A comprehensive study on mid-level representation and ensemble learning for emotional analysis of video material

Multimedia Tools and Applications - In today’s society where audio-visual content such as professionally edited and user-generated videos is ubiquitous, automatic analysis of this content is...     

Community based feedback techniques to improve video search

In this paper, we present a novel approach to aid users in the difficult task of video search. We use a graph based model based on implicit feedback mined from the interactions of previous users of our video search system to provide recommendations to aid users in their search tasks. This approach means that users are not burdened with providing explicit feedback, while still getting the benefits of recommendations. The goal of this approach is to improve the quality of the results that users find, and in doing so also help users to explore a large and difficult information space. In particular we wish to make the challenging task of video search much easier for users. The results of our evaluation indicate that we achieved our goals, the performance of the users in retrieving relevant videos improved, and users were able to explore the collection to a greater extent.     

Temperature-programmed high-performance liquid chromatography coupled to isotope ratio mass spectrometry

The utility of liquid chromatography coupled to the isotope ratio mass spectrometry technique (LC-IRMS) has already been established through a variety of successful applications. However, the analytical constraint related to the use of aqueous mobile phases limits the LC separation mechanism. We report here a new strategy for high-precision (13)C isotopic analyses based on temperature-programmed LC-IRMS using aqueous mobile phases. Under these conditions, the isotopic precision and accuracy were studied. On one hand, experiments were carried out with phenolic acids using isothermal LC conditions at high temperature (170 degrees C); on the other hand, several experiments were performed by ramping the temperature, as conventionally used in a gas chromatography-based method with hydrosoluble fatty acids and pulses of CO 2 reference gas. In isothermal conditions at 170 degrees C, despite the increase of the CO 2 background, p-coumaric acid and its glucuronide conjugate gave reliable isotopic ratios compared to flow injection analysis-isotopic ratio mass spectrometry (FIA-IRMS) analyses (isotopic precision and accuracy are lower than 0.3 per thousand). On the opposite, for its sulfate conjugate, the isotopic accuracy is affected by its coelution with p-coumaric acid. Not surprisingly, this study also demonstrates that at high temperature (170 degrees C), a compound eluting with long residence time (i.e., ferulic acid) is degraded, affecting thus the delta (13)C (drift of 3 per thousand) and the peak area (compared to FIA-IRMS analysis at room temperature). Quantitation is also reported in isothermal conditions for p-coumaric acid in the range of 10-400 ng/mL and with benzoic acid as an internal standard. For temperature gradient LC-IRMS, in the area of the LC gradient (set up at 20 degrees C/min), the drift of the background observed produces a nonlinearity of SD (delta (13)C) approximately 0.01 per thousand/mV. To circumvent this drift, which impacts severely the precision and accuracy, an alternative approach, i.e., eluting the compound on the plateau of temperature studied was reported here. Other experiments with temperature-programmed LC-IRMS experiments are also reported with the presence of methanol in the injected solution to mimic residual solvent originating from the sample preparation or to slightly increase the solubility of the targeted compound for high-precision measurement.     

An experimental evaluation of ontology-based user profiles

In recent years, a number of research works have been carried out to improve the information retrieval process by exploiting external knowledge, e.g. by employing ontologies. Even though ontologies seem to be a promising technique to improve the retrieval process, hardly any study has been performed to evaluate the use of ontologies over a longer time period to model user interests. In this work we introduce an ontology based video recommender system that exploits implicit relevance feedback to capture users’ evolving information needs. The system exploits a generic ontology to organise users’ interests. We evaluate the recommendations by performing a user-centred multiple time-series study where participants were asked to include the system into their daily news gathering routine. The results of this study suggest that the system can be successfully employed to improve personal information seeking tasks in news domain.     

Simulated evaluation of faceted browsing based on feature selection

In this paper we explore the limitations of facet based browsing which uses sub-needs of an information need for querying and organising the search process in video retrieval. The underlying assumption of this approach is that the search effectiveness will be enhanced if such an approach is employed for interactive video retrieval using textual and visual features. We explore the performance bounds of a faceted system by carrying out a simulated user evaluation on TRECVid data sets, and also on the logs of a prior user experiment with the system. We first present a methodology to reduce the dimensionality of features by selecting the most important ones. Then, we discuss the simulated evaluation strategies employed in our evaluation and the effect on the use of both textual and visual features. Facets created by users are simulated by clustering video shots using textual and visual features. The experimental results of our study demonstrate that the faceted browser can potentially improve the search effectiveness.     

Urea-Peptide Hybrids as VEGF-A165/NRP-1 Complex Inhibitors with Improved Receptor Affinity and Biological Properties

Neuropilin-1 (NRP-1), the major co-receptor of vascular endothelial growth factor receptor-2 (VEGFR-2), may also independently act with VEGF-A₁₆₅ to stimulate tumour growth and metastasis. Therefore, there is great interest in compounds that can block VEGF-A165/NRP-1 interaction. Peptidomimetic type inhibitors represent a promising strategy in the treatment of NRP-1-related disorders. Here, we present the synthesis, affinity, enzymatic stability, molecular modeling and in vitro binding evaluation of the branched urea–peptide hybrids, based on our previously reported Lys(hArg)-Dab-Oic-Arg active sequence, where the Lys(hArg) branching has been modified by introducing urea units to replace the peptide bond at various positions. One of the resulting hybrids increased the affinity of the compound for NRP-1 more than 10-fold, while simultaneously improving resistance for proteolytic stability in serum. In addition, ligand binding to NRP-1 induced rapid protein stock exocytotic trafficking to the plasma membrane in breast cancer cells. Examined properties characterize this compound as a good candidate for further development of VEGF₁₆₅/NRP-1 inhibitors.