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 78 for “"Open-Vocabulary"”.
-
Building and Evaluating Open-Vocabulary Language Models
… NLP tool and application. This thesis focuses on open-vocabulary language models, i.e., models that can deal with novel and unknown words at runtime. We will propose both new ways to construct such models as well as use such models in cross-linguistic evaluations to answer questions of difficulty …
-
Weakly-Supervised Scaling for Open-Vocabulary Action Detection
In this work, we focus on scaling open-vocabulary action detection. Existing approaches for action detection are predominantly limited to closed-set scenarios and rely on complex, parameter-heavy architectures. Extending these models to the open-vocabulary setting poses two key challenges: (1) the …
-
Learning Morphology for Open-Vocabulary Neural Machine Translation
… to the requirement of using a fixed-size word vocabulary during training. In addition to controlling the model complexity, this limitation is also related to the difficulty of learning accurate word representations under conditions of high data sparsity. This problem is an important bottleneck …
-
Open-Vocabulary Scene Graph Generation With Compositional Prompt-Tuning
… distribution. This work describes a novel Open-vocabulary Scene Graph Generation model with Compositional Prompt Tuning (OCoPro) that enforces compositionality through a Cross-modal Composition Refinement (CCR) module and uses compositional prompts to efficiently predict open vocabulary …
-
Semantically Grounded Evaluation for Open-Vocabulary Human-Object Interaction Detection
Open-vocabulary human–object interaction (HOI) detection is a step towards building scal¬able systems that generalize to unseen interactions in real-world scenarios and support grounded multimodal systems that reason about human–object relationships. However, stan¬dard evaluation metrics, such as …
-
Advancing vision-language models for open-vocabulary recognition and generative evaluation
… in the field. <br><br>This thesis advances the open-vocabulary detection problem, which allows VLMs to recognize objects and attributes beyond those seen during training. We propose a method that highlights the importance of part-wise alignment in object detection, especially when using weakly …
-
Semantically Consistent Alignment for Novel Object Discovery in Open-Vocabulary 3D Object Detection
… or out-of-distribution objects encountered in open-world driving scenarios. To address this limitation, the field of open-vocabulary (OV)-3D object detection has emerged, aiming to generalize beyond predefined label sets by leveraging vision-language models (VLMs) to align 3D object proposals …
-
Advancing Temporal Action Localization: Efficient Large Model Adaptation and Open-Vocabulary Recognition in Videos
… VideoMAEv2. The OVFormer framework addresses Open-Vocabulary TAL by generating rich class descriptions using a language model, aligning these with video features through cross-attention, and employing a two-stage training strategy for novel category generalization. LoSA enables efficient use …
-
Open-vocabulary brain-to-text decoding via cross-modal transfer with large language models
… original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-09-01 without embargo terms
-
Realistic Mobile Manipulation Tasks for Evaluating Home-Assistant Robots
… thesis introduces three tasks, namely HomeRobot: Open Vocabulary Mobile Manipulation (OVMM), "GO To Any Thing" (GOAT) and Housekeep, to realsze the different dimensions of realism critical for evaluating embodied agents: 1) autonomy, the ability to operate without very specific instructions (e.g. …
-
Incorporate Out-of-Vocabulary Words for Psycholinguistic Analysis using Social Media Texts - An OOV-aware Data Curation Process and a Hybrid Approach
… These lexical variants are referred as out-of-vocabulary (OOV) words. They are not captured in standard dictionaries used by standard Natural Language Processing (NLP) tools. Literature indicates that these OOV words may include hidden linguistic patterns that reflect individual …
-
Robot navigation and manipulation with foundation models
… for robot navigation, enabling robots to locate open-vocabulary spatial goals, such as "move to the middle of the chair and the sofa." Instead of relying on fixed-category labels, we use vision-language models to generate per-pixel visual-language features, allowing natural language queries to …
-
UNDERSTANDING ALIGNMENT FOR VISION AND LANGUAGE MODELS
… aligning vision models with language models for open-vocabulary object detection. In this setting, alignment enables the recognition of categories beyond the fixed label set used during training. Methods are proposed to bridge the gap between textual descriptions and visual features, allowing for …
-
Towards Achieving General Video Understanding
… directions encompassing multimodal fusion, open-vocabulary recognition, robustness enhancement, and unified video–language modeling. First, a multi-modal prototype contrastive framework is proposed for fine-grained video classification, integrating visual and auditory cues through a …
-
Unsupervised object learning
… mask annotations. We construct a method for open-vocabulary segmentation that uses a pre-trained text-to-image diffusion model to connect language with visual representations of objects. It avoids the need for any further training, showing how text-to-image diffusion models are also powerful …
-
Overcoming Vocabulary Challenges in Natural Language Processing
… one of the very first steps, designing the model vocabulary. Language models are typically defined over a finite set of inputs, even if designed to have an "open vocabulary" through common tokenization techniques like subword segmentation. Current tokenization approaches are primarily designed …
-
Exploring Segmentation, Detection and Tracking in Videos
… label efficiency through self-supervision, and open-vocabulary generalization across modalities. The first contribution introduces a unified bottom-up approach for video instance segmentation that formulates object association as spatio-temporal tag propagation, where each pixel is assigned a …
-
Toward reliable AI: Practical and certified defenses for adversarially robust vision systems
… black-box attacks. Second, we introduce Open Vocabulary Certification (OVC), a fast certification framework for open-vocabulary vision-language models such as CLIP. OVC leverages pre-computed certificates for related prompts, along with embedding caching and distributional approximations, …
-
Quake-OVUDA: Component-Level AI-Based Post-Earthquake Building Inspections with Vision–Language Guided Unsupervised Domain Adaptation
… this thesis incorporates features learned from open-vocabulary (OV) semantic segmentation into the UDA framework, DAFormer, thereby enabling improved contextual understanding and transferring of features from the synthetic to real domains. Specifically, the Simple Encoder Decoder (SED) OV model …
Page 1 of 4