相关论文: Semantic Discriminability for Visual Communication

Vision-language instruction tuning achieves two main purposes: learning visual concepts and learning visual skills. In this paper, we found that vision-language benchmarks fall into the dichotomy of mainly benefiting from training on…

Understanding how helpful a visualization is from experimental results is difficult because the observed performance is confounded with aspects of the study design, such as how useful the information that is visualized is for the task. We…

The semantic mapping problem is probably the main obstacle to computer-to-computer communication. If computer A knows that its concept X is the same as computer B's concept Y, then the two machines can communicate. They will in effect be…

We propose an approach, called the Equilibrium Distribution Model (EDM), for automatically selecting colors with optimum perceptual contrast for scientific visualization. Given any number of features that need to be emphasized in a…

Semantic Segmentation is a significant research field in Computer Vision. Despite being a widely studied subject area, many visualization tools do not exist that capture segmentation quality and dataset statistics such as a class imbalance…

Visualization's design knowledge-effectiveness rankings, encoding guidelines, color models, preattentive processing rules -- derives from six decades of psychophysical studies of human vision. Yet vision-language models (VLMs) increasingly…

Recent advancements in vision models have greatly improved their ability to handle complex chart understanding tasks, like chart captioning and question answering. However, it remains challenging to assess how these models process charts.…

We are witnessing significant progress on perception models, specifically those trained on large-scale internet images. However, efficiently generalizing these perception models to unseen embodied tasks is insufficiently studied, which will…

Rule sets are often used in Machine Learning (ML) as a way to communicate the model logic in settings where transparency and intelligibility are necessary. Rule sets are typically presented as a text-based list of logical statements…

Images with visual and scene text content are ubiquitous in everyday life. However, current image interpretation systems are mostly limited to using only the visual features, neglecting to leverage the scene text content. In this paper, we…

Reasoning about images/objects and their hierarchical interactions is a key concept for the next generation of computer vision approaches. Here we present a new framework to deal with it through a visual hierarchical context-based…

A recent spate of state-of-the-art semi- and un-supervised solutions disentangle and encode image "content" into a spatial tensor and image appearance or "style" into a vector, to achieve good performance in spatially equivariant tasks…

Semantic communication, regarded as the breakthrough beyond the Shannon paradigm, aims at the successful transmission of semantic information conveyed by the source rather than the accurate reception of each single symbol or bit regardless…

As the intermediate-level representations bridging the two levels, structured representations of visual scenes, such as visual relationships between pairwise objects, have been shown to not only benefit compositional models in learning to…

What impressions might readers form with visualizations that go beyond the data they encode? In this paper, we build on recent work that demonstrates the socio-indexical function of visualization, showing that visualizations communicate…

Recently, researchers started to pay attention to the detection of temporal shifts in the meaning of words. However, most (if not all) of these approaches restricted their efforts to uncovering change over time, thus neglecting other…

Applications such as textual entailment, plagiarism detection or document clustering rely on the notion of semantic similarity, and are usually approached with dimension reduction techniques like LDA or with embedding-based neural…

The accuracy with which humans can detect small chromatic differences varies throughout color space. For example, we are far more precise when discriminating two similar orange stimuli than two similar green stimuli. In order for two colors…

Many visual representations, such as volume-rendered images and metro maps, feature a noticeable amount of information loss. At a glance, there seem to be numerous opportunities for viewers to misinterpret the data being visualized, hence…

Sensemaking is the cognitive process of extracting information, creating schemata from knowledge, making decisions from those schemata, and inferring conclusions. Human analysts are essential to exploring and quantifying this process, but…