Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 19 of 19 for “"Scene Graph Generation"”.
-
Seq2Seq Scene Graph Generation Utilizing Vision-language Pretrained Model
Scene graph generation (SGG) aims to represent a visual scene with a hierarchical structure that contains objects, attributes and relationships. Most existing SGG methods require two stages for detecting objects and predicting their pairwise relationships, which is complicated and computational …
-
Open-Vocabulary Scene Graph Generation With Compositional Prompt-Tuning
Scene graphs are explicit data structures that express the semantics of an image. It is semantically richer than simple image encodings from Convolutional Neural Networks (CNNs) because objects (big or small) are represented as distinct nodes and the relationship between them are expressed as …
-
Towards Multimodal Scene Graph Generation Approaches to Video Understanding
… advances video understanding by enhancing Video Scene Graph Generation (VidSGG) through improved temporal modeling, the integration of long-range temporal dependencies via continuous updates to interaction histories, and the utilization of Large Language Models (LLMs) for scene graph reasoning. …
-
Modern Object and Visual Relationship Detection in Images from a Critical, Cognitive and Data Perspective
… as well. In this thesis we tackle the problem of scene graph generation: the task of generating a directed graph that describes the relationships between detected objects in an image. We empirically identify, highlight and discuss the shortcomings of modern deep learning approaches to this task …
-
Scene Understanding and Spatial Analysis Using Scene Graph Enhanced by Hall's Proxemics Zones in Smart Homes
… and intuitive automation in smart homes. I apply scene graphs to provide a structured representation, such as positions, relationships, and properties, of the static and moving objects in indoor home environments. The novelty of this approach lies in the application of proxemics via scene graph …
-
Understanding semantics and geometry of scenes
… we present new approaches for structured scene understanding from images and videos. Structured scene understanding finds numerous applications, including in robotics and autonomous vehicles, as well as in 3D content creation and video editing. The focus of this research is on three …
-
RELATION UNDERSTANDING IN VIDEOS
… addition, the thesis discusses future works in scene graph generation and visual knowledge extraction from videos.
-
Neurosymbolic Programming in Scallop: Design, Implementation, and Applications
… span natural language reasoning, image and video scene graph generation, program vulnerability detection, and RNA secondary structure prediction. Through extensive empirical studies, we demonstrate that Scallop-based neurosymbolic solutions achieve superior accuracy, interpretability, and data …
-
Structured visual understanding, generation and reasoning
… parts), and multiple objects usually exist in a scene and interact with each other in predictable ways (e.g., man playing basketball). This structure manifests itself in the visual data that captures the world around us and in the text describing it and thus can potentially provide a strong …
-
Effective representations for road scene understanding with scalable learning
… require an accurate understanding of the scene for safe operation in real-world driving scenarios. This thesis examines and offers effective representations for road scene understanding based on in-situ perception, which can be employed directly for planning and decision making in a …
-
Deep Visual Understanding and Beyond - Saliency, Uncertainty, and Bridges to Natural Language
… effective in combating class-imbalance issues in scene graph generation, which aims at discovering relationships among visual objects in an image. Moreover, to overcome the primary drawback in vision-language (VL) pre-training and other VL applications, which conventionally necessitate annotated …
-
Visual relationship understanding
… results for the recently introduced task of scene graph generation. In the final part of the thesis, we consider action understanding in videos. In many scenarios, we observe moving objects instead of still images. Thus, it is also important to capture motion information and recognize the …
-
Affordance learning for visual-semantic perception
… including how robots perceive objects by scene understanding. This area has been popular in the Psychology, which has recently come to influence Computer Vision. In this way, Computer Vision has borrowed the concept of affordance from Psychology in order to develop Visual-Semantic …
-
Structured Grounding for Relational Scene Understanding and Reference-Conditioned Generation
… not faithful to their evidence or conditions. A scene graph may assign a frequent but incorrect predicate to an entity pair; an image generator may transfer reference appearance to an incorrect region; and a video generator may lose reference identity over time. This thesis studies these failures …
-
Transformers for efficient and high-level image and video understanding
… classification and detection toward more complex scene understanding. However, the quadratic complexity of the attention mechanism presents significant challenges for computational efficiency, particularly for long sequences, limiting the direct application of standard Transformers to high-level …
-
Efficient robot learning for perception and mapping
… primary focus is on the core tasks of semantic scene understanding and simultaneous localization and mapping (SLAM). Initially, we present a novel method for automating the extrinsic calibration of the widely used camera-LiDAR sensor setup, leveraging regular perception data without a dedicated …
-
Vision-Based Multimodal Frameworks for Human Behavioral Analysis: Applications in Group Activity Understanding and Public Health
… sports analysis, video surveillance, and social scene understanding. Unlike traditional action recognition focused on individuals, GAR requires understanding complex spatiotemporal relationships between multiple actors, their interactions, and the broader context in which these activities occur. …
-
Security-Aware Sensor Fusion in Autonomy
… data-driven learning. Leveraging advancements in scene graph generation and foundation models, this neuro-symbolic framework grounds perception in high-level semantic relationships and commonsense reasoning. Through feasibility studies using physics-based simulators and real-world datasets, we …
-
LEARNING STRUCTURED REPRESENTATIONS OF VISUAL SCENES
… two levels, structured representations of visual scenes, such as visual relationships between pairwise objects, have been shown to not only benefit compositional models in learning to reason along with the structures but provide higher interpretability for model decisions. Nevertheless, these …