Mattia Soldan

King Abdullah University of Science and Technology | KAUST · Division of Computer, Electrical and Mathematical Sciences and Engineering (CEMSE)

In Large-Scale Sensor Networks where powered sinks are not present, sensors must not only collect data but also store it until an external entity gathers the sensed information. A smart approach is to consider a network configuration in which K out of the N total nodes are able to sense the environment and collect information packets while the rema...

In this paper, we introduce the task of retrieving relevant video moments from a large corpus of untrimmed, unsegmented videos given a natural language query. Our task poses unique challenges as a system must efficiently identify both the relevant videos and localize the relevant moments in the videos. This task is in contrast to prior work that lo...

Smartphones and wearable devices are fast growing technologies that, in conjunction with advances in wireless sensor hardware, are enabling ubiquitous sensing applications. Wearables are suitable for indoor and outdoor scenarios, can be placed on many parts of the human body and can integrate a large number of sensors capable of gathering physiolog...

Grounding language queries in videos aims at identifying the time interval (or moment) semantically relevant to a language query. The solution to this challenging task demands the understanding of videos' and queries' semantic content and the fine-grained reasoning about their multi-modal interactions. Our key idea is to recast this challenge into...

The recent and increasing interest in video-language research has driven the development of large-scale datasets that enable data-intensive machine learning techniques. In comparison, limited effort has been made at assessing the fitness of these datasets for the video-language grounding task. Recent works have begun to discover significant limitat...

Video activity localization aims at understanding the semantic content in long untrimmed videos and retrieving actions of interest. The retrieved action with its start and end locations can be used for highlight generation, temporal action detection, etc. Unfortunately, learning the exact boundary location of activities is highly challenging becaus...

The recent introduction of the large-scale long-form MAD dataset for language grounding in videos has enabled researchers to investigate the performance of current state-of-the-art methods in the long-form setup, with unexpected findings. In fact, current grounding methods alone fail at tackling this challenging task and setup due to their inabilit...

In this report, we propose a video-language pretraining (VLP) based solution \cite{kevin2022egovlp} for four Ego4D challenge tasks, including Natural Language Query (NLQ), Moment Query (MQ), Object State Change Classification (OSCC), and PNR Localization (PNR). Especially, we exploit the recently released Ego4D dataset \cite{grauman2021ego4d} to pi...

Video-Language Pretraining (VLP), aiming to learn transferable representation to advance a wide range of video-text downstream tasks, has recently received increasing attention. Dominant works that achieve strong performance rely on large-scale, 3rd-person video-text datasets, such as HowTo100M. In this work, we exploit the recently released Ego4D...