Despite recent efforts, accuracy in group emotion recognition is still generally low. One of the reasons for these underwhelming performance levels is the scarcity of available labeled data which, like the literature approaches, is mainly focused on still images. In this work, we address this problem by adapting an inflated ResNet-50 pretrained for a similar task, activity recognition, where large labeled video datasets are available. Audio information is processed using a Bidirectional Long Short-Term Memory (Bi-LSTM) network receiving extracted features. A multimodal approach fuses audio and video information at the score level using a support vector machine classifier. Evaluation with data from the EmotiW 2020 AV Group-Level Emotion sub-challenge shows a final test accuracy of 65.74% for the multimodal approach, approximately 18% higher than the official baseline. The results show that using activity recognition pretraining offers performance advantages for group-emotion recognition and that audio is essential to improve the accuracy and robustness of video-based recognition.

Multimedia content production is nowadays widespread due to technological advances, namely supported by smartphones and social media. Although the massive amount of media content brings new opportunities to the industry, it also obfuscates the relevance of marketing content, meant to maintain and lure new audiences. This leads to an emergent necessity of producing these kinds of contents as quickly and engagingly as possible. Creating these automatically would decrease both the production costs and time, particularly by using static media for the creation of short storytelling animated clips. We propose an innovative approach that uses context and content information to transform a still photo into an appealing context-aware video clip. Thus, our solution presents a contribution to the state-of-the-art in computer vision and multimedia technologies and assists content creators with a value-added service to automatically build rich contextualized multimedia stories from single photographs.

Color and color differences are critical aspects in many image processing and computer vision applications. A paradigmatic example is object segmentation, where color distances can greatly influence the performance of the algorithms. Metrics for color difference have been proposed in the literature, including the definition of standards such as CIEDE2000, which quantifies the change in visual perception of two given colors. This standard has been recommended for industrial computer vision applications, but the benefits of its application have been impaired by the complexity of the formula. This paper proposes a new strategy that improves the usability of the CIEDE2000 metric when a maximum acceptable distance can be imposed. We argue that, for applications where a maximum value, above which colors are considered to be different, can be established, then it is possible to reduce the amount of calculations of the metric, by preemptively analyzing the color features. This methodology encompasses the benefits of the metric while overcoming its computational limitations, thus broadening the range of applications of CIEDE2000 in both the computer vision algorithms and computational resource requirements.

Technological advances are pushing into the mass market innovative wearable devices featuring increasing processing and sensing capacity, non-intrusiveness and ubiquitous use. Sensors built-in those devices, enable acquiring different types of data and by taking advantage of the available processing power, it is possible to run intelligent applications that process the sensed data to offer added-value to the user in multiple domains. Although not new to the modern society, it is unquestionable that the present exercise boom is rapidly spreading across all age groups. However, in a great majority of cases, people perform their physical activity on their own, either due to time or budget constraints and may easily get discouraged if they do not see results or perform exercises inadequately. This paper presents an application, running on a wearable device, aiming at operating as a personal trainer that validates a set of proposed exercises in a sports session. The developed solution uses inertial sensors of an Android Wear smartwatch and, based on a set of pattern recognition algorithms, detects the rate of success in the execution of a planned workout. The fact that all processing can be executed on the device is a differentiator factor to other existing solutions.

In this paper we present a complete system for object tracking over multiple uncalibrated cameras with or without overlapping fields of view. We employ an approach based on the bag-of-visterms technique to represent and match tracked objects. The tracks are compared with a global object model based on an ensemble of individual object models. The system can globally recognise objects and minimise common tracking problems such as track drift or split. The output is a timeline representing the objects present in a given multi-camera scene. The methods employed in the system are online and can be optimized to operate in real-time.

This paper addresses the inter-operability problem of multimedia terminal in media content delivery over heterogeneous networks and devices. We design and implement a terminal which includes a content browser providing presentation, navigation and interaction with MPEG-21 Digital Item Declaration (MPEG-21 DID) in order to support universal media access (UMA). We optimized the architecture in a client-server distributed approach with Web Service support. This terminal enables the MPEG-21 standard compliant content accessible on different terminal devices via common Web browsers. Such a design strategy illustrates a next-generation multimedia terminal supporting inter-operability in multimedia content adaptation over a heterogeneous delivery chain.

This paper addresses multimedia end user system design for content distribution over heterogeneous networks and terminals, with particular focus on end-to-end quality of service (QoS) control. A multimedia terminal comprising content-related metadata processor, usage environment characteristics provider, end user QoS monitor and H.264psilas extension scalable video coding (SVC) audio-visual player in coordination under a terminal middleware, has been conceived and implemented. This end user terminal enables end-to-end QoS control for content adaptation solution both in semantic and physical approaches to maximize end userpsilas perceptual experience and minimize resources. Such design approach illustrates a possible architecture for next generation multimedia end user terminal supporting MPEG-21 and H.264psilas extension SVC codec standards.