing for Multi-Label Image Retrieval. . . . . . . .J. Wan, L. Niu, B. Bai, and H.  ...  Shi 2044 DMA Regularization: Enhancing Discriminability of Neural Networks by Decreasing the Minimal Angle . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ...  Huang 286 Temporal Localization of Non-Static Digital Videos Using the Electrical Network Frequency .  ... 
doi:10.1109/lsp.2020.3040844 fatcat:xpovskhrvfgctk3hhufuvpyyne

Layered Neural Rendering for Retiming People in Video [article]

Erika Lu, Forrester Cole, Tali Dekel, Weidi Xie, Andrew Zisserman, David Salesin, William T. Freeman, Michael Rubinstein
2021 arXiv   pre-print
We achieve these effects computationally via a dedicated learning-based layered video representation, where each frame in the video is decomposed into separate RGBA layers, representing the appearance  ...  of different people in the video.  ...  ACKNOWLEDGMENTS We thank the friends and family that appeared in our videos. The original Ballroom video belongs to Desert Classic Dance.  ... 
arXiv:2009.07833v2 fatcat:zgg5nx6ykrhmzjta5a27rpvvgy

Table of contents

2020 IEEE Transactions on Geoscience and Remote Sensing  
Gao 8766 Nonlocal Graph Convolutional Networks for Hyperspectral Image Classification ........................................... .......................................................................  ...  Bruzzone 8780 Topology-Enhanced Urban Road Extraction via a Geographic Feature-Enhanced Network ............................... .........................................................................  ... 
doi:10.1109/tgrs.2020.3034509 fatcat:zhasseasdzbdxd76xvo5ad53hq

Layered neural rendering for retiming people in video

Erika Lu, Forrester Cole, Tali Dekel, Weidi Xie, Andrew Zisserman, David Salesin, William T. Freeman, Michael Rubinstein
2020 ACM Transactions on Graphics  
Our method is based on a novel deep neural network that learns a layered decomposition of the input video (right).  ...  We achieve these effects computationally via a dedicated learning-based layered video representation, where each frame in the video is decomposed into separate RGBA layers, representing the appearance  ...  ACKNOWLEDGMENTS We thank the friends and family that appeared in our videos. The original Ballroom video belongs to Desert Classic Dance.  ... 
doi:10.1145/3414685.3417760 fatcat:pahhs3c26bhhvchbpuo7fdxiiu

Human Performance Modeling and Rendering via Neural Animated Mesh [article]

Fuqiang Zhao, Yuheng Jiang, Kaixin Yao, Jiakai Zhang, Liao Wang, Haizhao Dai, Yuhui Zhong, Yingliang Zhang, Minye Wu, Lan Xu, Jingyi Yu
2022 arXiv   pre-print
In this paper, we present a comprehensive neural approach for high-quality reconstruction, compression, and rendering of human performances from dense multi-view videos.  ...  We have recently seen tremendous progress in the neural advances for photo-real human modeling and rendering.  ...  Besides, we thank Bo Yang from ShanghaiTech University for producing a supplementary video.  ... 
arXiv:2209.08468v1 fatcat:udtujhyjpvdndhk24anrbxtfxi

2020 Index IEEE Signal Processing Letters Vol. 27

2020 IEEE Signal Processing Letters  
Lim, K., +, LSP 2020 231-235 DMA Regularization: Enhancing Discriminability of Neural Networks by Decreasing the Minimal Angle.  ...  ., +, LSP 2020 950-954 Lightweight Deep CNN for Natural Image Matting via Similarity-Preserving Knowledge Distillation.  ... 
doi:10.1109/lsp.2021.3055468 fatcat:wfdtkv6fmngihjdqultujzv4by

Robust High-Resolution Video Matting with Temporal Guidance [article]

Shanchuan Lin, Linjie Yang, Imran Saleemi, Soumyadip Sengupta
2021 arXiv   pre-print
Furthermore, we propose a novel training strategy that enforces our network on both matting and segmentation objectives. This significantly improves our model's robustness.  ...  We introduce a robust, real-time, high-resolution human video matting method that achieves new state-of-the-art performance.  ...  Video matting. Very few neural matting methods are de- We argue that human matting tasks are closely related to signed for videos natively.  ... 
arXiv:2108.11515v1 fatcat:tasly6fuvfaotk25zlsqnjai3u

Deep learning based fence segmentation and removal from an image using a video sequence [article]

Sankaraganesh Jonna, Krishna K. Nakka, Rajiv R. Sahay
2016 arXiv   pre-print
Specifically, we use a pre-trained convolutional neural network to segment fence pixels from a single image.  ...  The knowledge of spatial locations of fences is used to subsequently estimate optical flow in the occluded frames of the video for the final data fusion step.  ...  Overfitting occurs in neural networks when the training data is limited.  ... 
arXiv:1609.07727v2 fatcat:ppur7ow7tjdwzkabfzj2swbm2m

2020 Index IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 42

2021 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Yu, H., +, TPAMI April 2020 956-973 Unsupervised Video Matting via Sparse and Low-Rank Representation.  ...  ., +, TPAMI June 2020 1317-1332 Local-Aggregation Graph Networks. Chang, J., +, TPAMI Nov. 2020 2874- 2886 Fuzzy set theory Neural Opacity Point Cloud.  ...  Object recognition Adversarial Action Prediction Networks. Kong, Y., +, TPAMI March 2020 539-553 Capturing the Geometry of Object Categories from Video Supervision.  ... 
doi:10.1109/tpami.2020.3036557 fatcat:3j6s2l53x5eqxnlsptsgbjeebe

Learned Video Compression [article]

Oren Rippel, Sanjay Nair, Carissa Lew, Steve Branson, Alexander G. Anderson, Lubomir Bourdev
2018 arXiv   pre-print
We present a new algorithm for video coding, learned end-to-end for the low-latency mode. In this setting, our approach outperforms all existing video codecs across nearly the entire bitrate range.  ...  On high-definition 1080p videos, H.265 and VP9 typically produce codes up to 20% larger, and H.264 up to 35% larger.  ...  The context consists of values of neighboring pre-transmitted bits, leveraging structure within and across bitplanes. Adaptive codelength regularization.  ... 
arXiv:1811.06981v1 fatcat:wgyznvwdcfcbjib4iqmje2yvau

Table of Contents

2019 2019 IEEE/CVF International Conference on Computer Vision (ICCV)  
Fashion Retrieval via Graph Reasoning Networks on a Similarity Pyramid 3066 Zhanghui Kuang (Sensetime Ltd.), Yiming Gao (Sun Yat-sen University), Guanbin Li (Sun Yat-sen University), Ping Luo (The Chinese  ...  UAB), Abel Gonzalez-Garcia (Computer Vision Center), Antonio Lopez (CVC & UAB), and Joost Weijer (Computer Vision Center) One-Shot Neural Architecture Search via Self-Evaluated Template Network 3680 Xuanyi  ... 
doi:10.1109/iccv.2019.00004 fatcat:5aouo4scprc75c7zetsimylj2y

Table of contents

2021 ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
NEURAL NETWORKS ........................................POWER ALLOCATION USING GRAPH NEURAL NETWORKS ................................. 4725 AND DEEP ALGORITHM UNFOLDING Arindam Chowdhury, Rice University  ...  , Ecole Normale Superieure Paris Saclay, France SPTM-12.6: ROBUST GRAPH-FILTER IDENTIFICATION WITH GRAPH DENOISING ................................... 5539 REGULARIZATION Samuel Rey, Antonio G.  ... 
doi:10.1109/icassp39728.2021.9414617 fatcat:m5ugnnuk7nacbd6jr6gv2lsfby
« Previous Showing results 1 — 15 out of 905 results