Related papers: Vision as looking and seeing through a bottleneck

Reading is a pervasive and cognitively demanding activity that underpins modern human culture. It is a prime instance of a class of tasks where eye movements are coordinated for the purpose of comprehension. Existing theories explain either…

One of the primary challenges faced by deep learning is the degree to which current methods exploit superficial statistics and dataset bias, rather than learning to generalise over the specific representations they have experienced. This is…

In this work, I use a survey of senior visualization researchers and thinkers to ideate about the notion of progress in visualization research: how are we growing as a field, what are we building towards, and are our existing methods…

Visual information determines majority of our spatial behavior. The eye projects a 2-D image of the world on the retina. We demonstrate that when a monocular-like imaging system operates entirely with optically dense fluids, an increase in…

The human visual system uses two parallel pathways for spatial processing and object recognition. In contrast, computer vision systems tend to use a single feedforward pathway, rendering them less robust, adaptive, or efficient than human…

Processes occurring in brains, a.k.a. biological neural networks, can and have been modeled within artificial neural network architectures. Due to this, we have conducted a review of research on the phenomenon of blindsight in an attempt to…

Deep neural networks are a key component of behavior prediction and motion generation for self-driving cars. One of their main drawbacks is a lack of transparency: they should provide easy to interpret rationales for what triggers certain…

Visual design relies on seeing things in different ways, acting on them, and seeing results to act again. Parametric design tools are often not robust to design changes that result from sketching over the visualization of their output. We…

Vision and language are two fundamental capabilities of human intelligence. Humans routinely perform tasks through the interactions between vision and language, supporting the uniquely human capacity to talk about what they see or…

Vision-and-Language Navigation (VLN) tasks agents with locating specific objects in unseen environments using natural language instructions and visual cues. Many existing VLN approaches typically follow an 'observe-and-reason' schema, that…

Vision-Language Models (VLMs) have demonstrated remarkable performance across a variety of real-world tasks. However, existing VLMs typically process visual information by serializing images, a method that diverges significantly from the…

Vision-and-language navigation (VLN) is a multimodal task where an agent follows natural language instructions and navigates in visual environments. Multiple setups have been proposed, and researchers apply new model architectures or…

The challenge of navigation in environments with dynamic objects continues to be a central issue in the study of autonomous agents. While predictive methods hold promise, their reliance on precise state information makes them less practical…

A new prior is proposed for learning representations of high-level concepts of the kind we manipulate with language. This prior can be combined with other priors in order to help disentangling abstract factors from each other. It is…

Humans perceive the world by concurrently processing and fusing high-dimensional inputs from multiple modalities such as vision and audio. Machine perception models, in stark contrast, are typically modality-specific and optimised for…

Human capabilities in understanding visual relations are far superior to those of AI systems, especially for previously unseen objects. For example, while AI systems struggle to determine whether two such objects are visually the same or…

Despite the remarkable success of Vision-Language Models (VLMs), their performance on a range of complex visual tasks is often hindered by a "visual processing bottleneck": a propensity to lose grounding in visual evidence and exhibit a…

By providing substantial amounts of data and standardized evaluation protocols, datasets in computer vision have helped fuel advances across all areas of visual recognition. But even in light of breakthrough results on recent benchmarks, it…

Understanding how the visual cortex of the human brain really works is still an open problem for science today. A better understanding of natural intelligence could also benefit object-recognition algorithms based on convolutional neural…

Mistake analysis in procedural activities is a critical area of research with applications spanning industrial automation, physical rehabilitation, education and human-robot collaboration. This paper reviews vision-based methods for…