Search Results for author:
Found 33 papers, 9 papers with code
3M-TRANSFORMER: A Multi-Stage Multi-Stream Multimodal Transformer for Embodied Turn-Taking Prediction
Predicting turn-taking in multiparty conversations has many practical applications in human-computer/robot interaction.
Debiased-CAM to mitigate systematic error with faithful visual explanations of machine learning
We present Debiased-CAM to recover explanation faithfulness across various bias types and levels by training a multi-input, multi-task model with auxiliary tasks for explanation and bias level predictions.
Enhancing Egocentric 3D Pose Estimation with Third Person Views
In this paper, we propose a novel approach to enhance the 3D body pose estimation of a person computed from videos captured from a single wearable camera.
Learning grounded word meaning representations on similarity graphs
This paper introduces a novel approach to learn visually grounded meaning representations of words as low-dimensional node embeddings on an underlying graph hierarchy.
Graph Constrained Data Representation Learning for Human Motion Segmentation
Recently, transfer subspace learning based approaches have shown to be a valid alternative to unsupervised subspace clustering and temporal data clustering for human motion segmentation (HMS).
Interaction-GCN: A Graph Convolutional Network based framework for social interaction recognition in egocentric videos
In this paper we propose a new framework to categorize social interactions in egocentric videos, we named InteractionGCN.
Modeling long-term interactions to enhance action recognition
In this paper, we propose a new approach to under-stand actions in egocentric videos that exploits the semantics of object interactions at both frame and temporal levels.
Debiased-CAM to mitigate image perturbations with faithful visual explanations of machine learning
We present Debiased-CAM to recover explanation faithfulness across various bias types and levels by training a multi-input, multi-task model with auxiliary tasks for explanation and bias level predictions.
Seeing and Hearing Egocentric Actions: How Much Can We Learn?
Our interaction with the world is an inherently multimodal experience.
Learning event representations for temporal segmentation of image sequences by dynamic graph embedding
The main advantage of DGE over state-of-the-art self-supervised approaches is that it does not require any training set, but instead learns iteratively from the data itself a low-dimensional embedding that reflects their temporal and semantic similarity.
Enhancing temporal segmentation by nonlocal self-similarity
Temporal segmentation of untrimmed videos and photo-streams is currently an active area of research in computer vision and image processing.
How Much Does Audio Matter to Recognize Egocentric Object Interactions?
Sounds are an important source of information on our daily interactions with objects.
Social Relation Recognition in Egocentric Photostreams
This paper proposes an approach to automatically categorize the social interactions of a user wearing a photo-camera 2fpm, by relying solely on what the camera is seeing.
On the Role of Event Boundaries in Egocentric Activity Recognition from Photostreams
Event boundaries play a crucial role as a pre-processing step for detection, localization, and recognition tasks of human activities in videos.
Smartphone picture organization: A hierarchical approach
Unlike photo collections captured by a digital camera, which typically are pre-processed by the user who organizes them into event-related folders, smartphone pictures are automatically stored in the cloud.
Batch-based Activity Recognition from Egocentric Photo-Streams Revisited
Wearable cameras can gather large a\-mounts of image data that provide rich visual information about the daily activities of the wearer.
Social Style Characterization from Egocentric Photo-streams
This paper proposes a system for automatic social pattern characterization using a wearable photo-camera.
Detecting Hands in Egocentric Videos: Towards Action Recognition
Recently, there has been a growing interest in analyzing human daily activities from data collected by wearable cameras.
Towards social pattern characterization in egocentric photo-streams
Following the increasingly popular trend of social interaction analysis in egocentric vision, this manuscript presents a comprehensive study for automatic social pattern characterization of a wearable photo-camera user, by relying on the visual analysis of egocentric photo-streams.
Batch-Based Activity Recognition from Egocentric Photo-Streams
However, one of its main technical challenges is to deal with the low frame rate of wearable photo-cameras, which causes abrupt appearance changes between consecutive frames.
Recognizing Activities of Daily Living from Egocentric Images
Recognizing Activities of Daily Living (ADLs) has a large number of health applications, such as characterize lifestyle for habit improvement, nursing and rehabilitation services.
Pay Attention to Those Sets! Learning Quantification from Images
We however argue that precisely identifying the composition of the sets is not only beyond current state-of-the-art models but perhaps even detrimental to a task that is most efficiently performed by refining the approximate numerosity estimator of the system.
R-Clustering for Egocentric Video Segmentation
In this paper, we present a new method for egocentric video temporal segmentation based on integrating a statistical mean change detector and agglomerative clustering(AC) within an energy-minimization framework.
Clothing and People - A Social Signal Processing Perspective
In our society and century, clothing is not anymore used only as a means for body protection.
All the people around me: face discovery in egocentric photo-streams
Given an unconstrained stream of images captured by a wearable photo-camera (2fpm), we propose an unsupervised bottom-up approach for automatic clustering appearing faces into the individual identities present in these data.
With Whom Do I Interact? Detecting Social Interactions in Egocentric Photo-streams
Given a user wearing a low frame rate wearable camera during a day, this work aims to automatically detect the moments when the user gets engaged into a social interaction solely by reviewing the automatically captured photos by the worn camera.
SR-Clustering: Semantic Regularized Clustering for Egocentric Photo Streams Segmentation
While wearable cameras are becoming increasingly popular, locating relevant information in large unstructured collections of egocentric images is still a tedious and time consuming processes.
A Computational Model for Amodal Completion
This paper presents a computational model to recover the most likely interpretation of the 3D scene structure from a planar image, where some objects may occlude others.
Semantic Summarization of Egocentric Photo Stream Events
With the rapid increase of users of wearable cameras in recent years and of the amount of data they produce, there is a strong need for automatic retrieval and summarization techniques.
Active skeleton for bacteria modeling
The investigation of spatio-temporal dynamics of bacterial cells and their molecular components requires automated image analysis tools to track cell shape properties and molecular component locations inside the cells.
Towards Storytelling from Visual Lifelogging: An Overview
Visual lifelogging consists of acquiring images that capture the daily experiences of the user by wearing a camera over a long period of time.
Particle detection and tracking in fluorescence time-lapse imaging: a contrario approach
This paper proposes a probabilistic approach for the detection and the tracking of particles in fluorescent time-lapse imaging.
Multi-Face Tracking by Extended Bag-of-Tracklets in Egocentric Videos
In this paper, we propose a novel method to find correspondences of multiple faces in low temporal resolution egocentric videos acquired through a wearable camera.
