Related papers: Image-embodied Knowledge Representation Learning
Zero-Shot Learning (ZSL), which aims at automatically recognizing unseen objects, is a promising learning paradigm to understand new real-world knowledge for machines continuously. Recently, the Knowledge Graph (KG) has been proven as an…
Most researches for knowledge graph completion learn representations of entities and relations to predict missing links in incomplete knowledge graphs. However, these methods fail to take full advantage of both the contextual information of…
Large Language Models (LLMs) encode meanings of words in the form of distributed semantics. Distributed semantics capture common statistical patterns among language tokens (words, phrases, and sentences) from large amounts of data. LLMs…
The pursuit of decision safety in clinical applications highlights the potential of concept-based methods in medical imaging. While these models offer active interpretability, they often suffer from concept leakages, where unintended…
Multi-modal entity alignment aims to identify equivalent entities between two different multi-modal knowledge graphs, which consist of structural triples and images associated with entities. Most previous works focus on how to utilize and…
Knowledge bases, and their representations in the form of knowledge graphs (KGs), are naturally incomplete. Since scientific and industrial applications have extensively adopted them, there is a high demand for solutions that complete their…
Sketch drawings capture the salient information of visual concepts. Previous work has shown that neural networks are capable of producing sketches of natural objects drawn from a small number of classes. While earlier approaches focus on…
Humans are able to accurately reason in 3D by gathering multi-view observations of the surrounding world. Inspired by this insight, we introduce a new large-scale benchmark for 3D multi-view visual question answering (3DMV-VQA). This…
Knowledge-Intensive Visual Grounding (KVG) requires models to localize objects using fine-grained, domain-specific entity names rather than generic referring expressions. Although Multimodal Large Language Models (MLLMs) possess rich entity…
Implicit Neural Representations (INRs) are powerful to parameterize continuous signals in computer vision. However, almost all INRs methods are limited to low-level tasks, e.g., image/video compression, super-resolution, and image…
We demonstrate the complementary natures of neural knowledge graph embedding, fine-grain entity type prediction, and neural language modeling. We show that a language model-inspired knowledge graph embedding approach yields both improved…
Many large-scale knowledge bases simultaneously represent two views of knowledge graphs (KGs): an ontology view for abstract and commonsense concepts, and an instance view for specific entities that are instantiated from ontological…
Entity alignment, which is a prerequisite for creating a more comprehensive Knowledge Graph (KG), involves pinpointing equivalent entities across disparate KGs. Contemporary methods for entity alignment have predominantly utilized knowledge…
End-to-end multimodal learning on knowledge graphs has been left largely unaddressed. Instead, most end-to-end models such as message passing networks learn solely from the relational information encoded in graphs' structure: raw values, or…
Knowledge graph embeddings are now a widely adopted approach to knowledge representation in which entities and relationships are embedded in vector spaces. In this chapter, we introduce the reader to the concept of knowledge graph…
Knowledge Graph (KG) is a graph based data structure to represent facts of the world where nodes represent real world entities or abstract concept and edges represent relation between the entities. Graph as representation for knowledge has…
Entity alignment is to find identical entities in different knowledge graphs (KGs) that refer to the same real-world object. Embedding-based entity alignment techniques have been drawing a lot of attention recently because they can help…
Image classification has been studied extensively but there has been limited work in the direction of using non-conventional, external guidance other than traditional image-label pairs to train such models. In this thesis we present a set…
Features of the same sample generated by different pretrained models often exhibit inherently distinct feature distributions because of discrepancies in the model pretraining objectives or architectures. Learning invariant representations…
This paper considers the problem of knowledge inference on large-scale imperfect repositories with incomplete coverage by means of embedding entities and relations at the first attempt. We propose IIKE (Imperfect and Incomplete Knowledge…