相关论文: Framework for 2D Ad placements in LinearTV

Visual Place Recognition (VPR) is a core component in computer vision, typically formulated as an image retrieval task for localization, mapping, and navigation. In this work, we instead study VPR as an image pair retrieval front-end for…

We propose a system that uses video as the input to track the position of objects relative to their surrounding environment in real-time. The neural network employed is trained on a 100% synthetic dataset coming from our own automated…

Machine learning techniques, namely convolutional neural networks (CNN) and regression forests, have recently shown great promise in performing 6-DoF localization of monocular images. However, in most cases image-sequences, rather only…

In the industry, numerous commercial packages provide tools to introduce, and analyse human behaviour in the product's environment (for maintenance, ergonomics...), thanks to Virtual Humans. We will focus on control. Thanks to algorithms…

We introduce InVi, an approach for inserting or replacing objects within videos (referred to as inpainting) using off-the-shelf, text-to-image latent diffusion models. InVi targets controlled manipulation of objects and blending them…

In this paper, we study the problem of procedure planning in instructional videos, which can be seen as a step towards enabling autonomous agents to plan for complex tasks in everyday settings such as cooking. Given the current visual…

In display advertising, users' online ad experiences are important for the advertising effectiveness. However, users have not been well accommodated in real-time bidding (RTB). This further influences their site visits and perception of the…

In E-commerce advertising, where product recommendations and product ads are presented to users simultaneously, the traditional setting is to display ads at fixed positions. However, under such a setting, the advertising system loses the…

Mobile Advertisement is a location-aware dissemination solution built on top of a vehicular ad-hoc network. We envision a network of WiFi access points that dynamically disseminate data to clients running on the car's smart device. The…

In the evolving landscape of video enhancement and editing methodologies, a majority of deep learning techniques often rely on extensive datasets of observed input and ground truth sequence pairs for optimal performance. Such reliance often…

Video Panoptic Segmentation (VPS) is a challenging task that is extends from image panoptic segmentation.VPS aims to simultaneously classify, track, segment all objects in a video, including both things and stuff. Due to its wide…

Visual effects (VFX) production often struggles with slow, resource-intensive mask generation. This paper presents an automated video segmentation pipeline that creates temporally consistent instance masks. It employs machine learning for:…

Contemporary monocular 6D pose estimation methods can only cope with a handful of object instances. This naturally hampers possible applications as, for instance, robots seamlessly integrated in everyday processes necessarily require the…

In this paper, we work to bring telepresence to every desktop. Unlike commercial systems, personal 3D video conferencing systems must render high-quality videos while remaining financially and computationally viable for the average…

Near-Periodic Patterns (NPP) are ubiquitous in man-made scenes and are composed of tiled motifs with appearance differences caused by lighting, defects, or design elements. A good NPP representation is useful for many applications including…

In this paper, we propose a multi-target image tracking algorithm based on continuously apative mean-shift (Cam-shift) and unscented Kalman filter. We improved the single-lamp tracking algorithm proposed in our previous work to multi-target…

Automated tagging of video advertisements has been a critical yet challenging problem, and it has drawn increasing interests in last years as its applications seem to be evident in many fields. Despite sustainable efforts have been made,…

In this paper, we introduce a new uplink visible light indoor positioning system that estimates the position of the users in the network-side of a visible light communications (VLC) system. This technique takes advantage of the diffuse…

We present a framework for visual action planning of complex manipulation tasks with high-dimensional state spaces such as manipulation of deformable objects. Planning is performed in a low-dimensional latent state space that embeds images.…

In the search for binary systems inspiral signal in interferometric gravitational waves detectors, one needs the generation and placement of a grid of templates. We present an original technique for the placement in the associated parameter…