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.
Filters
A System for Video Recommendation using Visual Saliency, Crowdsourced and Automatic Annotations
2015
Proceedings of the 23rd ACM international conference on Multimedia - MM '15
Preserved Fulltext
In this paper we present a system for content-based video recommendation that exploits visual saliency to better represent video features and content 1 . ...
a more effective video representation used in the recommender system. ...
CONCLUSIONS In this paper we have presented a system that performs item-based video recommendation using a content based description of videos obtained from crowdsourced and automatic annotations. ...
doi:10.1145/2733373.2807982
dblp:conf/mm/FerracaniPBMB15
fatcat:3rwuw5etojdg3nelmpccy2jaei
Knowledge discovery over community-sharing media: From signal to intelligence
2009
2009 IEEE International Conference on Multimedia and Expo
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.
applications such as annotation, automatic training data acquisition, contextual advertising, and visualization. ...
and pose new challenges for the design of efficient search, mining, and visualization methods for manipulation. ...
For example, the ALIPR system [7] used advanced statistical learning techniques to provide fully automatic and real-time annotation for user-uploaded digital pictures. ...
doi:10.1109/icme.2009.5202775
dblp:conf/icmcs/HsuMY09
fatcat:nzblrwkfjfdcvfhlc65pvkotbi
Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback
[article]
2024
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 2024; you can also visit the original URL.
The file type is application/pdf.
Other Versions
To bridge this gap, we introduce Uni-RLHF, a comprehensive system implementation tailored for RLHF. ...
Uni-RLHF contains three packages: 1) a universal multi-feedback annotation platform, 2) large-scale crowdsourced feedback datasets, and 3) modular offline RLHF baseline implementations. ...
The authors thank Peilong Han for his help in building and deploying the platform. ...
arXiv:2402.02423v2
fatcat:gfwfik3dyzfehgsn4sya3uqkza
Glimpse: A Gaze-Based Measure of Temporal Salience
2021
Sensors
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.
Glimpse could serve as the basis for several downstream tasks such as segmentation or summarization of videos. Glimpse's software and data are publicly available. ...
The measure is conceptually simple, training free, and provides a semantically meaningful quantification of visual attention over time. ...
In this context, one could use GLIMPSE to automatically build annotated datasets of temporal salience with little effort. ...
doi:10.3390/s21093099
pmid:33946830
pmcid:PMC8125412
fatcat:tospskeb45h5bctyeg6modnkgm
A Natural and Immersive Virtual Interface for the Surgical Safety Checklist Training
2014
Proceedings of the 2014 ACM International Workshop on Serious Games - SeriousGames '14
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.
With the focus on natural language and entity understanding, for instance, we have improved Bing's ability to understand the user intent beyond queries and keywords. ...
By leveraging big data from billions of search queries, billions of images on the web and from the social networks, and billions of user clicks, we have designed massive machine learning systems to continuously ...
Discriminative Hashing for Compact Binary Codes
Personalized Visual Vocabulary Adaption for Social Image Retrieval
Co-saliency Detection via Base Reconstruction
Automatic Facial Image Annotation and ...
doi:10.1145/2656719.2656725
dblp:conf/mm/FerracaniPB14a
fatcat:obsb2i4iybhu3dq77hujvjtbze
AI-Empowered Persuasive Video Generation: A Survey
[article]
2021
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 2021; you can also visit the original URL.
The file type is application/pdf.
Today, such videos are often produced by professionals, which is a time-, labour- and cost-intensive undertaking. ...
Promotional videos are rapidly becoming a popular medium for persuading people to change their behaviours in many settings (e.g., online shopping, social enterprise initiatives). ...
[48] X-S Hua, Lie Lu, and H-J Zhang. 2006. Photo2Video—A System for Automatically Converting Photographic Series
Into Video. ...
arXiv:2112.09401v1
fatcat:t5bsqo6shbcoleryphaawewevy
Unsupervised Discovery of Character Dictionaries in Animation Movies
2018
IEEE transactions on multimedia
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.
These candidates are further pruned using saliency constraints and visual object tracking. A character dictionary per movie is then generated from exemplars obtained by clustering these candidates. ...
Our results indicate high precision and recall of the automatically detected characters compared to human-annotated ground truth, demonstrating the generalizability of our approach. ...
The relevant and noisy exemplars that we annotated for the system evaluation can potentially be used for these methods. ...
doi:10.1109/tmm.2017.2745712
fatcat:5rslvy7gkfhehllnqpnkst6dne
Contextual Internet Multimedia Advertising
2010
Proceedings of the IEEE
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.
Those visual contents have become the primary sources for online advertising. ...
In this paper, we summarize the trend of Internet multimedia advertising and conduct a broad survey on the methodologies for advertising which are driven by the rich contents of images and videos. ...
While fully automatic categorization or annotation still achieved limited success [35] , [42] , Internet-based annotation which is characterized by collecting crowdsourcing knowledge, as well as combining ...
doi:10.1109/jproc.2009.2039841
fatcat:n2yp2lmv2fdutcw32agbahwnu4
Engagement detection in online learning: a review
2019
Smart Learning Environments
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.
These methods are nonintrusive in nature, and the hardware and the software that these methods use to capture and analyze video data are cost-effective and easily achievable. ...
., audio, video, texts for learner log data etc.) they process for the engagement detection. ...
Funding Academic Research Fund (ARF) and Research Incentive Grant (RIG), Athabasca University, Canada. Availability of data and materials Not applicable. ...
doi:10.1186/s40561-018-0080-z
fatcat:lwkphkvkdzen7d3v4bh46waazu
Automatic Understanding of Image and Video Advertisements
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.
We also analyze the most common persuasive strategies ads use, and the capabilities that computer vision systems should have to understand these strategies. ...
To enable research on this problem, we create two datasets: an image dataset of 64,832 image ads, and a video dataset of 3,477 ads. ...
This research was also supported by a Google Faculty Research Award and an NVIDIA hardware grant. ...
doi:10.1109/cvpr.2017.123
dblp:conf/cvpr/HussainZZYTAOK17
fatcat:lpdwh7s755dnrol5hzbnwk7sfu
Automatic Understanding of Image and Video Advertisements
[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.
We also analyze the most common persuasive strategies ads use, and the capabilities that computer vision systems should have to understand these strategies. ...
To enable research on this problem, we create two datasets: an image dataset of 64,832 image ads, and a video dataset of 3,477 ads. ...
This research was also supported by a Google Faculty Research Award and an NVIDIA hardware grant. ...
arXiv:1707.03067v1
fatcat:eekhvqmj4baxnpurlt3mhbonbq
An Image Is Worth More than a Thousand Favorites: Surfacing the Hidden Beauty of Flickr Pictures
2021
Proceedings of the ... International AAAI Conference on Weblogs and Social Media
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 2022; you can also visit the original URL.
The file type is application/pdf.
By gathering a large crowdsourced ground truth of aesthetics scores for Flickr images, we show that our method retrieves photos whose median perceived beauty score is equal to the most popular ones, and ...
We propose to use a computer vision method to surface beautiful pictures from the immense pool of near-zero-popularity items, and we test it on a large dataset of creative-commons photos on Flickr. ...
Judith Redi for her precious help and discussions. ...
doi:10.1609/icwsm.v9i1.14612
fatcat:lfqgvsi65jfz5pm3fln4nklgka
When I Look into Your Eyes: A Survey on Computer Vision Contributions for Human Gaze Estimation and Tracking
2020
Sensors
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 automatic detection of eye positions, their temporal consistency, and their mapping into a line of sight in the real world (to find where a person is looking at) is reported in the scientific literature ...
A very long journey has been made from the first pioneering works, and this continuous search for more accurate solutions process has been further boosted in the last decade when deep neural networks have ...
A new video dataset for object referring, with 30,000 objects over 5000 stereo video sequences annotated via crowdsourcing for their descriptions and gaze targets has been made available into [97] . ...
doi:10.3390/s20133739
pmid:32635375
pmcid:PMC7374327
fatcat:jwou6gv4f5dy7lrsxvtbnb2fly
An Image is Worth More than a Thousand Favorites: Surfacing the Hidden Beauty of Flickr Pictures
[article]
2015
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
By gathering a large crowdsourced ground truth of aesthetics scores for Flickr images, we show that our method retrieves photos whose median perceived beauty score is equal to the most popular ones, and ...
We propose to use a computer vision method to surface beautiful pictures from the immense pool of near-zero-popularity items, and we test it on a large dataset of creative-commons photos on Flickr. ...
Judith Redi for her precious help and discussions. ...
arXiv:1505.03358v2
fatcat:fu4sq22my5febhkgbylmmyxki4
LIRIS-ACCEDE: A Video Database for Affective Content Analysis
2015
IEEE Transactions on Affective 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.
Affective annotations were achieved using crowdsourcing through a pair-wise video comparison protocol, thereby ensuring that annotations are fully consistent, as testified by a high inter-annotator agreement ...
In addition, to enable fair comparison and landmark progresses of future affective computational models, we further provide four experimental protocols and a baseline for prediction of emotions using a ...
Crowdsourcing is often the recommended solution for creating a large dataset representing a condition. ...
doi:10.1109/taffc.2015.2396531
fatcat:4nh6hkm7yba35esleky5favgeq
« Previous
Showing results 1 — 15 out of 314 results