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 13 of 13 for “"Language + vision"”.
-
Learning Language-vision Correspondences
… features. In an iterative procedure we use language (the words) to drive a perceptual grouping process that assembles an appearance model for a named object. We also exploit co-occurrences among appearance models to learn hierarchical appearance models. Results of applying our method to …
-
Methods to improve quality and diversity of language-vision models
Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2023-12-01
-
Improving commonsense reasoning in multimodal models
… reasoning in foundation models across language, vision, and video modalities. We first introduce frameworks that generate and leverage temporal inferences, improving performance on downstream language tasks requiring event reasoning. We then extend this idea to the visual domain with an …
-
Adaptive Post-Training Quantization for Language-Centric Foundation Models
The growing scale and complexity of language-centric foundation models spanning text, vision, and speech impose substantial storage, memory, and inference costs, motivating post-training quantization (PTQ) for efficient deployment. However, architectural and modality-specific differences govern how …
-
A Study on Multimodal AI for Mild Cognitive Impairment Detection
… MCI prediction. We introduce a multimodal speech-language-vision Deep Learning-based method to differentiate MCI from Normal Cognition (NC). Our proposed architecture includes co-attention blocks to fuse three different modalities at the embedding level to find the potential interactions between …
-
Vision and language understanding with localized evidence
Enabling machines to solve computer vision tasks with natural language components can greatly improve human interaction with computers. In this thesis, we address vision and language tasks with deep learning methods that explicitly localize relevant visual evidence. Spatial evidence localization in …
-
A Neuro-Symbolic Approach to Vision, Language, and Multi-Modal Reasoning
… medicine. With advances in foundation models for language, image, and multi-modal data, it is becoming feasible for end users to accomplish complex tasks that would otherwise require substantial domain expertise, engineered pipelines, and resources. Yet the capabilities of today's foundation …
-
Accounting conceptual frameworks and metaphors of vision
… conceptual metaphor in Western society: Vision as Knowledge amidst the post-modern turn. This is done in a selection of accounting conceptual frameworks from 1978 to 2015. The motivation for analysis was first to discover what visual knowledge was like in accounting conceptual frameworks. …
-
Towards The Grounding Of Abstract Categories In Cognitive Robots
The grounding of language in humanoid robots is a fundamental problem, especially in social scenarios which involve the interaction of robots with human beings. Indeed, natural language represents the most natural interface for humans to interact and exchange information about concrete entities …
-
Transfer Learning and Attention Mechanisms in a Multimodal Setting
… information coming from different sources (e.g., language, vision), focus on the most relevant information from the input they receive in a given life situation, and exploit what they have learned before without forgetting it. In the field of Artificial Intelligence and Computational Linguistics, …
-
Learning generalizable and transferable representations across domains and modalities
… attain state-of-the-art performance for computer vision tasks with the help of massive supervised datasets, it is usually assumed that all train and test examples are drawn independently from the same distribution. However, in real-world applications, dataset bias and domain shift violate this …
-
Tell me what to track: visual object tracking and retrieval by natural language descriptions
Natural Language (NL) descriptions can be one of the most convenient ways to initialize a visual tracker. NL descriptions can also help provide information for longer-term invariance, thus helping the tracker cope better with typical visual tracking challenges, e.g. occlusion, motion blur, etc. …
-
General Vision and Language Methods in Real Applications: A Focus on Vision-and-Language Navigation
The field of Vision and Language has aroused significant interest and holds tremendous potential for real applications, particularly in the area of Vision-and-Language Navigation (VLN). The VLN task enables robots to understand navigation instructions expressed in natural language, perceive the …