MediaEval 2015 - GTM-UVigo Systems for Person Discovery Task at MediaEval 2015

•

0 likes•152 views

In this paper, we present the systems developed by GTMUVigo team for the Multimedia Person Discovery in Broadcast TV task at MediaEval 2015. The systems propose two different strategies for person discovery in audio through speaker diarization (one based on an online clustering strategy with error correction using OCR information and the other based on agglomerative hierarchical clustering) as well as intrashot and intershot trategies for face clustering. http://ceur-ws.org/Vol-1436/ http://www.multimediaeval.org

Education

GTM-UVigo Systems for Person Discovery Task
at MediaEval 2015
Paula L´opez Otero, Rosal´ıa Barros, Laura Doc´ıo Fern´andez,
Elisardo Gonz´alez Agulla, Jos´e Luis Alba Castro, Carmen Garc´ıa
Mateo
L´opez Otero, Barros et al. — GTM-UVigo Systems for Person Discovery Task at MediaEval 2015 1/6

Main contributions
Error correction in speaker diarization using written names
Face tracking correction using quality scores
Visual Voice activity detection
L´opez Otero, Barros et al. — GTM-UVigo Systems for Person Discovery Task at MediaEval 2015 2/6

Speaker diarization + written names
Speech activity detection
L´opez Otero, Barros et al. — GTM-UVigo Systems for Person Discovery Task at MediaEval 2015 3/6

Speaker diarization + written names
Speaker segmentation
L´opez Otero, Barros et al. — GTM-UVigo Systems for Person Discovery Task at MediaEval 2015 3/6

Speaker diarization + written names
Speaker clustering
L´opez Otero, Barros et al. — GTM-UVigo Systems for Person Discovery Task at MediaEval 2015 3/6

Face diarization + shot segmentation
Face detection and tracking
L´opez Otero, Barros et al. — GTM-UVigo Systems for Person Discovery Task at MediaEval 2015 4/6

Face diarization + shot segmentation
Quality Filter
L´opez Otero, Barros et al. — GTM-UVigo Systems for Person Discovery Task at MediaEval 2015 4/6

Face diarization + shot segmentation
Visual Voice Activity Detection
L´opez Otero, Barros et al. — GTM-UVigo Systems for Person Discovery Task at MediaEval 2015 4/6

Face diarization + shot segmentation
Face recognition
L´opez Otero, Barros et al. — GTM-UVigo Systems for Person Discovery Task at MediaEval 2015 4/6

Results
REPERE INA
EwMAP MAP C EwMAP MAP C
fusion 75.76 % 77.10 % 78.03 % 80.34 % 80.61 % 92.42 %
audio 69.37 % 70.90 % 78.48 % 89.38 % 89.76 % 97.34 %
video 73.94 % 75.29 % 78.03 % 80.66 % 80.94 % 92.46 %
baseline 63.58 % 63.93 % 71.75 % 78.35 % 78.64 % 92.71 %
L´opez Otero, Barros et al. — GTM-UVigo Systems for Person Discovery Task at MediaEval 2015 5/6

Conclusions
Diﬃcult scenarios:
Audio: background music, noise.
Video: face pose and distance to the camara, video quality.
Face approaches work better in REPERE, but speech
approach works better in INA.
Future work: ﬁnding a smarter way to combine speech and
video.
L´opez Otero, Barros et al. — GTM-UVigo Systems for Person Discovery Task at MediaEval 2015 6/6

GTM-UVigo Systems for Person Discovery Task
at MediaEval 2015
L´opez Otero, Barros et al. — GTM-UVigo Systems for Person Discovery Task at MediaEval 2015 6/6

Viewers also liked

This paper describes the results of our participation to the Synchronization of Multi-User Event Media Task at the MediaEval 2015 challenge. Using multiple similarity measures, we identify pairs of similar media from different galleries. We use a graph-based approach to temporally synchronize user galleries; subsequently we use time information, geolocation information and visual concept detection results to cluster all photos into different sub-events. Our method achieves good accuracy on considerably diverse datasets. http://ceur-ws.org/Vol-1436/ http://www.multimediaeval.org

MediaEval 2015 - CERTH at MediaEval 2015 Synchronization of Multi-User Event ...

multimediaeval

The objective of this paper is to provide an overview of the Synchronization of Multi-User Event Media (SEM) Task, which is part of the MediaEval Benchmark for Multimedia Evaluation. The SEM task was initially presented at MediaEval in 2014, with the goal of proposing a challenge in aligning multiple users’ photo galleries related to the same event but with unreliable timestamps. Besides aligning the pictures on a common timeline, participants were also required to detect the sub-events and cluster the pictures accordingly. For 2015 we have decided to extend the task also to other types of media, thus including audio and video information for a more complete and diversified representation of the analyzed event. http://ceur-ws.org/Vol-1436/ http://www.multimediaeval.org

MediaEval 2015 - Synchronization of Multi-User Event Media at MediaEval 2015:...

multimediaeval

Presenter: Cynthia Liem TUD-MMC at MediaEval 2016: Predicting Media Interestingness Task In Working Notes Proceedings of the MediaEval 2016 Workshop, Hilversum, Netherlands, October 20-21, CEUR-WS.org (2016) by Cynthia Liem Paper: http://ceur-ws.org/Vol-1739/MediaEval_2016_paper_30.pdf Video: https://youtu.be/NQan10E_-kE Abstract: This working notes paper describes the TUD-MMC entry to the MediaEval 2016 Predicting Media Interestingness Task. Noting that the nature of movie trailer shots is different from that of preceding tasks on image and video interestingness, we propose two baseline heuristic approaches based on the clear occurrence of people. MAP scores obtained on the development set and test set suggest that our approaches cover a limited but non-marginal subset of the interestingness spectrum. Most strikingly, our obtained scores on the Image and Video Subtasks are comparable or better than those obtained when evaluating the ground truth annotations of the Image Subtask against the Video Subtask and vice versa

MediaEval 2016 - TUD-MMC Predicting media Interestingness Task

multimediaeval

Media REVEALr: A social multimedia monitoring and intelligence system for Web...

Symeon Papadopoulos

Presenter: Bogdan Boteanu, LAPI @ 2016 Retrieving Diverse Social Images Task: A Pseudo-Relevance Feedback Diversification Perspective In Working Notes Proceedings of the MediaEval 2016 Workshop, Hilversum, Netherlands, October 20-21, CEUR-WS.org (2016) by Bogdan Boteanu, Mihai G. Constantin, Bogdan Ionescu Paper: http://ceur-ws.org/Vol-1739/MediaEval_2016_paper_20.pdf Video: https://youtu.be/mDI8Z31p7TY Abstract: In this paper we present the results achieved during the 2016 MediaEval Retrieving Diverse Social Images Task, using an approach based on pseudo-relevance feedback, in which human feedback is replaced by an automatic selection of images. The proposed approach is designed to have in priority the diversification of the results, in contrast to most of the existing techniques that address only the relevance. Diversification is achieved by exploiting a hierarchical clustering scheme followed by a diversification strategy. Methods are tested on the benchmarking data and results are analyzed. Insights for future work conclude the paper.

MediaEval 2016 - LAPI @ 2016 Retrieving Diverse Social Images Task: A Pseudo-...

multimediaeval

MediaEval 2016 - IR Evaluation: Putting the User Back in the Loop

multimediaeval

Presenter: Maigrot Cédric MediaEval 2016: A Multimodal System for the Verifying Multimedia Use Task In Working Notes Proceedings of the MediaEval 2016 Workshop, Hilversum, Netherlands, October 20-21, CEUR-WS.org (2016) by Cédric Maigrot, Vincent Claveau, Ewa Kijak, Ronan Sicre Paper: http://ceur-ws.org/Vol-1739/MediaEval_2016_paper_45.pdf Video: https://youtu.be/ay1zWydnijY Abstract: This paper presents a multi-modal hoax detection system composed of text, source, and image analysis. As hoax can be very diverse, we want to analyze several modalities to better detect them. This system is applied in the context of the Verifying Multimedia Use task of MediaEval 2016. Experiments show the performance of each separated modality as well as their combination.

MediaEval 2016: A Multimodal System for the Verifying Multimedia Use Task

multimediaeval

This slideset presents an approach to automatically detecting breaking news events from social media streams, using event detection to collecting near real time relevant video documents from social networks regarding that breaking news. A visual analytics dashboard provides access to the results of the content processing pipeline, providing a rich interactive interface to explore emerging stories and select video material around those stories for verification.

Video Retrieval for Multimedia Verification of Breaking News on Social Networks

InVID Project

MediaEval 2016 - COSMIR and the OpenMIC Challenge: A Plan for Sustainable Mus...

multimediaeval

Presenter: Giorgos Kordopatis-Zilos Placing Images with Refined Language Models and Similarity Search with PCA-reduced VGG Features In Working Notes Proceedings of the MediaEval 2016 Workshop, Hilversum, Netherlands, October 20-21, CEUR-WS.org (2016) by Giorgos Kordopatis-Zilos, Adrian Popescu, Symeon Papadopoulos, Yiannis Kompatsiaris Paper: http://ceur-ws.org/Vol-1739/MediaEval_2016_paper_13.pdf Video: https://youtu.be/WR4I3CWjcR4 Abstract: We describe the participation of the CERTH/CEA-LIST team in the MediaEval 2016 Placing Task. We submitted five runs to the estimation-based sub-task: one based only on text by employing a Language Model-based approach with several refinements, one based on visual content, using geospatial clustering over the most visually similar images, and three based on a hybrid scheme exploiting both visual and textual cues from the multimedia items, trained on datasets of different size and origin. The best results were obtained by a hybrid approach trained with external training data and using two publicly available gazetteers.

MediaEval 2016 - Placing Images with Refined Language Models and Similarity S...

multimediaeval

This paper provides an overview of the Verifying Multimedia Use task that takes places as part of the 2015 MediaEval Benchmark. The task deals with the automatic detection of manipulation and misuse of Web multimedia content. Its aim is to lay the basis for a future generation of tools that could assist media professionals in the process of verification. Examples of manipulation include maliciously tampering with images and videos, e.g., splicing, removal/addition of elements, while other kinds of misuse include the reposting of previously captured multimedia content in a different context (e.g., a new event) claiming that it was captured there. For the 2015 edition of the task, we have generated and made available a large corpus of real-world cases of images that were distributed through tweets, along with manually assigned labels regarding their use, i.e. misleading (fake) versus appropriate (real). http://ceur-ws.org/Vol-1436/ http://www.multimediaeval.org

MediaEval 2015 - Verifying Multimedia Use at MediaEval 2015

multimediaeval

Viewers also liked (11)