Indoor scene recognition is a growing field with great potential for behaviour understanding, robot localization, and elderly monitoring, among others. In this study, we approach the task of scene recognition from a novel standpoint, using multimodal learning and video data gathered from social media. The accessibility and variety of social media videos can provide realistic data for modern scene recognition techniques and applications. We propose a model based on fusion of transcribed speech to text and visual features, which is used for classification on a novel dataset of social media videos of indoor scenes named InstaIndoor. Our model achieves up to 70% accuracy and 0.7 F1-Score. Furthermore, we highlight the potential of our approach by benchmarking on a YouTube-8M subset of indoor scenes as well, where it achieves 74% accuracy and 0.74 F1-Score. We hope the contributions of this work pave the way to novel research in the challenging field of indoor scene recognition.

The use of deep learning techniques has exploded during the last few years, resulting in a direct contribution to the field of artificial intelligence. This work aims to be a review of the state-of-the-art in scene recognition with deep learning models from visual data. Scene recognition is still an emerging field in computer vision, which has been addressed from a single image and dynamic image perspective. We first give an overview of available datasets for image and video scene recognition. Later, we describe ensemble techniques introduced by research papers in the field. Finally, we give some remarks on our findings and discuss what we consider challenges in the field and future lines of research. This paper aims to be a future guide for model selection for the task of scene recognition.

No abstract

Abstract. The paper brings in attention the importance that the sliding system of a tool machinery is having in the final precision of the manufacturing. We are basically comparing two type of slides, one constructed with plane surfaces and the other one with circular crosssections (as known as cylindrical slides), analysing each solution from the point of view of its technology of manufacturing, of the precision that the particular slides are transferring to the tool machinery, cost of production, etc. Special attention is given to demonstrate theoretical and to confirm by experimental works what is happening with the stress distribution in the case of plane slides and cylindrical slides, both in longitudinal and in cross-over sections. Considering the results obtained for the stress distribution in the transversal and longitudinal cross sections, by composing them, we can obtain the stress distribution on the semicircular slide. Based on the results, special solutions for establishing the stress distribution between two surfaces without interact in the contact zone have been developed.

In this paper, we carried out a study of the parameters influencing the separation of olives from tree branches when harvesting is executed by means of shaking the trunk. It showed there are two important parameters, namely the shaking force and the amplitude of the shaking [1, 2, 3]. In order to determine these two parameters, we used a mathematic model which was used in developing a software that can determine their value depending on the diameter of the trunk in the contact area [4].