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 20 of 36 for “"embedding space"”.
-
Multi-Modal Protein Function Prediction using a Joint Embedding Space from Two Graph Neural Networks
… using two graph neural networks to infer a joint embedding space that captures many properties of a protein including structure, disease associations, drug interactions, protein interactions, biological processes and more. We evaluate the embedding space on downstream prediction tasks including …
-
Multi-scale Deep Nearest Neighbors
In this thesis, we aim to learn a deep embedding space suitable for k-NN. Our approach is based on minimizing the leave-one-out 1-NN classification error in the embedding space. Directly optimizing for such a rule is not tractable due to its discontinuous nature. We propose Multi-scale Deep Nearest …
-
Structuring Representation Geometry in Self-Supervised Learning
… or molecular strings—into a representation space ℝ_𝑑 where everything that is hard to do with raw perceptual data becomes easy. For instance, measuring the similarity between two objects [scientific notation] expressed as tensors of pixel intensities is non-trivial in their raw form, but …
-
Text mining with word embedding for outlier and sentiment analysis
… mining tools to analyze massive text data. Word embedding is an emerging text analysis technique that leverages the fine-grained statistics of context information to map each word to a vector in the embedding space which reflects the semantic proximity between words. Embedding techniques not only …
-
Embedding and latent variable models using maximal correlation
… conditional expectation algorithm to construct embeddings one dimensional at a time to maximally preserve the linear correlation in the embedding space. Each dimension is enforced to be orthogonal to all other dimensions to not encode redundant information. Intuitively, we want to map objects …
-
Towards multilingual lexicon discovery from visually grounded speech
… both English and Hindi to a shared, multimodal embedding space. Next, we use this model to segment and cluster regions of the spoken captions which approximately correspond to words. Then, we exploit between-cluster similarities in the embedding space to associate English pseudo-word clusters …
-
Zero-shot object-goal navigation using multimodal goal embeddings
… encode goal images into a multimodal, semantic embedding space to enable training semantic-goal navigation (SemanticNav) agents at scale in unannotated 3D environments (e.g., HM3D). After training, SemanticNav agents can be instructed to find objects described in free-form natural language …
-
Transfer Learning For Spoken Language Processing
… a shared semantically aligned joint speech-text embedding space. To learn the multimodal semantic embedding space, we propose a teacher/student learning framework where we fine-tune a pre-trained multilingual speech encoder (student) using semantic supervision from a pre-trained multilingual …
-
Visual attention models for far-field scene analysis
… model as a mixture of Gaussians in the spectral embedding space. New examples of activity can be efficiently classified by projection into the embedding space. We demonstrate clustering and unusual activity detection results on a week of activity in the scene (about 40,000 moving object tracks) …
-
Cerebral white matter analysis using diffusion imaging
… as a point in a high-dimensional spectral embedding space, and common structures are found by clustering in this space. By annotating the clusters with anatomical labels, we create a model that we call a high-dimensional white matter atlas.
-
Model-based Planning for Efficient Task Execution
… However, they plan in a high-dimensional latent space, opaque to human collaborators. Hence, it is difficult for humans to understand the agent’s decision-making process. This lack of interpretability hinders effective collaboration between humans and robots. The key question we are trying to …
-
Dealing with Inaccurate and Incomplete Labels in Industrial Streaming Data
… of the approaches, we propose to use constrained embedding representations for the raw input data. These representations are shown to be efficient for dealing with limited annotated data by analysis of the labeled and unlabeled data based on similarities in the embedding space. They allow for robust …
-
Inference of Low-Dimensional Latent Structure in High-Dimensional Data
… are employed to learn a reversible statistical embedding. The proposed embedding procedure is connected to spectral embedding methods, for example, diffusion maps and Isomap, yielding a new statistical spectral framework. The proposed approach allows one to discard the training data when …
-
Conditional Neural Language Models for Multimodal Learning and Natural Language Understanding
… a LSTM encoder for learning visual-semantic embeddings for ranking the relevance of text to images in a joint embedding space. Next we introduce three log-bilinear models for generating image descriptions that integrate both additive and multiplicative interactions. Beyond image conditioning, …
-
Sketch Quality Prediction Using Transformers
… of the experiments show that the transformer embedding space facilitates separation of 'good' sketch quality from 'bad' sketch quality with high accuracy.
-
FALCON: Fast Visual Concept Learning by Integrating Images, Linguistic descriptions, and Conceptual Relations
… as axis-aligned boxes in a high-dimensional space (the “box embedding space”). Given an input image and its paired sentence, our model first resolves the referential expression in the sentence and associates the novel concept with particular objects in the scene. Next, our model interprets …
-
Neural Document Segmentation Using Weighted Sliding Windows with Transformer Encoders
… This approach injects query-awareness into the embedding space of the shared Transformer, resulting in improved segmentation performance. Extensive experiments demonstrate that our methods outperform state-of-the-art approaches. On the Wiki-727k benchmark, both our WeSWin and WeSWin-Ret models …
-
User Simulation in Interactive Information Retrieval : methods and frameworks for simulating complex search behavior
… Markov models, cognitive state models, and embedding space alignment techniques to accurately represent interactive search behavior. Beyond model development, new evaluation methods and metrics are proposed for assessing the quality of simulated search sessions. These include statistical …
-
Visual question answering using external knowledge
… which goes straight to the facts via a learned embedding space. We demonstrate state-of-the-art results on the challenging recently introduced factbased visual question answering dataset, outperforming competing methods by more than 5%. Upon further analysis, we observe that a successive process …
-
Approaches to Artistic Style Suppression: An Evaluation Framework for Copyright Compliance in Generative Artificial Intelligence
… assessment, and geometric validation in embedding space. The framework is demonstrated through a systematic evaluation of inference-time negative prompting across five artists representing diverse traditions: James Jean and Esao Andrews (contemporary illustration), Claude Monet …
Page 1 of 2