Filters








4,980 Hits in 4.0 sec

ERA: Entity Relationship Aware Video Summarization with Wasserstein GAN [article]

Guande Wu, Jianzhe Lin, Claudio T. Silva
2021 arXiv   pre-print
This paper proposes a novel Entity relationship Aware video summarization method (ERA) to address the above problems.  ...  We hope our straightforward yet effective approach will shed some light on the future research of unsupervised video summarization.  ...  Unsupervised Video Summarization Unsupervised video summarization methods learn a video summary with the absence of the ground-truth labels.  ... 
arXiv:2109.02625v1 fatcat:fb3muz3rofbnblgmtefgyrl3o4

Unsupervised Object-Level Video Summarization with Online Motion Auto-Encoder [article]

Yujia Zhang, Xiaodan Liang, Dingwen Zhang, Min Tan, Eric P. Xing
2018 arXiv   pre-print
It can be distinguished from existing pipelines in two aspects: extracting key motions of participated objects, and learning to summarize in an unsupervised and online manner.  ...  In this paper, we investigate a pioneer research direction towards the fine-grained unsupervised object-level video summarization.  ...  video summaries. • Unsupervised online dictionary learning.  ... 
arXiv:1801.00543v2 fatcat:ajsvozp6mzaztlbiskg6ymgc44

Query-Aware Sparse Coding for Multi-Video Summarization [article]

Zhong Ji, Yaru Ma, Yanwei Pang, Xuelong Li
2017 arXiv   pre-print
To provide a user-friendly summarization, this paper also develops an event-keyframe presentation structure to present keyframes in groups of specific events related to the query by using an unsupervised  ...  To this end, this paper proposes a novel query-aware approach by formulating the multi-video summarization in a sparse coding framework, where the web images searched by the query are taken as the important  ...  Fig. 5 . 5 The summarization presentation via a two-layer EKP structure.  ... 
arXiv:1707.04021v1 fatcat:ghzth6mjura33ninrnyjbio7ly

Exploiting Robust Unsupervised Video Person Re-identification [article]

Xianghao Zang, Ge Li, Wei Gao, Xiujun Shu
2021 arXiv   pre-print
To improve the performance stability for unsupervised video reID, this paper introduces a general scheme fusing part models and unsupervised learning.  ...  A local-aware module is employed to explore the poentials of local-level feature for unsupervised learning. A global-aware module is proposed to overcome the disadvantages of local-level features.  ...  The main contributions of this paper can be summarized as follows: • This paper introduces a robust part models-based scheme for unsupervised video reID, which makes it easier to explore the different  ... 
arXiv:2111.05170v2 fatcat:u4s6xx4cubdorgn2n4wblprtje

Learning Temporal Co-Attention Models for Unsupervised Video Action Localization

Guoqiang Gong, Xinghan Wang, Yadong Mu, Qi Tian
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Technically, our contributions are two-folds: 1) temporal co-attention models, either class-specific or classagnostic, learned from video-level labels or pseudo-labels in an iterative reinforced fashion  ...  of unique actions that appear in the video set is known.  ...  Each unlabeled untrimmed video is assigned with a pseudo action class label based on clustering results.  ... 
doi:10.1109/cvpr42600.2020.00984 dblp:conf/cvpr/GongWM020 fatcat:ot354qdmy5epniroy7hw7out6q

Video Summarization Using Deep Neural Networks: A Survey [article]

Evlampios Apostolidis, Eleni Adamantidou, Alexandros I. Metsai, Vasileios Mezaris, Ioannis Patras
2021 arXiv   pre-print
After presenting the motivation behind the development of technologies for video summarization, we formulate the video summarization task and discuss the main characteristics of a typical deep-learning-based  ...  This work focuses on the recent advances in the area and provides a comprehensive survey of the existing deep-learning-based methods for generic video summarization.  ...  Nevertheless, this machine learning framework has been widely used for unsupervised video summarization, as discussed in the following section. C. Unsupervised Video Summarization 1.  ... 
arXiv:2101.06072v2 fatcat:7mozntfhdrf3lkw6pwcr5v2rpu

Unsupervised Video Object Segmentation using Motion Saliency-Guided Spatio-Temporal Propagation [article]

Yuan-Ting Hu, Jia-Bin Huang, Alexander G. Schwing
2018 arXiv   pre-print
Unsupervised video segmentation plays an important role in a wide variety of applications from object identification to compression.  ...  To address these challenges for unsupervised video segmentation, we develop a novel saliency estimation technique as well as a novel neighborhood graph, based on optical flow and edge cues.  ...  Recently, deep learning based methods [25, 49, 48] were also used to address unsupervised video segmentation.  ... 
arXiv:1809.01125v1 fatcat:d6vwfn6ypfa5rd2b7gpggks5k4

A bottom-up summarization algorithm for videos in the wild

Gang Pan, Yaoxian Zheng, Rufei Zhang, Zhenjun Han, Di Sun, Xingming Qu
2019 EURASIP Journal on Advances in Signal Processing  
Video summarization aims to provide a compact video representation while preserving the essential activities of the original video.  ...  Several video summarizations results are presented in supplementary material.  ...  Supervised methods Departing from unsupervised methods, recent work formulates video summarization as a supervised learning problem. Gygli et al.  ... 
doi:10.1186/s13634-019-0611-y fatcat:wbhvecleqvh3delthkq27lsvzi

DeepQAMVS: Query-Aware Hierarchical Pointer Networks for Multi-Video Summarization [article]

Safa Messaoud, Ismini Lourentzou, Assma Boughoula, Mona Zehni, Zhizhen Zhao, Chengxiang Zhai, Alexander G. Schwing
2021 arXiv   pre-print
Query-aware multi-video summarization is a promising technique that caters to this demand.  ...  In this work, we introduce a novel Query-Aware Hierarchical Pointer Network for Multi-Video Summarization, termed DeepQAMVS, that jointly optimizes multiple criteria: (1) conciseness, (2) representativeness  ...  RELATED WORK We cover related work on single video summarization (SVS), multivideo summarization (MVS) and pointer networks (PN).  ... 
arXiv:2105.06441v1 fatcat:ep5qts5xjzdt3maqdfgik25qkm

Less Is More: Learning Highlight Detection From Video Duration

Bo Xiong, Yannis Kalantidis, Deepti Ghadiyaram, Kristen Grauman
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
We propose a scalable unsupervised solution that exploits video duration as an implicit supervision signal.  ...  In experiments on two challenging public video highlight detection benchmarks, our method substantially improves the state-of-the-art for unsupervised highlight detection.  ...  Learning with Noisy Labels: Our work is also related to learning from noisy data, a topic of broad interest in machine learning [25, 19] .  ... 
doi:10.1109/cvpr.2019.00135 dblp:conf/cvpr/XiongKGG19 fatcat:daaqnaq5vndqvctzy7pmmhseuq

Learning Video Object Segmentation from Unlabeled Videos [article]

Xiankai Lu, Wenguan Wang, Jianbing Shen, Yu-Wing Tai, David Crandall,, Steven C. H. Hoi
2020 arXiv   pre-print
We propose a new method for video object segmentation (VOS) that addresses object pattern learning from unlabeled videos, unlike most existing methods which rely heavily on extensive annotated data.  ...  We introduce a unified unsupervised/weakly supervised learning framework, called MuG, that comprehensively captures intrinsic properties of VOS at multiple granularities.  ...  Related Work 2.1. Video Object Segmentation Z-VOS.  ... 
arXiv:2003.05020v1 fatcat:qood45mzjfchleuq4p6gilq6ce

Graduated Assignment for Joint Multi-Graph Matching and Clustering with Application to Unsupervised Graph Matching Network Learning

Runzhong Wang, Junchi Yan, Xiaokang Yang
2020 Neural Information Processing Systems  
Our technique can be further utilized for end-to-end learning whose loss refers to the cross-entropy between two lines of matching pipelines, as such the keypoint feature extraction CNNs can be learned  ...  In this paper, we resort to a graduated assignment procedure for soft matching and clustering over iterations, whereby the two-way constraint and clustering confidence are modulated by two separate annealing  ...  Graduated Assignment Network with Unsupervised Learning We name the unsupervised learning pipeline as graduated assignment neural network (GANN) for both MGM and MGMC.  ... 
dblp:conf/nips/WangYY20 fatcat:o6nukeb7wre4tnpjt5mhfkrgs4

Diversity-Aware Multi-Video Summarization

Rameswar Panda, Niluthpol Chowdhury Mithun, Amit K. Roy-Chowdhury
2017 IEEE Transactions on Image Processing  
Most video summarization approaches have focused on extracting a summary from a single video; we propose an unsupervised framework for summarizing a collection of videos.  ...  We develop a novel diversity-aware sparse optimization method for multi-video summarization by exploring the complementarity within the videos.  ...  It is easy to see that problem (4) favors selection of interesting segments by assigning a lower score via Q (v) .  ... 
doi:10.1109/tip.2017.2708902 pmid:28574359 fatcat:wg5ghht3mnh65jylmt4kl3k3ry

Large-Scale Video Summarization Using Web-Image Priors

Aditya Khosla, Raffay Hamid, Chih-Jen Lin, Neel Sundaresan
2013 2013 IEEE Conference on Computer Vision and Pattern Recognition  
In this work, we apply our novel insight to develop a summarization algorithm that uses the web-image based prior information in an unsupervised manner.  ...  As these videos are generally of poor quality, summarization methods designed for well-produced videos do not generalize to them.  ...  Related Work Video summarization has been looked at from multiple perspectives [28] .  ... 
doi:10.1109/cvpr.2013.348 dblp:conf/cvpr/KhoslaHLS13 fatcat:sayh7chlxfg2za4ejxprft55y4

2020 Index IEEE Transactions on Circuits and Systems for Video Technology Vol. 30

2020 IEEE transactions on circuits and systems for video technology (Print)  
Chen, W., +, TCSVT Feb. 2020 334-348 Unsupervised learning Graph Interaction Networks for Relation Transfer in Human Activity Videos.  ...  ., +, TCSVT April 2020 929-943 Unsupervised Video Action Clustering via Motion-Scene Interaction Constraint.  ... 
doi:10.1109/tcsvt.2020.3043861 fatcat:s6z4wzp45vfflphgfcxh6x7npu
« Previous Showing results 1 — 15 out of 4,980 results