Related papers: Making Third Person Techniques Recognize First-Per…
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…
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)…
This paper proposes an interaction reasoning network for modelling spatio-temporal relationships between hands and objects in video. The proposed interaction unit utilises a Transformer module to reason about each acting hand, and its…
Long-term action anticipation from egocentric video is critical for applications such as human-computer interaction and assistive technologies, where anticipating user intent enables proactive and context-aware AI assistance. However,…
This work presents a novel approach for the early recognition of the type of a laparoscopic surgery from its video. Early recognition algorithms can be beneficial to the development of 'smart' OR systems that can provide automatic…
In this paper, we aim to address the problem of human interaction recognition in videos by exploring the long-term inter-related dynamics among multiple persons. Recently, Long Short-Term Memory (LSTM) has become a popular choice to model…
Lifelogging devices are spreading faster everyday. This growth can represent great benefits to develop methods for extraction of meaningful information about the user wearing the device and his/her environment. In this paper, we propose a…
Spatio-temporal contexts are crucial in understanding human actions in videos. Recent state-of-the-art Convolutional Neural Network (ConvNet) based action recognition systems frequently involve 3D spatio-temporal ConvNet filters, chunking…
In egocentric videos, actions occur in quick succession. We capitalise on the action's temporal context and propose a method that learns to attend to surrounding actions in order to improve recognition performance. To incorporate the…
Moments capture a huge part of our lives. Accurate recognition of these moments is challenging due to the diverse and complex interpretation of the moments. Action recognition refers to the act of classifying the desired action/activity…
Video understanding is one of the most challenging topics in computer vision. In this paper, a four-stage video understanding pipeline is presented to simultaneously recognize all atomic actions and the single on-going activity in a video.…
Egocentric video grounding is a crucial task for embodied intelligence applications, distinct from exocentric video moment localization. Existing methods primarily focus on the distributional differences between egocentric and exocentric…
Human actions often involve complex interactions across several inter-related objects in the scene. However, existing approaches to fine-grained video understanding or visual relationship detection often rely on single object representation…
Human activity recognition is typically addressed by detecting key concepts like global and local motion, features related to object classes present in the scene, as well as features related to the global context. The next open challenges…
Accurately identifying hands in images is a key sub-task for human activity understanding with wearable first-person point-of-view cameras. Traditional hand segmentation approaches rely on a large corpus of manually labeled data to generate…
This paper aims to develop a new architecture that can make full use of the feature maps of convolutional networks. To this end, we study a number of methods for video-based person re-identification and make the following findings: 1)…
Current upper extremity outcome measures for persons with cervical spinal cord injury (cSCI) lack the ability to directly collect quantitative information in home and community environments. A wearable first-person (egocentric) camera…
The lack of large-scale real datasets with annotations makes transfer learning a necessity for video activity understanding. We aim to develop an effective method for few-shot transfer learning for first-person action classification. We…
This chapter aims to aid the development of Cyber-Physical Systems (CPS) in automated understanding of events and activities in various applications of video-surveillance. These events are mostly captured by drones, CCTVs or novice and…
Event boundaries play a crucial role as a pre-processing step for detection, localization, and recognition tasks of human activities in videos. Typically, although their intrinsic subjectiveness, temporal bounds are provided manually as…