Publications by Andrea Cavallaro

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

We present an MPEG 7 compliant description of generic video sequences aiming at their scalable transmission and reconstruction. The proposed method allows efficient and flexible video coding while keeping the advantages of textual descriptions in database applications. Visual objects are described in terms of their shape, color, texture and motion; these features can be extracted automatically and are sufficient in a wide range of applications. To permit partial sequence reconstruction, at least one simple

Change detection is a temporal segmentation tool aiming at identifying changes in image sets or image sequences at two different times. Many change detection algorithms have been proposed over the past decade for the generation of video objects in a wide range of applications, ranging from interactive multimedia to remote surveillance. Most of these algorithms are tailored to the specific application at hand. Therefore there is a need of a general model for change detection which could support the choice of

In this paper, we present a video encoding scheme that uses object-based adaptation to deliver surveillance video to mobile devices. The method relies on a set of complementary video adaptation strategies and generates content that matches various appliance and network resources. Prior to encoding, some of the adaptation strategies exploit video object segmentation and selective filtering in order to improve the perceived quality. Moreover, object segmentation enables the generation of automatic summaries a

Perceptual prefiltering is the process of enhancing relevant portions of an image or of a video, and of simplifying contextual information in order to improve the perceived quality or the compression ratio. In this paper, we discuss the results of subjective quality evaluation experiments performed to assess the impact of perceptual prefiltering on video coding and we propose an objective quality metric that mimics the behavior of human observers. The predicted performance of the proposed metric is consiste

We present an algorithm for tracking video object which is based on an hybrid strategy. This strategy uses both object and region information to solve the correspondence problem. Low level descriptors are exploited to track object s regions and to cope wit ...

This paper presents a new scalable and highly flexible color image coder based on a Matching Pursuit expansion. The Matching Pursuit algorithm provides an intrinsically progressive stream and the proposed coder allows us to reconstruct color information from the first bit received. In order to efficiently capture edges in natural images, the dictionary of atoms is built by translation, rotation and anisotropic refinement of a wavelet-like mother function. This dictionary is moreover invariant under shifts a

Implicit hate speech (IHS) is indirect language that conveys prejudice or hatred through subtle cues, sarcasm or coded terminology. IHS is challenging to detect as it does not include explicit derogatory or inflammatory words. To address this challenge, task-specific pipelines can be complemented with external knowledge or additional information such as context, emotions and sentiment data. In this paper, we show that, by solely fine-tuning recent general-purpose embedding models based on large language mod

This paper introduces a system for video object extraction useful for general applications where foreground objects move within a slow changing background. Surveillance of indoor and outdoor sequences is a typical example. The originality of the approach resides in two related components. First, the statistical change detection used in the system does not require any sophisticated parametric tuning as it is based on a probabilistic method. Second, the change is detected between a current instance of the sce

The real-time estimation through vision of the physical properties of objects manipulated by humans is important to inform the control of robots for performing accurate and safe grasps of objects handed over by humans. However, estimating the 3D pose and d ...

Human-robot collaboration requires the contactless estimation of the physical properties of containers manipulated by a person, for example while pouring content in a cup or moving a food box. Acoustic and visual signals can be used to estimate the physica ...

Subjective interpretation and content diversity make predicting whether an image is private or public a challenging task. Graph neural networks combined with convolutional neural networks (CNNs), which consist of 14,000 to 500 millions parameters, generate ...

Local illumination changes due to shadows often reduce the quality of object-based video composition and mislead object recognition. This problem makes shadow detection a desirable tool for a wide range of applications, such as video production and visual ...

In this paper, we propose an automatic method for the objective evaluation of segmentation results. The method is based on computing the deviation of the segmentation results from a reference segmentation. The discrepancy between two results is weighted based on spatial and temporal contextual information, by taking into account the way humans perceive visual information. The metric is useful for applications where the final judge of the quality is a human observer or the results of segmentation are otherwi

Visual Language Models (VLMs) are often used for zero-shot detection of visual attributes in the image. We present a zero-shot evaluation of open-source VLMs for privacy-related attribute recognition. We identify the attributes for which VLMs exhibit strong inter-annotator agreement, and discuss the disagreement cases of human and VLM annotations. Our results show that when evaluated against human annotations, VLMs tend to predict the presence of privacy attributes more often than human annotators. In addit

Visual affordance segmentation identifies the surfaces of an object an agent can interact with. Common challenges for the identification of affordances are the variety of the geometry and physical properties of these surfaces as well as occlusions. In this ...

Recent works in hand-object reconstruction mainly focus on the single-view and dense multi-view settings. On the one hand, single-view methods can leverage learned shape priors to generalise to unseen objects but are prone to inaccuracies due to occlusions ...

While hate speech detection (HSD) has been extensively studied in text, existing multi-modal approaches remain limited, particularly in videos. As modalities are not always individually informative, simple fusion methods fail to fully capture inter-modal dependencies. Moreover, previous work often omits relevant modalities such as on-screen text and audio, which may contain subtle hateful content and thus provide essential cues, both individually and in combination with others. In this paper, we present MM-

Explainable AI (XAI) methods aim to describe the decision process of deep neural networks. Early XAI methods produced visual explanations, whereas more recent techniques generate multimodal explanations that include textual information and visual represent ...

Autonomous vehicles (AVs) rely on accurate and robust sensor observations for safety-critical decision making in a variety of conditions. The fundamental building blocks of such systems are sensors and classifiers that process ultrasound, radar, GPS, lidar ...

Andrea Cavallaro

Chat with Graph Search

MPEG-7 Description of Generic Video Objects for Scene Reconstruction

Classification of change detection algorithms for object-based applications

Surveillance Video for Mobile Devices

Evaluating Perceptually Prefiltered Video

Tracking Video Objects in Cluttered Background

Color image scalable coding with Matching Pursuit

Color Image Scalable Coding with Matching Pursuit

Specializing General-purpose LLM Embeddings for Implicit Hate Speech Detection across Datasets

Video Object Extraction based on Adaptive Background and Statistical Change Detection

Benchmark for Human-to-Robot Handovers of Unseen Containers with Unknown Filling

Audio-Visual Object Classification For Human-Robot Collaboration

Learning Privacy from Visual Entities

Shadow-aware object-based video processing

Objective evaluation of segmentation quality using spatio-temporal context

Which Private Attributes do VLMs Agree on and Predict Well?

Affordance segmentation of hand-occluded containers from exocentric images

Sparse multi-view hand-object reconstruction for unseen environments

MM-HSD: Multi-Modal Hate Speech Detection in Videos

BLACK-BOX ATTACKS ON IMAGE ACTIVITY PREDICTION AND ITS NATURAL LANGUAGE EXPLANATIONS

Toward Robust Sensing for Autonomous Vehicles: An Adversarial Perspective