Shape-changing interfaces (SCIs) dynamically alter their form, an inherent characteristic that introduces fragility into their design. As a result, users’ perceptions of an interface’s fragility or its potential to move or break may influence their interaction, however the extent of this effect is unclear. To address this gap, we conducted a qualitative study (N = 18) using video stimuli showcasing 20 existing SCIs. Through thematic analysis, we identified key factors impacting perceived fragility and formalized these into a framework. We then conducted a second study (N = 36) for which we fabricated SCIs that varied across selected fragility-related dimensions. We recorded user interactions and compared how the selected dimensions shaped manipulation of the objects and how they were considered by users. Together, these studies provide a structured foundational understanding of perceived fragility in SCIs and offer insights to enhance perceived robustness and inform future SCI development.

Recent progress in Large Language Models (LLMs) has enabled advanced reasoning and zero-shot recognition for human activity understanding with ambient sensor data. However, widely used multi-resident datasets such as CASAS, ARAS, and MARBLE lack natural language context and fine-grained annotation, limiting the full exploitation of LLM capabilities in realistic smart environments. To address this gap, we present MuRAL (Multi-Resident Ambient sensor dataset with natural Language), comprising over 21 hours of multi-user sensor data from 21 sessions in a smart home. MuRAL uniquely features detailed natural language descriptions, explicit resident identities, and rich activity labels, all situated in complex, dynamic, multi-resident scenarios. We benchmark state-of-the-art LLMs on MuRAL for three core tasks: subject assignment, action description, and activity classification. Results show that current LLMs still face major challenges on MuRAL, especially in maintaining accurate resident assignment over long sequences, generating precise action descriptions, and effectively integrating context for activity prediction. The dataset is publicly available at: https://mural.imag.fr/.

In this work, we address the task of unconditional head motion generation to animate still human faces in a low-dimensional semantic space from a single reference pose. Different from traditional audio-conditioned talking head generation that seldom puts emphasis on realistic head motions, we devise a GAN-based architecture that learns to synthesize rich head motion sequences over long duration while maintaining low error-accumulation levels. In particular, the autoregressive generation of incremental outputs ensures smooth trajectories, while a multi-scale discriminator on input pairs drives generation toward better handling of high- and low-frequency signals and less mode collapse. We experimentally demonstrate the relevance of the proposed method and show its superiority compared to models that attained state-of-the-art performances on similar tasks.

Human Activity Recognition (HAR) is one of the central problems in fields such as healthcare, elderly care, and security at home. However, traditional ambient-sensor-based HAR approaches face challenges including data scarcity, difficulties in model generalization, and the complexity of recognizing activities in multi-person scenarios. This paper proposes a large-language-model-based framework called LAHAR which addresses HAR in multi-person scenarios. By endowing LLMs with inter-sensor relevance estimation and sensor-subject relevance estimation abilities, LAHAR can assign sensor events to the corresponding subjects. By providing action-level descriptions of sensor events and subsequently performing activity-level reasoning based on these descriptions, LAHAR is ultimately able to process data spanning several tens of hours with second-level resolution and results in an activity timeline for each subject. We validated LAHAR on the ARAS dataset. The results demonstrate that LAHAR achieves comparable accuracy to the state-of-the-art method at higher resolutions and maintains robustness in multiperson scenarios.

In this paper, we describe a graph-based algorithm that uses the features obtained by a self-supervised transformer to detect and segment salient objects in images and videos. With this approach, the image patches that compose an image or video are organised into a fully connected graph, in which the edge between each pair of patches is labeled with a similarity score based on the features learned by the transformer. Detection and segmentation of salient objects can then be formulated as a graph-cut problem and solved using the classical Normalized Cut algorithm. Despite the simplicity of this approach, it achieves state-of-the-art results on several common image and video detection and segmentation tasks. For unsupervised object discovery, this approach outperforms the competing approaches by a margin of 6.1%, 5.7%, and 2.6% when tested with the VOC07, VOC12, and COCO20 K datasets. For the unsupervised saliency detection task in images, this method improves the score for Intersection over Union (IoU) by 4.4%, 5.6% and 5.2%. When tested with the ECSSD, DUTS, and DUT-OMRON datasets. This method also achieves competitive results for unsupervised video object segmentation tasks with the DAVIS, SegTV2, and FBMS datasets.

Prediction of human actions in social interactions has important applications in the design of social robots or artificial avatars. In this paper, we focus on a unimodal representation of interactions and propose to tackle interaction generation in a data-driven fashion. In particular, we model human interaction generation as a discrete multi-sequence generation problem and present SocialInteractionGAN, a novel adversarial architecture for conditional interaction generation. Our model builds on a recurrent encoder-decoder generator network and a dual-stream discriminator, that jointly evaluates the realism of interactions and individual action sequences and operates at different time scales. Crucially, contextual information on interacting participants is shared among agents and reinjected in both the generation and the discriminator evaluation processes. Experiments show that albeit dealing with low dimensional data, SocialInteractionGAN succeeds in producing high realism action sequences of interacting people, comparing favorably to a diversity of recurrent and convolutional discriminator baselines, and we argue that this work will constitute a first stone towards higher dimensional and multimodal interaction generation. Evaluations are conducted using classical GAN metrics, that we specifically adapt for discrete sequential data. Our model is shown to properly learn the dynamics of interaction sequences, while exploiting the full range of available actions.

Transformers trained with self-supervision using selfdistillation loss (DINO) have been shown to produce attention maps that highlight salient foreground objects. In this paper, we show a graph-based method that uses the selfsupervised transformer features to discover an object from an image. Visual tokens are viewed as nodes in a weighted graph with edges representing a connectivity score based on the similarity of tokens. Foreground objects can then be segmented using a normalized graph-cut to group self-similar regions. We solve the graph-cut problem using spectral clustering with generalized eigen-decomposition and show that the second smallest eigenvector provides a cutting solution since its absolute value indicates the likelihood that a token belongs to a foreground object. Despite its simplicity, this approach significantly boosts the performance of unsupervised object discovery: we improve over the recent state-of-the-art LOST by a margin of 6.9%, 8.1%, and 8.1% respectively on the VOC07, VOC12, and COCO20K. The performance can be further improved by adding a second stage class-agnostic detector (CAD). Our proposed method can be easily extended to unsupervised saliency detection and weakly supervised object detection. For unsupervised saliency detection, we improve IoU for 4.9%, 5.2%, 12.9% on ECSSD, DUTS, DUT-OMRON respectively compared to state-of-the-art. For weakly supervised object detection, we achieve competitive performance on CUB and ImageNet. Our code is available at: https://www.m-psi.fr/Papers/TokenCut2022/

Decision making for autonomous driving in urban environments is challenging due to the complexity of the road structure and the uncertainty in the behavior of diverse road users. Traditional methods consist of manually designed rules as the driving policy, which require expert domain knowledge, are difficult to generalize and might give sub-optimal results as the environment gets complex. Whereas, using reinforcement learning, optimal driving policy could be learned and improved automatically through several interactions with the environment. However, current research in the field of reinforcement learning for autonomous driving is mainly focused on highway setup with little to no emphasis on urban environments. In this work, a deep reinforcement learning based decision-making approach for high-level driving behavior is proposed for urban environments in the presence of pedestrians. For this, the use of Deep Recurrent Q-Network (DRQN) is explored, a method combining state-of-the art Deep Q-Network (DQN) with a long term short term memory (LSTM) layer helping the agent gain a memory of the environment. A 3-D state representation is designed as the input combined with a well defined reward function to train the agent for learning an appropriate behavior policy in a real-world like urban simulator. The proposed method is evaluated for dense urban scenarios and compared with a rule-based approach and results show that the proposed DRQN based driving behavior decision maker outperforms the rule-based approach.

This article presents our unimodal privacy-safe and non-individual proposal for the audio-video group emotion recognition subtask at the Emotion Recognition in the Wild (EmotiW) Challenge 2020. This sub challenge aims to classify in the wild videos into three categories: Positive, Neutral and Negative. Recent deep learning models have shown tremendous advances in analyzing interactions between people, predicting human behavior and affective evaluation. Nonetheless, their performance comes from individual-based analysis, which means summing up and averaging scores from individual detections, which inevitably leads to some privacy issues. In this research, we investigated a frugal approach towards a model able to capture the global moods from the whole image without using face or pose detection, or any individual-based feature as input. The proposed methodology mixes state-of-the-art and dedicated synthetic corpora as training sources. With an in-depth exploration of neural network architectures for group-level emotion recognition, we built a VGG-based model achieving 59.13% accuracy on the VGAF test set (eleventh place of the challenge). Given that the analysis is unimodal based only on global features and that the performance is evaluated on a real-world dataset, these results are promising and let us envision extending this model to multimodality for classroom ambiance evaluation, our final target application.

This article reports on an investigation of the use of convolutional neural networks to predict the visual attention of chess players. The visual attention model described in this article has been created to generate saliency maps that capture hierarchical and spatial features of chessboard, in order to predict the probability fixation for individual pixels Using a skip-layer architecture of an autoencoder, with a unified decoder, we are able to use multiscale features to predict saliency of part of the board at different scales, showing multiple relations between pieces. We have used scan path and fixation data from players engaged in solving chess problems, to compute 6600 saliency maps associated to the corresponding chess piece configurations. This corpus is completed with synthetically generated data from actual games gathered from an online chess platform. Experiments realized using both scan-paths from chess players and the CAT2000 saliency dataset of natural images, highlights several results. Deep features, pretrained on natural images, were found to be helpful in training visual attention prediction for chess. The proposed neural network architecture is able to generate meaningful saliency maps on unseen chess configurations with good scores on standard metrics. This work provides a baseline for future work on visual attention prediction in similar contexts.

Autonomous Vehicles navigating in urban areas have a need to understand and predict future pedestrian behavior for safer navigation. This high level of situational awareness requires observing pedestrian behavior and extrapolating their positions to know future positions. While some work has been done in this field using Hidden Markov Models (HMMs), one of the few observed drawbacks of the method is the need for informed priors for learning behavior. In this work, an extension to the Growing Hidden Markov Model (GHMM) method is proposed to solve some of these drawbacks. This is achieved by building on existing work using potential cost maps and the principle of Natural Vision. As a consequence, the proposed model is able to predict pedestrian positions more precisely over a longer horizon compared to the state of the art. The method is tested over “legal” and “illegal” behavior of pedestrians, having trained the model with sparse observations and partial trajectories. The method, with no training data, is compared against a trained state of the art model. It is observed that the proposed method is robust even in new, previously unseen areas.

In a multi-user context, the Bluetooth data from the smartphone could give an approximation of the distance between users. Meanwhile, the Wi-Fi data can be used to calculate the user's position directly. However, both the Wi-Fi-based position outputs and Bluetooth-based distances are affected by some degree of noise. In our work, we propose several approaches to combine the two types of outputs for improving the tracking accuracy in the context of collaborative positioning. The two proposed approaches attempt to build a model for measuring the errors of the Bluetooth output and Wi-Fi output. In a non-temporal approach, the model establishes the relationship in a specific interval of the Bluetooth output and Wi-Fi output. In a temporal approach, the error measurement model is expanded to include the time component between users' movement. To evaluate the performance of the two approaches, we collected the data from several multi-user scenarios in indoor environment. The results show that the proposed approaches could reach a distance error around 3.0m for 75 percent of time, which outperforms the positioning results of the standard Wi-Fi fingerprinting model.

This article deals with the specific context of an autonomous car navigating in an urban center within a shared space between pedestrians and cars. The driver delegates the control to the autonomous system while remaining seated in the driver's seat. The proposed study aims at giving a first insight into the definition of human perception of space applied to vehicles by testing the existence of a personal space around the car. It aims at measuring proxemic information about the driver's comfort zone in such conditions. Proxemics, or human perception of space, has been largely explored when applied to humans or to robots, leading to the concept of personal space, but poorly when applied to vehicles. In this article, we highlight the existence and the characteristics of a zone of comfort around the car which is not correlated to the risk of a collision between the car and other road users. Our experiment includes 19 volunteers using a virtual reality headset to look at 30 scenarios filmed in 360° from the point of view of a passenger sitting in the driver's seat of an autonomous car. They were asked to say “stop” when they felt discomfort visualizing the scenarios. As said, the scenarios voluntarily avoid collision effect as we do not want to measure fear but discomfort. The scenarios involve one or three pedestrians walking past the car at different distances from the wings of the car, relative to the direction of motion of the car, on both sides. The car is either static or moving straight forward at different speeds. The results indicate the existence of a comfort zone around the car in which intrusion causes discomfort. The size of the comfort zone is sensitive neither to the side of the car where the pedestrian passes nor to the number of pedestrians. In contrast, the feeling of discomfort is relative to the car's motion (static or moving). Another outcome from this study is an illustration of the usage of first person 360° video and a virtual reality headset to evaluate feelings of a passenger within an autonomous car.

Pretend play is a storytelling technique, naturally used from very young ages, which relies on object substitution to represent the characters of the imagined story. We propose a system which assists the storyteller by generating a virtualized story from a recorded dialogue performed with 3D printed figurines. We capture the gestures and facial expressions of the storyteller using Kinect cameras and IMU sensors and transfer them to their virtual counterparts in the story-world. As a proof-of-concept, we demonstrate our system with an improvised story involving a prince and a witch, which was successfully recorded and transferred into 3D animation.

Movements are an important part of robot design and we need dedicated tools to design them. As previous research has shown, 3D animation techniques are of great use to animate a robot. However, most robots don't benefit from an animation tool and therefore from animation artists knowledge. We present an open-source robot animation software to address this issue and describe some principles for designing a robot animation software derived from the specificity of robot as a medium.

This paper introduces our work in the framework of Track 3 of the IPIN 2016 Indoor Localization Competition, which addresses the smartphone-based tracking problem in an offline manner. Our approach splits the path-reconstruction into several smaller tasks, including building identification, floor identification, user direction and speed inference. For each task, a specific set of data from the provided log data is used. Evaluation is carried out using a cross validation scheme. To produce the robustness again noisy data, we combine several approaches into one on the basis of their testing results. By testing on the provided training data, we have a good accuracy on building and floor identification. For the task of tracking the user's position within the floor, the result is 10m at 3rd-quarter distance error after 3 minutes of walking.

New technologies and especially robotics is going towards more natural user interfaces. Works have been done in different modality of interaction such as sight (visual computing), and audio (speech and audio recognition) but some other modalities are still less researched. The touch modality is one of the less studied in HRI but could be valuable for naturalistic interaction. However touch signals can vary in semantics. It is therefore necessary to be able to recognize touch gestures in order to make human-robot interaction even more natural. We propose a method to recognize touch gestures. This method was developed on the CoST corpus and then directly applied on the HAART dataset as a participation of the Social Touch Challenge at ICMI 2015. Our touch gesture recognition process is detailed in this article to make it reproducible by other research teams. Besides features set description, we manually filtered the training corpus to produce 2 datasets. For the challenge, we submitted 6 different systems. A Support Vector Machine and a Random Forest classifiers for the HAART dataset. For the CoST dataset, the same classifiers are tested in two conditions: using all or filtered training datasets. As reported by organizers, our systems have the best correct rate in this year's challenge (70.91% on HAART, 61.34% on CoST). Our performances are slightly better that other participants but stay under previous reported state-of-the-art results.

Since the commercialization of low cost RGB-D sensors, like the Kinect, more and more indoor robots have been equipped with this kind of sensors to perform tasks as people tracking or gesture recognition. Nevertheless, as far as we know from the literature, studies do not consider the limits of the sensors in term of motion speed, position of the sensor on the robot, etc. In this work, we propose to provide a corpus dedicated to low level RGB-D algorithms benchmarking. Originality of our approach is the use of dummies in order to play static users in the environment. This idea let us vary other variables that can impact algorithm performance: linear/angular speed of the robot, trajectory of the robot, RGB-D sensor height and vertical angle of view, number and relative position of dummies and furniture position. This paper first describes the experimental platform used to perform the acquisitions and the environment setup required to reproduce the dataset. Then, a precise description of all available data is given. We will see that, as this corpus contains a lot of configurations, it will allow researchers to investigate how these variables impact the results of their algorithms.

Abstract: This paper deals with the problem of implementing a context model for a smart environment. The problem has already been addressed several times using many different data‐ or problem‐driven methods. In order to separate the modelling phase from implementation, we first represent the context model by a network of situations. Then, different implementations can be automatically generated from this context model depending on user needs and underlying perceptual components. Two different implementations are proposed in this paper: a deterministic one based on Petri nets and a probabilistic one based on hidden Markov models. Both implementations are illustrated and applied to real‐world problems.

International audience

This paper proposes an in-depth look at the influence of different speech and audio codecs on the performance of our continuous speech recognition engine. GSM full rate, G711, G723.1 and MPEG coders are investigated. It is shown that MPEG transcoding degrades the speech recognition performance for low bitrates whereas performance remains acceptable for specialized speech coders like GSM or G711. A new strategy is proposed to cope with degradation due to low bitrate coding. The acoustic models of the speech recognition system are trained with transcoded speech (one acoustic model for each speech/audio codec). First results show that this strategy allows one to recover acceptable performance.

International audience