Results 41 to 50 of about 7,519,950 (294)

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, Wörgötter, Florentin, Georg-August-Universität Göttingen, Sporleder, Caroline, Piater, Justus, Yahyapour, Ramin, Damm, Carsten, Modrow, Eckart   +7 more
openaire   +3 more sources

Using Articulated Scene Models for Dynamic 3D Scene Analysis in Vista Spaces [PDF]

, 2010
Beuter N, Swadzba A, Kummert F, Wachsmuth S. Using Articulated Scene Models for Dynamic 3D Scene Analysis in Vista Spaces. 3D Research. 2010;1(3): 4.In this paper we describe an efficient but detailed new approach to analyze complex dynamic scenes ...
Beuter, Niklas, Agnes Swadzba, Franz Kummert Sven, Kummert, Franz, Swadzba, Agnes, Wachsmuth, Sven ; https://orcid.org/, Franz Kummert, Niklas Beuter, Sven Wachsmuth   +8 more
core   +1 more source

Sketch-and-Fill Network for Semantic Segmentation

IEEE Access, 2021
Recent efforts in semantic segmentation using deep learning framework have made notable advances. While achieving high performance, however, they often require heavy computation, making them impractical to be used in real world applications.
Youngsaeng Jin, Sungmin Eum, David Han, Hanseok Ko   +3 more
doaj   +1 more source

Human's Scene Sketch Understanding [PDF]

Proceedings of the 2016 ACM on International Conference on Multimedia Retrieval, 2016
Human's sketch understanding is important. It has many applications in human computer interaction, multimedia, and computer vision. Recognizing human sketches is also challenging. Previous methods focus on single-object sketch recognition. Understanding human's scene sketch that involves multiple objects and their complex interactions has not been ...
Yuxiang Ye, Yijuan Lu, Hao Jiang 0007
openaire   +1 more source

Probing Spatial Clues: Canonical Spatial Templates for Object Relationship Understanding

IEEE Access, 2021
Humans often leverage spatial clues to categorize scenes in a fraction of a second. This form of intelligence is very relevant in time-critical situations (e.g., when driving a car) and valuable to transfer to automated systems.
Guillem Collell, Thierry Deruyttere, Marie-Francine Moens   +2 more
doaj   +1 more source

In-Place Scene Labelling and Understanding with Implicit Scene Representation [PDF]

2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2021
Semantic labelling is highly correlated with geometry and radiance reconstruction, as scene entities with similar shape and appearance are more likely to come from similar classes. Recent implicit neural reconstruction techniques are appealing as they do not require prior training data, but the same fully self-supervised approach is not possible for ...
Shuaifeng Zhi, Tristan Laidlow, Stefan Leutenegger, Andrew J. Davison   +3 more
openaire   +4 more sources

Procedural Text Understanding via Scene-Wise Evolution

, 2022
Procedural text understanding requires machines to reason about entity states within the dynamical narratives. Current procedural text understanding approaches are commonly entity-wise, which separately track each entity and independently predict ...
Liao, Meng, Lin, Hongyu, Lu, Yaojie, Sun, Le, Xu, Jin, Han, Xianpei, Xie, Weijian, Tang, Jialong, Yaojie Lu, Weijian Xie, Le Sun, Jin Xu, Meng Liao, Hongyu Lin, Xianpei Han, Jialong Tang   +15 more
core   +1 more source

Unbiased 3D Semantic Scene Graph Prediction in Point Cloud Using Deep Learning

Applied Sciences, 2023
As a core task of computer vision perception, 3D scene understanding has received widespread attention. However, the current research mainly focuses on the semantic understanding task at the level of entity objects and often neglects the semantic ...
Chaolin Han, Hongwei Li, Jian Xu, Bing Dong, Yalin Wang, Xiaowen Zhou, Shan Zhao   +6 more
doaj   +1 more source

Guidance of Visual Attention by Semantic Information in Real-World Scenes

Frontiers in Psychology, 2014
Recent research on attentional guidance in real-world scenes has focused on object recognition within the context of a scene. This approach has been valuable for determining some factors that drive the allocation of visual attention and determine visual ...
Chia-Chien eWu, Farahnaz Ahmed Wick, Marc ePomplun   +2 more
doaj   +1 more source

Learning Direct Optimization for scene understanding [PDF]

Pattern Recognition, 2020
We develop a Learning Direct Optimization (LiDO) method for the refinement of a latent variable model that describes input image x. Our goal is to explain a single image x with an interpretable 3D computer graphics model having scene graph latent variables z (such as object appearance, camera position).
Romaszko, Lukasz, Williams, Christopher K.I., Winn, John   +2 more
openaire   +5 more sources