相关论文: A gaze driven fast-forward method for first-person…

We address the challenging task of anticipating human-object interaction in first person videos. Most existing methods ignore how the camera wearer interacts with the objects, or simply consider body motion as a separate modality. In…

Many cameras implement auto-focus functionality. However, they typically require the user to manually identify the location to be focused on. While such an approach works for temporally-sparse autofocusing functionality (e.g., photo…

Eliminating time-consuming post-production processes and delivering high-quality videos in today's fast-paced digital landscape are the key advantages of real-time approaches. To address these needs, we present Real Time GAZED: a real-time…

We present a technique that uses images, videos and sensor data taken from first-person point-of-view devices to perform egocentric field-of-view (FOV) localization. We define egocentric FOV localization as capturing the visual information…

This paper addresses the challenging problem of estimating the general visual attention of people in images. Our proposed method is designed to work across multiple naturalistic social scenarios and provides a full picture of the subject's…

Egocentric videos can bring a lot of information about how humans perceive the world and interact with the environment, which can be beneficial for the analysis of human behaviour. The research in egocentric video analysis is developing…

In cinema, large camera lenses create beautiful shallow depth of field (DOF), but make focusing difficult and expensive. Accurate cinema focus usually relies on a script and a person to control focus in realtime. Casual videographers often…

Recently, breakthroughs in video modeling have allowed for controllable camera trajectories in generated videos. However, these methods cannot be directly applied to user-provided videos that are not generated by a video model. In this…

We focus on first-person action recognition from egocentric videos. Unlike third person domain, researchers have divided first-person actions into two categories: involving hand-object interactions and the ones without, and developed…

Wearable cameras allow people to record their daily activities from a user-centered (First Person Vision) perspective. Due to their favorable location, wearable cameras frequently capture the hands of the user, and may thus represent a…

Egocentric cameras are becoming increasingly popular and provide us with large amounts of videos, captured from the first person perspective. At the same time, surveillance cameras and drones offer an abundance of visual information, often…

Despite many advances in deep-learning based semantic segmentation, performance drop due to distribution mismatch is often encountered in the real world. Recently, a few domain adaptation and active learning approaches have been proposed to…

We investigate the problem of object referring (OR) i.e. to localize a target object in a visual scene coming with a language description. Humans perceive the world more as continued video snippets than as static images, and describe…

The one-shot talking-head synthesis task aims to animate a source image to another pose and expression, which is dictated by a driving frame. Recent methods rely on warping the appearance feature extracted from the source, by using motion…

In this paper, we propose a user-based video indexing method, that automatically generates thumbnails of the most important scenes of an online video stream, by analyzing users' interactions with a web video player. As a test bench to…

Understanding what makes a video memorable has important applications in advertising or education technology. Towards this goal, we investigate spatio-temporal attention mechanisms underlying video memorability. Different from previous…

The diffusion-based generative models have achieved remarkable success in text-based image generation. However, since it contains enormous randomness in generation progress, it is still challenging to apply such models for real-world visual…

Automatic detection of individual intake gestures during eating occasions has the potential to improve dietary monitoring and support dietary recommendations. Existing studies typically make use of on-body solutions such as inertial and…

Human motion generation is a challenging task that aims to create realistic motion imitating natural human behaviour. We focus on the well-studied behaviour of priming an object/location for pick up or put down - that is, the spotting of an…

Short-term action anticipation (STA) in first-person videos is a challenging task that involves understanding the next active object interactions and predicting future actions. Existing action anticipation methods have primarily focused on…