An in-depth evaluation of multimodal video genre categorization

Mironica, Ionut; Ionescu, Bogdan; Knees, Peter; Lambert, Patrick

doi:10.1109/cbmi.2013.6576545

Cited by 9 publications

(9 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The dataset is composed of 14,838 videos (3,288 hours) collected from the blip.tv 2 and is divided into a training set of 5,288 videos (36%) and a test set of 9,550 videos (64%). Those videos are distributed among 26 video genre categories assigned by the blip.tv media platform, namely (the numbers in brackets are the total number of videos): art (530), autos and vehicles (21) The main challenge of this collection is the high diversity of genres, as well as the high variety of visual contents within each genre category [14,15].…”

Section: Experiments and Resultsmentioning

confidence: 99%

Bag of Genres for Video Retrieval

Duarte

Penatti

Almeida

2016

2016 29th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)

View full text Add to dashboard Cite

This paper presents a higher level representation for videos aiming at video genre retrieval. In video genre retrieval, there is a challenge that videos may comprise multiple categories, for instance, news videos may be composed of sports, documentary, and action. Therefore, it is interesting to encode the distribution of such genres in a compact and effective manner. We propose to create a visual dictionary using a genre classifier. Each visual word in the proposed model corresponds to a region in the classification space determined by the classifier's model learned on the training frames. Therefore, the video feature vector contains a summary of the activations of each genre in its contents. We evaluate the bag-of-genres model for video genre retrieval, using the dataset of MediaEval Tagging Task of 2012. Results show that the proposed model increases the quality of the representation being more compact than existing features.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

Bag of Genres for Video Retrieval

Duarte

Penatti

Almeida

2016

2016 29th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)

View full text Add to dashboard Cite

show abstract

“…On Blip10000 dataset the highest performance is obtained using the proposed FK RBF run on standard audio descriptors, with an increase of MAP from 29.3% (without RF) to 46.3%; as well as run on all the combined descriptors which yields an increase from 30.2% (without RF) to 46.8%. On the other hand, the smallest increase in performance is obtained with BoVW descriptors, which also achieve low results during MediaEval 2012 Tagging Task benchmarking [59];…”

Section: Comparison With State-of-the-artmentioning

confidence: 96%

Fisher Kernel Temporal Variation-based Relevance Feedback for video retrieval

Mironica

Ionescu

Uijlings

et al. 2016

Computer Vision and Image Understanding

Self Cite

View full text Add to dashboard Cite

This paper proposes a novel framework for Relevance Feedback based on the Fisher Kernel (FK). Specifically, we train a Gaussian Mixture Model (GMM) on the top retrieval results (without supervision) and use this to create a FK representation, which is therefore specialized in modelling the most relevant examples. We use the FK representation to explicitly capture temporal variation in video via frame-based features taken at different time intervals. While the GMM is being trained, a user selects from the top examples those which he is looking for. This feedback is used to train a Support Vector Machine on the FK representation, which is then applied to re-rank the top retrieved results. We show that our approach outperforms other state-of-the-art relevance feedback methods. Experiments were carried out on the Blip10000, UCF50, UCF101 and ADL standard datasets using a broad range of multi-modal content descriptors (visual, audio, and text).

show abstract

“…The second dataset is composed of 100 points corresponding to real video sequences from the Blip10000 [9] dataset. Each video is described via the standard audio features proposed in [17]. In this dataset, videos are classified in 3 equal sized categories: "Health", "Documentary" and "Literature".…”

Section: B Multi-class Experimentsmentioning

confidence: 99%

Semi-supervised spectral clustering with automatic propagation of pairwise constraints

Voiron¹,

Benoît²,

Filip³

et al. 2015

2015 13th International Workshop on Content-Based Multimedia Indexing (CBMI)

Self Cite

View full text Add to dashboard Cite

International audienceIn our data driven world, clustering is of major importance to help end-users and decision makers understanding information structures. Supervised learning techniques rely on ground truth to perform the classification and are usually subject to overtraining issues. On the other hand, unsupervised clustering techniques study the structure of the data without disposing of any training data. Given the difficulty of the task, unsupervised learning tends to provide inferior results to supervised learning. To boost their performance, a compromise is to use learning only for some of the ambiguous classes. In this context, this paper studies the impact of pairwise constraints to unsupervised Spectral Clustering. We introduce a new generalization of constraint propagation which maximizes partitioning quality while reducing annotation costs. Experiments show the efficiency of the proposed scheme

show abstract

An in-depth evaluation of multimodal video genre categorization

Cited by 9 publications

References 19 publications

Bag of Genres for Video Retrieval

Bag of Genres for Video Retrieval

Fisher Kernel Temporal Variation-based Relevance Feedback for video retrieval

Semi-supervised spectral clustering with automatic propagation of pairwise constraints

Contact Info

Product

Resources

About