VisualTextualRank: An Extension of VisualRank to Large-Scale Video Shot Extraction Exploiting Tag Co-occurrence

H., Nga; Yanai, Keiji

doi:10.1587/transinf.2014edp7106

Cited by 3 publications

(3 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Even though average precision is not significantly improved, shots retrieved by our proposed method look much more diverse as shown in the followings. Regarding evaluation for diversity of ranking results, we use evaluation method as described in [7]. Diversity score of a ranking result is defined as the ratio of the number of identical videos in its top ranked N video shots to N. This definition is based on the fact that shots from the same video tend to look similar.…”

Section: Dataset Constructionmentioning

confidence: 99%

“…On the other hand, our proposed system can be applied to extract data for various types of actions which are distributed over much more immense video source. Our previous work [2], [6], [7] proposed to collect video shots corresponding to any kind of action concept using Web videos. We conducted experiments for more than 100 action concepts in the previous work and obtained promising results.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Retrieval of Action Video Shots from the Web Using Density-Based Cluster Analysis and Outlier Detection

Yanai

2016

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

SUMMARYIn this paper, we introduce a fully automatic approach to construct action datasets from noisy Web video search results. The idea is based on combining cluster structure analysis and density-based outlier detection. For a specific action concept, first, we download its Web top search videos and segment them into video shots. We then organize these shots into subsets using density-based hierarchy clustering. For each set, we rank its shots by their outlier degrees which are determined as their isolatedness with respect to their surroundings. Finally, we collect high ranked shots as training data for the action concept. We demonstrate that with action models trained by our data, we can obtain promising precision rates in the task of action classification while offering the advantage of fully automatic, scalable learning. Experiment results on UCF11, a challenging action dataset, show the effectiveness of our method.

show abstract

Section: Dataset Constructionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Automatic Retrieval of Action Video Shots from the Web Using Density-Based Cluster Analysis and Outlier Detection

Yanai

2016

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…(1) Bipartite Graph Based Ranking Many real applications can be modeled as a bipartite graph, including Video shots and Tags [46], Queries and URLs, Entities and Co-List [47] in a Web page, Phenotypes and Diseases [48].…”

Section: Subtopic Relevance Estimationmentioning

confidence: 99%

A Bipartite Graph-Based Ranking Approach to Query Subtopics Diversification Focused on Word Embedding Features

Ullah

Aono

2016

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYWeb search queries are usually vague, ambiguous, or tend to have multiple intents. Users have different search intents while issuing the same query. Understanding the intents through mining subtopics underlying a query has gained much interest in recent years. Query suggestions provided by search engines hold some intents of the original query, however, suggested queries are often noisy and contain a group of alternative queries with similar meaning. Therefore, identifying the subtopics covering possible intents behind a query is a formidable task. Moreover, both the query and subtopics are short in length, it is challenging to estimate the similarity between a pair of short texts and rank them accordingly. In this paper, we propose a method for mining and ranking subtopics where we introduce multiple semantic and content-aware features, a bipartite graph-based ranking (BGR) method, and a similarity function for short texts. Given a query, we aggregate the suggested queries from search engines as candidate subtopics and estimate the relevance of them with the given query based on word embedding and content-aware features by modeling a bipartite graph. To estimate the similarity between two short texts, we propose a Jensen-Shannon divergence based similarity function through the probability distributions of the terms in the top retrieved documents from a search engine. A diversified ranked list of subtopics covering possible intents of a query is assembled by balancing the relevance and novelty. We experimented and evaluated our method on the NTCIR-10 INTENT-2 and NTCIR-12 IMINE-2 subtopic mining test collections. Our proposed method outperforms the baselines, known related methods, and the official participants of the INTENT-2 and IMINE-2 competitions.

show abstract

Automatic Construction of Action Datasets Using Web Videos with Density-Based Cluster Analysis and Outlier Detection

Yanai

2016

Image and Video Technology

View full text Add to dashboard Cite

VisualTextualRank: An Extension of VisualRank to Large-Scale Video Shot Extraction Exploiting Tag Co-occurrence

Cited by 3 publications

References 23 publications

Automatic Retrieval of Action Video Shots from the Web Using Density-Based Cluster Analysis and Outlier Detection

Automatic Retrieval of Action Video Shots from the Web Using Density-Based Cluster Analysis and Outlier Detection

A Bipartite Graph-Based Ranking Approach to Query Subtopics Diversification Focused on Word Embedding Features

Automatic Construction of Action Datasets Using Web Videos with Density-Based Cluster Analysis and Outlier Detection

Contact Info

Product

Resources

About