The Experts below are selected from a list of 162 Experts worldwide ranked by ideXlab platform
Yuli Gao - One of the best experts on this subject based on the ideXlab platform.
-
harvesting large scale weakly Tagged Image databases from the web
Computer Vision and Pattern Recognition, 2010Co-Authors: Jianping Fan, Yi Shen, Ning Zhou, Yuli GaoAbstract:To leverage large-scale weakly-Tagged Images for computer vision tasks (such as object detection and scene recognition), a novel cross-modal tag cleansing and junk Image filtering algorithm is developed for cleansing the weakly-Tagged Images and their social tags (i.e., removing irrelevant Images and finding the most relevant tags for each Image) by integrating both the visual similarity contexts between the Images and the semantic similarity contexts between their tags. Our algorithm can address the issues of spams, polysemes and synonyms more effectively and determine the relevance between the Images and their social tags more precisely, thus it can allow us to create large amounts of training Images with more reliable labels by harvesting from large-scale weakly-Tagged Images, which can further be used to achieve more effective classifier training for many computer vision tasks.
-
CVPR - Harvesting large-scale weakly-Tagged Image databases from the web
2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2010Co-Authors: Jianping Fan, Yi Shen, Ning Zhou, Yuli GaoAbstract:To leverage large-scale weakly-Tagged Images for computer vision tasks (such as object detection and scene recognition), a novel cross-modal tag cleansing and junk Image filtering algorithm is developed for cleansing the weakly-Tagged Images and their social tags (i.e., removing irrelevant Images and finding the most relevant tags for each Image) by integrating both the visual similarity contexts between the Images and the semantic similarity contexts between their tags. Our algorithm can address the issues of spams, polysemes and synonyms more effectively and determine the relevance between the Images and their social tags more precisely, thus it can allow us to create large amounts of training Images with more reliable labels by harvesting from large-scale weakly-Tagged Images, which can further be used to achieve more effective classifier training for many computer vision tasks.
Xiansheng Hua - One of the best experts on this subject based on the ideXlab platform.
-
summarizing Tagged Image collections by cross media representativeness voting
International Conference on Multimedia and Expo, 2009Co-Authors: Jingdong Wang, Xiansheng HuaAbstract:In this paper, we address the problem of generating both visual and textual summaries for Tagged Image collections simultaneously. The visual and textual summaries consist of representative Images and tags of the collection, which are selected through a proposed cross-media voting scheme. In the voting scheme, the likelihood of an Image to be a representative is voted by not only other Images but also the tags, according to the intra-media and cross-media affinities. The likelihood of a tag to be a representative is obtained in similar manner at the same time. We demonstrate that the proposed scheme produces more informative textual and visual summaries than summarizing Images and tags separately.
-
ICME - Summarizing Tagged Image collections by cross-media representativeness voting
2009 IEEE International Conference on Multimedia and Expo, 2009Co-Authors: Jingdong Wang, Xiansheng HuaAbstract:In this paper, we address the problem of generating both visual and textual summaries for Tagged Image collections simultaneously. The visual and textual summaries consist of representative Images and tags of the collection, which are selected through a proposed cross-media voting scheme. In the voting scheme, the likelihood of an Image to be a representative is voted by not only other Images but also the tags, according to the intra-media and cross-media affinities. The likelihood of a tag to be a representative is obtained in similar manner at the same time. We demonstrate that the proposed scheme produces more informative textual and visual summaries than summarizing Images and tags separately.
Edward J Delp - One of the best experts on this subject based on the ideXlab platform.
-
user generated video annotation using geo Tagged Image databases
International Conference on Multimedia and Expo, 2009Co-Authors: Golnaz Abdollahian, Edward J DelpAbstract:In this paper we propose a system that annotates a user generated video based on the associated location metadata, by exploiting user-Tagged Image databases. An example of such a database is a photo sharing website such as Flickr [1] where users upload their Images and annotate them with various tags. The goal is to find the tags that have high probability of being relevant to the video without any complex object or action recognition being done to the video sequence. A video is first segmented into camera views and a set of keyframes are selected to represent the video. We will describe the concept of camera view as the basic element of user generated videos which has special properties suitable for the video annotation application. The keyframes are used to retrieve the most relevant Images in the database. A “tag processing” step is then used to tag the video.
-
ICME - User generated video annotation using Geo-Tagged Image databases
2009 IEEE International Conference on Multimedia and Expo, 2009Co-Authors: Golnaz Abdollahian, Edward J DelpAbstract:In this paper we propose a system that annotates a user generated video based on the associated location metadata, by exploiting user-Tagged Image databases. An example of such a database is a photo sharing website such as Flickr [1] where users upload their Images and annotate them with various tags. The goal is to find the tags that have high probability of being relevant to the video without any complex object or action recognition being done to the video sequence. A video is first segmented into camera views and a set of keyframes are selected to represent the video. We will describe the concept of camera view as the basic element of user generated videos which has special properties suitable for the video annotation application. The keyframes are used to retrieve the most relevant Images in the database. A “tag processing” step is then used to tag the video.
Jianping Fan - One of the best experts on this subject based on the ideXlab platform.
-
harvesting large scale weakly Tagged Image databases from the web
Computer Vision and Pattern Recognition, 2010Co-Authors: Jianping Fan, Yi Shen, Ning Zhou, Yuli GaoAbstract:To leverage large-scale weakly-Tagged Images for computer vision tasks (such as object detection and scene recognition), a novel cross-modal tag cleansing and junk Image filtering algorithm is developed for cleansing the weakly-Tagged Images and their social tags (i.e., removing irrelevant Images and finding the most relevant tags for each Image) by integrating both the visual similarity contexts between the Images and the semantic similarity contexts between their tags. Our algorithm can address the issues of spams, polysemes and synonyms more effectively and determine the relevance between the Images and their social tags more precisely, thus it can allow us to create large amounts of training Images with more reliable labels by harvesting from large-scale weakly-Tagged Images, which can further be used to achieve more effective classifier training for many computer vision tasks.
-
CVPR - Harvesting large-scale weakly-Tagged Image databases from the web
2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2010Co-Authors: Jianping Fan, Yi Shen, Ning Zhou, Yuli GaoAbstract:To leverage large-scale weakly-Tagged Images for computer vision tasks (such as object detection and scene recognition), a novel cross-modal tag cleansing and junk Image filtering algorithm is developed for cleansing the weakly-Tagged Images and their social tags (i.e., removing irrelevant Images and finding the most relevant tags for each Image) by integrating both the visual similarity contexts between the Images and the semantic similarity contexts between their tags. Our algorithm can address the issues of spams, polysemes and synonyms more effectively and determine the relevance between the Images and their social tags more precisely, thus it can allow us to create large amounts of training Images with more reliable labels by harvesting from large-scale weakly-Tagged Images, which can further be used to achieve more effective classifier training for many computer vision tasks.
-
ACM Multimedia - Leveraging loosely-Tagged Images and inter-object correlations for tag recommendation
Proceedings of the international conference on Multimedia - MM '10, 2010Co-Authors: Yi Shen, Jianping FanAbstract:Large-scale loosely-Tagged Images (i.e., multiple object tags are given loosely at the Image level) are available on Internet, and it is very attractive to leverage such loosely-Tagged Images for automatic Image annotation applications. In this paper, a multi-task structured SVM algorithm is developed to leverage both the inter-object correlations and the loosely-Tagged Images for achieving more effective training of a large number of inter-related object classifiers. To leverage the loosely-Tagged Images for object classifier training, each loosely-Tagged Image is partitioned into a set of Image instances (Image regions) and a multiple instance learning algorithm is developed for instance label identification by automatically identifying the correspondences between multiple tags (given at the Image level) and the Image instances. An object correlation network is constructed for characterizing the inter-object correlations explicitly and identifying the inter-related learning tasks automatically. To enhance the discrimination power of a large number of inter-related object classifiers, a multi-task structured SVM algorithm is developed to model the inter-task relatedness more precisely and leverage the inter-object correlations for classifier training. Our experiments on a large number of inter-related object classes have provided very positive results.
Jingdong Wang - One of the best experts on this subject based on the ideXlab platform.
-
summarizing Tagged Image collections by cross media representativeness voting
International Conference on Multimedia and Expo, 2009Co-Authors: Jingdong Wang, Xiansheng HuaAbstract:In this paper, we address the problem of generating both visual and textual summaries for Tagged Image collections simultaneously. The visual and textual summaries consist of representative Images and tags of the collection, which are selected through a proposed cross-media voting scheme. In the voting scheme, the likelihood of an Image to be a representative is voted by not only other Images but also the tags, according to the intra-media and cross-media affinities. The likelihood of a tag to be a representative is obtained in similar manner at the same time. We demonstrate that the proposed scheme produces more informative textual and visual summaries than summarizing Images and tags separately.
-
ICME - Summarizing Tagged Image collections by cross-media representativeness voting
2009 IEEE International Conference on Multimedia and Expo, 2009Co-Authors: Jingdong Wang, Xiansheng HuaAbstract:In this paper, we address the problem of generating both visual and textual summaries for Tagged Image collections simultaneously. The visual and textual summaries consist of representative Images and tags of the collection, which are selected through a proposed cross-media voting scheme. In the voting scheme, the likelihood of an Image to be a representative is voted by not only other Images but also the tags, according to the intra-media and cross-media affinities. The likelihood of a tag to be a representative is obtained in similar manner at the same time. We demonstrate that the proposed scheme produces more informative textual and visual summaries than summarizing Images and tags separately.
