Related papers: Sherlock: Scalable Fact Learning in Images
Visual representation learning has been a cornerstone in computer vision, involving typical forms such as visual embeddings, structural symbols, and text-based representations. Despite the success of CLIP-type visual embeddings, they often…
We seek to detect visual relations in images of the form of triplets t = (subject, predicate, object), such as "person riding dog", where training examples of the individual entities are available but their combinations are unseen at…
View-based methods have demonstrated promising performance in 3D shape understanding. However, they tend to make strong assumptions about the relations between views or learn the multi-view correlations indirectly, which limits the…
Temporal event representations are an essential aspect of learning among humans. They allow for succinct encoding of the experiences we have through a variety of sensory inputs. Also, they are believed to be arranged hierarchically,…
We introduce a benchmark to directly evaluate the alignment between human observers and vision models on a 3D shape inference task. We leverage an experimental design from the cognitive sciences which requires zero-shot visual inferences…
Understanding physical phenomena is a key competence that enables humans and animals to act and interact under uncertain perception in previously unseen environments containing novel objects and their configurations. Developmental…
While current deep learning models achieve high performance by learning statistical correlations from vast datasets,which stands in stark contrast to human learning. They lack the flexibility of humans-particularly preverbal infants-to…
Current multimodal LLMs encode images as static visual prefixes and rely on text-based reasoning, lacking goal-driven and adaptive visual access. Inspired by human visual perception-where attention is selectively and sequentially shifted…
Large-scale knowledge graphs provide structured representations of human knowledge. However, as it is impossible to collect all knowledge, knowledge graphs are usually incomplete. Reasoning based on existing facts paves a way to discover…
The past analyses of datasets of social networks have enabled us to make empirical findings of a number of aspects of human society, which are commonly featured as stylized facts of social networks, such as broad distributions of network…
Sample efficiency is a crucial property of language models with practical implications for training efficiency. In real-world text, information follows a long-tailed distribution. Yet, we expect models to learn and recall frequent and…
Evidence-based fact checking aims to verify the truthfulness of a claim against evidence extracted from textual sources. Learning a representation that effectively captures relations between a claim and evidence can be challenging. Recent…
Despite the advances made in visual object recognition, state-of-the-art deep learning models struggle to effectively recognize novel objects in a few-shot setting where only a limited number of examples are provided. Unlike humans who…
Human reasoning involves recognising common underlying principles across many examples. The by-products of such reasoning are invariants that capture patterns such as "if someone went somewhere then they are there", expressed using…
When language models are trained on textual data, they acquire both knowledge about the structure of language as well as knowledge of facts about the world. At inference time, their knowledge of facts can be leveraged to solve interesting…
Extracting structured knowledge from texts has traditionally been used for knowledge base generation. However, other sources of information, such as images can be leveraged into this process to build more complete and richer knowledge…
In this work, we interpret the representations of multi-object scenes in vision encoders through the lens of structured representations. Structured representations allow modeling of individual objects distinctly and their flexible use based…
Current captioning datasets focus on object-centric captions, describing the visible objects in the image, e.g. "people eating food in a park". Although these datasets are useful to evaluate the ability of Vision & Language models to…
An unsupervised shape analysis is proposed to learn concepts reflecting shape commonalities. Our approach is two-fold: i) a spatial topology analysis of point cloud segment constellations within objects is used in which constellations are…
Understanding the shape and structure of objects is undoubtedly extremely important for object recognition, but the most common pattern recognition method currently used is machine learning, which often requires a large number of training…