arXiv subjects

Giovanni Maria Farinella

Publications and source records attributed to Giovanni Maria Farinella.

64 records · Page 4Linked to original sources

arXiv2020

SceneAdapt: Scene-based domain adaptation for semantic segmentation using adversarial learning

Semantic segmentation methods have achieved outstanding performance thanks to deep learning. Nevertheless, when such algorithms are deployed to new contexts not seen during training, it is necessary to collect and label scene-specific data in order to adapt them to the new domain using fine-tuning. This process is required whenever an already installed camera is moved or a new camera is introduced in a camera network due to the different scene layouts induced by the different viewpoints. To limit the amount of additional training data to be collected, it would be ideal to train a semantic segmentation method using labeled data already available and only unlabeled data coming from the new camera. We formalize this problem as a domain adaptation task and introduce a novel dataset of urban scenes with the related semantic labels. As a first approach to address this challenging task, we propose SceneAdapt, a method for scene adaptation of semantic segmentation algorithms based on adversarial learning. Experiments and comparisons with state-of-the-art approaches to domain adaptation highlight that promising performance can be achieved using adversarial learning both when the two scenes have different but points of view, and when they comprise images of completely different scenes. To encourage research on this topic, we made our code available at our web page: https://iplab.dmi.unict.it/ParkSmartSceneAdaptation/.

cs.CV↗

arXiv2020

Survey on Visual Sentiment Analysis

Visual Sentiment Analysis aims to understand how images affect people, in terms of evoked emotions. Although this field is rather new, a broad range of techniques have been developed for various data sources and problems, resulting in a large body of research. This paper reviews pertinent publications and tries to present an exhaustive overview of the field. After a description of the task and the related applications, the subject is tackled under different main headings. The paper also describes principles of design of general Visual Sentiment Analysis systems from three main points of view: emotional models, dataset definition, feature design. A formalization of the problem is discussed, considering different levels of granularity, as well as the components that can affect the sentiment toward an image in different ways. To this aim, this paper considers a structured formalization of the problem which is usually used for the analysis of text, and discusses it's suitability in the context of Visual Sentiment Analysis. The paper also includes a description of new challenges, the evaluation from the viewpoint of progress toward more sophisticated systems and related practical applications, as well as a summary of the insights resulting from this study.

cs.CV↗

arXiv2020

Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video

In this paper, we tackle the problem of egocentric action anticipation, i.e., predicting what actions the camera wearer will perform in the near future and which objects they will interact with. Specifically, we contribute Rolling-Unrolling LSTM, a learning architecture to anticipate actions from egocentric videos. The method is based on three components: 1) an architecture comprised of two LSTMs to model the sub-tasks of summarizing the past and inferring the future, 2) a Sequence Completion Pre-Training technique which encourages the LSTMs to focus on the different sub-tasks, and 3) a Modality ATTention (MATT) mechanism to efficiently fuse multi-modal predictions performed by processing RGB frames, optical flow fields and object-based features. The proposed approach is validated on EPIC-Kitchens, EGTEA Gaze+ and ActivityNet. The experiments show that the proposed architecture is state-of-the-art in the domain of egocentric videos, achieving top performances in the 2019 EPIC-Kitchens egocentric action anticipation challenge. The approach also achieves competitive performance on ActivityNet with respect to methods not based on unsupervised pre-training and generalizes to the tasks of early action recognition and action recognition. To encourage research on this challenging topic, we made our code, trained models, and pre-extracted features available at our web page: http://iplab.dmi.unict.it/rulstm.

cs.CV↗

arXiv2020

The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines

Since its introduction in 2018, EPIC-KITCHENS has attracted attention as the largest egocentric video benchmark, offering a unique viewpoint on people's interaction with objects, their attention, and even intention. In this paper, we detail how this large-scale dataset was captured by 32 participants in their native kitchen environments, and densely annotated with actions and object interactions. Our videos depict nonscripted daily activities, as recording is started every time a participant entered their kitchen. Recording took place in 4 countries by participants belonging to 10 different nationalities, resulting in highly diverse kitchen habits and cooking styles. Our dataset features 55 hours of video consisting of 11.5M frames, which we densely labelled for a total of 39.6K action segments and 454.2K object bounding boxes. Our annotation is unique in that we had the participants narrate their own videos after recording, thus reflecting true intention, and we crowd-sourced ground-truths based on these. We describe our object, action and. anticipation challenges, and evaluate several baselines over two test splits, seen and unseen kitchens. We introduce new baselines that highlight the multimodal nature of the dataset and the importance of explicit temporal modelling to discriminate fine-grained actions e.g. 'closing a tap' from 'opening' it up.

cs.CV↗

arXiv2020

EGO-CH: Dataset and Fundamental Tasks for Visitors BehavioralUnderstanding using Egocentric Vision

Equipping visitors of a cultural site with a wearable device allows to easily collect information about their preferences which can be exploited to improve the fruition of cultural goods with augmented reality. Moreover, egocentric video can be processed using computer vision and machine learning to enable an automated analysis of visitors' behavior. The inferred information can be used both online to assist the visitor and offline to support the manager of the site. Despite the positive impact such technologies can have in cultural heritage, the topic is currently understudied due to the limited number of public datasets suitable to study the considered problems. To address this issue, in this paper we propose EGOcentric-Cultural Heritage (EGO-CH), the first dataset of egocentric videos for visitors' behavior understanding in cultural sites. The dataset has been collected in two cultural sites and includes more than $27$ hours of video acquired by $70$ subjects, with labels for $26$ environments and over $200$ different Points of Interest. A large subset of the dataset, consisting of $60$ videos, is associated with surveys filled out by real visitors. To encourage research on the topic, we propose $4$ challenging tasks (room-based localization, point of interest/object recognition, object retrieval and survey prediction) useful to understand visitors' behavior and report baseline results on the dataset.

cs.CV↗

arXiv2019

What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attention

Egocentric action anticipation consists in understanding which objects the camera wearer will interact with in the near future and which actions they will perform. We tackle the problem proposing an architecture able to anticipate actions at multiple temporal scales using two LSTMs to 1) summarize the past, and 2) formulate predictions about the future. The input video is processed considering three complimentary modalities: appearance (RGB), motion (optical flow) and objects (object-based features). Modality-specific predictions are fused using a novel Modality ATTention (MATT) mechanism which learns to weigh modalities in an adaptive fashion. Extensive evaluations on two large-scale benchmark datasets show that our method outperforms prior art by up to +7% on the challenging EPIC-Kitchens dataset including more than 2500 actions, and generalizes to EGTEA Gaze+. Our approach is also shown to generalize to the tasks of early action recognition and action recognition. Our method is ranked first in the public leaderboard of the EPIC-Kitchens egocentric action anticipation challenge 2019. Please see our web pages for code and examples: http://iplab.dmi.unict.it/rulstm - https://github.com/fpv-iplab/rulstm.

cs.CV↗

arXiv2019

Egocentric Visitors Localization in Cultural Sites

We consider the problem of localizing visitors in a cultural site from egocentric (first person) images. Localization information can be useful both to assist the user during his visit (e.g., by suggesting where to go and what to see next) and to provide behavioral information to the manager of the cultural site (e.g., how much time has been spent by visitors at a given location? What has been liked most?). To tackle the problem, we collected a large dataset of egocentric videos using two cameras: a head-mounted HoloLens device and a chest-mounted GoPro. Each frame has been labeled according to the location of the visitor and to what he was looking at. The dataset is freely available in order to encourage research in this domain. The dataset is complemented with baseline experiments performed considering a state-of-the-art method for location-based temporal segmentation of egocentric videos. Experiments show that compelling results can be achieved to extract useful information for both the visitor and the site-manager.

cs.CV↗

arXiv2019

Next-Active-Object prediction from Egocentric Videos

Although First Person Vision systems can sense the environment from the user's perspective, they are generally unable to predict his intentions and goals. Since human activities can be decomposed in terms of atomic actions and interactions with objects, intelligent wearable systems would benefit from the ability to anticipate user-object interactions. Even if this task is not trivial, the First Person Vision paradigm can provide important cues to address this challenge. We propose to exploit the dynamics of the scene to recognize next-active-objects before an object interaction begins. We train a classifier to discriminate trajectories leading to an object activation from all others and forecast next-active-objects by analyzing fixed-length trajectory segments within a temporal sliding window. The proposed method compares favorably with respect to several baselines on the Activity of Daily Living (ADL) egocentric dataset comprising 10 hours of videos acquired by 20 subjects while performing unconstrained interactions with several objects.

cs.CV↗

arXiv2018

Scaling Egocentric Vision: The EPIC-KITCHENS Dataset

First-person vision is gaining interest as it offers a unique viewpoint on people's interaction with objects, their attention, and even intention. However, progress in this challenging domain has been relatively slow due to the lack of sufficiently large datasets. In this paper, we introduce EPIC-KITCHENS, a large-scale egocentric video benchmark recorded by 32 participants in their native kitchen environments. Our videos depict nonscripted daily activities: we simply asked each participant to start recording every time they entered their kitchen. Recording took place in 4 cities (in North America and Europe) by participants belonging to 10 different nationalities, resulting in highly diverse cooking styles. Our dataset features 55 hours of video consisting of 11.5M frames, which we densely labeled for a total of 39.6K action segments and 454.3K object bounding boxes. Our annotation is unique in that we had the participants narrate their own videos (after recording), thus reflecting true intention, and we crowd-sourced ground-truths based on these. We describe our object, action and anticipation challenges, and evaluate several baselines over two test splits, seen and unseen kitchens. Dataset and Project page: http://epic-kitchens.github.io

cs.CV↗

arXiv2018

A Multi-Task Learning Approach for Meal Assessment

Key role in the prevention of diet-related chronic diseases plays the balanced nutrition together with a proper diet. The conventional dietary assessment methods are time-consuming, expensive and prone to errors. New technology-based methods that provide reliable and convenient dietary assessment, have emerged during the last decade. The advances in the field of computer vision permitted the use of meal image to assess the nutrient content usually through three steps: food segmentation, recognition and volume estimation. In this paper, we propose a use one RGB meal image as input to a multi-task learning based Convolutional Neural Network (CNN). The proposed approach achieved outstanding performance, while a comparison with state-of-the-art methods indicated that the proposed approach exhibits clear advantage in accuracy, along with a massive reduction of processing time.

cs.CV↗