Results 21 to 30 of about 61,033 (257)
From a Visual Scene to a Virtual Representation: A Cross-Domain Review
IEEE Access, 2023 The widespread use of smartphones and other low-cost equipment as recording devices, the massive growth in bandwidth, and the ever-growing demand for new applications with enhanced capabilities, made visual data a must in several scenarios, including ...
Americo Pereira +4 more
doaj +1 more source
SECURITY EVENT RECOGNITION FOR VISUAL SURVEILLANCE [PDF]
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2017 With rapidly increasing deployment of surveillance cameras, the reliable methods for automatically analyzing the surveillance video and recognizing special events are demanded by different practical applications.
W. Liao +3 more
doaj +1 more source
GaVe: A webcam-based gaze vending interface using one-point calibration
Journal of Eye Movement Research, 2023 Gaze input, i.e., information input via eye of users, represents a promising method for contact-free interaction in human-machine systems. In this paper, we present the GazeVending interface (GaVe), which lets users control actions on a display with ...
Zhe Zeng +6 more
doaj +1 more source
Understanding visual scenes [PDF]
Natural Language Engineering, 2018 AbstractA growing body of recent work focuses on the challenging problem of scene understanding using a variety of cross-modal methods which fuse techniques from image and text processing. In this paper, we develop representations for the semantics of scenes by explicitly encoding the objects detected in them and their spatial relations.
SILBERER, CARINA +2 more
openaire +2 more sources
3D scene graph prediction from point clouds
Virtual Reality & Intelligent Hardware, 2022 Background: In this study, we propose a novel 3D scene graph prediction approach for scene understanding from point clouds. Methods: It can automatically organize the entities of a scene in a graph, where objects are nodes and their relationships are ...
Fanfan Wu +3 more
doaj +1 more source
A novel dilated convolutional neural network model for road scene segmentation
EAI Endorsed Transactions on Scalable Information Systems, 2022 This article has been retracted, and the retraction notice can be found here: http://dx.doi.org/10.4108/eai.8-4-2022.173784. Road scene understanding is one of the important modules in the field of autonomous driving.
Yachao Zhang, Yuxia Yuan
doaj +1 more source
Towards In-context Scene Understanding
Advances in Neural Information Processing Systems 36, 2023 In-context learning$\unicode{x2013}$the ability to configure a model's behavior with different prompts$\unicode{x2013}$has revolutionized the field of natural language processing, alleviating the need for task-specific models and paving the way for generalist models capable of assisting with any query.
Ivana Balazevic +4 more
openaire +3 more sources
Monte Carlo Scene Search for 3D Scene Understanding [PDF]
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021 We explore how a general AI algorithm can be used for 3D scene understanding to reduce the need for training data. More exactly, we propose a modification of the Monte Carlo Tree Search (MCTS) algorithm to retrieve objects and room layouts from noisy RGB-D scans.
Hampali, Shreyas +5 more
openaire +3 more sources
Action-oriented Scene Understanding [PDF]
, 2022 In order to allow robots to act autonomously it is crucial that they do not only describe their environment accurately but also identify how to interact with their surroundings. While we witnessed tremendous progress in descriptive computer vision, approaches that explicitly target action are scarcer. This cumulative dissertation approaches the goal of
Lüddecke, Timo +7 more
openaire +3 more sources
An Approach to Task Representation Based on Object Features and Affordances
Sensors, 2022 Multi-purpose service robots must execute their tasks reliably in different situations, as well as learn from humans and explain their plans to them.
Paul Gajewski, Bipin Indurkhya
doaj +1 more source