A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Filters
Two-person interaction recognition via spatial multiple instance embedding
2015
Journal of Visual Communication and Image Representation
Preserved Fulltext
Experimental results on two benchmark datasets validate that using two-person visual descriptors together with spatial multiple instance learning offers an effective way for inferring the type of the interaction ...
Our method integrates multiple visual features in a weakly supervised manner by utilizing an embedding-based multiple instance learning framework. ...
Conclusion In this study, we propose a multiple instance learning (MIL) based approach for two-person interaction recognition in videos. ...
doi:10.1016/j.jvcir.2015.07.016
fatcat:hq6dq2hs55gdjkv6hc4onqxzt4
Domain-Adaptive Discriminative One-Shot Learning of Gestures
[chapter]
2014
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
The objective of this paper is to recognize gestures in videos -both localizing the gesture and classifying it into one of multiple classes. ...
The domain adaptation and learning methods are evaluated on two large scale challenging gesture datasets: one for sign language, and the other for Italian hand gestures. ...
Acknowledgements: We are grateful to Patrick Buehler and Sophia Pfister for help and discussions. Financial support was provided by Osk. Huttunen Foundation and EPSRC grant EP/I012001/1. ...
doi:10.1007/978-3-319-10599-4_52
fatcat:dosr662razhmxgbxotpuiprgqe
Co-Saliency Spatio-Temporal Interaction Network for Person Re-Identification in Videos
2020
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Video-based person re-identification approaches have gained significant attention recently, expanding image-based approaches by learning features from multiple frames. ...
In this work, we propose a novel Co-Saliency Spatio-Temporal Interaction Network (CSTNet) for person re-identification in videos. ...
Acknowledgments Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence ...
doi:10.24963/ijcai.2020/141
dblp:conf/ijcai/LiuZZJ20
fatcat:v5copcdxlraw5p5jdkstvyzqri
Co-Saliency Spatio-Temporal Interaction Network for Person Re-Identification in Videos
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Video-based re-identification approaches have gained significant attention recently, expanding image-based approaches by learning features from multiple frames. ...
In this work, we propose a novel Co-Saliency Spatio-Temporal Interaction Network (CSTNet) for person re-identification in videos. ...
Early works on video-based person re-identification focus on hand-crafted video representations and/or distance metric learning. Recent approaches are mostly based on deep learning techniques. ...
arXiv:2004.04979v2
fatcat:qs43hpej6jdtzkobtkfgfqia7m
Deep Heterogeneous Feature Fusion for Template-Based Face Recognition
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
template-based face recognition, where a template refers to a set of still face images or video frames from different sources which introduces more blur, pose, illumination and other variations than traditional ...
Although deep learning has yielded impressive performance for face recognition, many studies have shown that different networks learn different feature maps: while some networks are more receptive to pose ...
This research is based upon work supported by the Office of the Director of National Intelligence (ODNI), Intelligence Advanced Research Projects Activity (IARPA), via IARPA R&D Contract No. 2014-14071600012 ...
arXiv:1702.04471v1
fatcat:at53lndktnamvomrccpj67pgsa
Image-Set Based Face Recognition Using Boosted Global and Local Principal Angles
[chapter]
2010
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2011; you can also visit the original URL.
The file type is application/pdf.
Inspired by the work of [4, 14] , this paper presents a robust framework for image-set based face recognition using boosted global and local principal angles. ...
The discriminative power of each principal angle for the global and each local sub-pattern is explicitly exploited by learning a strong classifier in a boosting manner. ...
Generally, for a subspace base pairs U A , U B which have rank of k, there exist k principal angles. ...
doi:10.1007/978-3-642-12307-8_30
fatcat:wbo26vnzpnhora6lhzf5pvhylu
High-level event recognition in unconstrained videos
2012
International Journal of Multimedia Information Retrieval
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
In this paper, we review current technologies for complex event recognition in unconstrained videos. ...
The goal of high-level event recognition is to automatically detect complex high-level events in a given video sequence. ...
Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright annotation thereon. ...
doi:10.1007/s13735-012-0024-2
fatcat:mfzttic3svb4tho2xb6aczgp4y
Action recognition in real-world videos
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The goal of human action recognition is to temporally or spatially localize the human action of interest in video sequences. ...
In this chapter, we are using action, activity, event interchangeably. ...
Weakly supervised anomaly detection algorithms in [31] developed multiple instance ranking loss for criminal activity detection in surveillance videos. ...
arXiv:2004.10774v1
fatcat:asnrp2z6mvfnlh46w5idj4rogm
Large-scale multimodal semantic concept detection for consumer video
2007
Proceedings of the international workshop on Workshop on multimedia information retrieval - MIR '07
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2010; you can also visit the original URL.
The file type is application/pdf.
To the best of our knowledge, this is the first work on systematic investigation of multimodal classification using a large-scale ontology and realistic video corpus. ...
In this paper we present a systematic study of automatic classification of consumer videos into a large set of diverse semantic concept classes, which have been carefully selected based on user studies ...
Then the ensemble kernel is directly used for learning a one-vs. ...
doi:10.1145/1290082.1290118
dblp:conf/mir/ChangEJLYLL07
fatcat:dx5ro37fofgppdlvnxeijygmse
Similar Gesture Recognition using Hierarchical Classification Approach in RGB Videos
2018
2018 Digital Image Computing: Techniques and Applications (DICTA)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
The challenges and complexity involved in developing a video-based human action recognition system are manifold. ...
Recognizing human actions from the video streams has become one of the very popular research areas in computer vision and deep learning in the recent years. ...
In this paper, we discover the use of the CNN models on video-based human action recognition. A simple way to apply the CNN on videos will be in the following steps. ...
doi:10.1109/dicta.2018.8615804
dblp:conf/dicta/WuSB18
fatcat:tsc32wtxsfhnriiwt3ebqiiicq
Rank Pooling for Action Recognition
2017
IEEE Transactions on Pattern Analysis and Machine Intelligence
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2015 pre-print arXiv:1512.01848v1 fatcat:sbgpnihdcnhtlggfbpnpqi5psuOther Versions
By learning to rank the frame-level features of a video in chronological order, we obtain a new representation that captures the video-wide temporal dynamics of a video, suitable for action recognition ...
We evaluate our method on various benchmarks for generic action, fine-grained action and gesture recognition. ...
Leuven DBOF PhD fellowship, the FWO project Monitoring of abnormal activity with camera systems and iMinds High-Tech Visualization project. ...
doi:10.1109/tpami.2016.2558148
pmid:28278449
fatcat:x6c5hcmqvjahbawejbz6n7arym
Neural Aggregation Network for Video Face Recognition
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Other Versions
This paper presents a Neural Aggregation Network (NAN) for video face recognition. ...
The network takes a face video or face image set of a person with a variable number of face images as its input, and produces a compact, fixed-dimension feature representation for recognition. ...
HL's work was supported in part by Australia ARC Centre of Excellence for Robotic Vision (CE140100016) and by CSIRO Data61. ...
arXiv:1603.05474v4
fatcat:z2626u6r3ballourbfoxmzwa6q
A survey of approaches and trends in person re-identification
2014
Image and Vision Computing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Given an image/video of a person taken from one camera, re-identification is the process of identifying the person from images/videos taken from a different camera. ...
Open issues and challenges of the problem are highlighted with a discussion on potential directions for further research. ...
Person recognition is based on a nearest neighbor classifier. ...
doi:10.1016/j.imavis.2014.02.001
fatcat:3w7ju7pzl5gkbgl5djsbakrr7i
Neural Aggregation Network for Video Face Recognition
2017
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
This paper presents a Neural Aggregation Network (NAN) for video face recognition. ...
The network takes a face video or face image set of a person with a variable number of face images as its input, and produces a compact, fixed-dimension feature representation for recognition. ...
HL's work was supported in part by Australia ARC Centre of Excellence for Robotic Vision (CE140100016) and by CSIRO Data61. ...
doi:10.1109/cvpr.2017.554
dblp:conf/cvpr/YangRZCWLH17
fatcat:gqalohdicrdv3ozh3sumzq3wze
2020 Index IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 42
2021
IEEE Transactions on Pattern Analysis and Machine Intelligence
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
., +, TPAMI Feb. 2020 371-385
Learning Compact Features for Human Activity Recognition Via Probabilis-
tic First-Take-All. ...
Yu, T., +, TPAMI Oct. 2020 2523-2539 Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Force from Motion: Decoding Control Force of Activity in a First-Person Video. ...
., +, 2581 -2593 Open-Ended Learning of Latent Topics for 3D Object Recognition. Kasaei, S.H., +, 2567 -2580 Object Detection in Videos by High Quality Object Linking. ...
doi:10.1109/tpami.2020.3036557
fatcat:3j6s2l53x5eqxnlsptsgbjeebe
« Previous
Showing results 1 — 15 out of 2,759 results