Related papers: SVGauge: Towards Human-Aligned Evaluation for SVG …
Scalable Vector Graphics (SVGs) are fundamental to digital design and robot control, encoding not only visual structure but also motion paths in interactive drawings. In this work, we introduce RoboSVG, a unified multimodal framework for…
Sign Language Video Generation (SLVG) seeks to generate identity-preserving sign language videos from spoken language texts. Existing methods primarily rely on the single coarse condition (\eg, skeleton sequences) as the intermediary to…
Recent advancements in generative AI have made text-guided image inpainting - adding, removing, or altering image regions using textual prompts - widely accessible. However, generating semantically correct photorealistic imagery, typically…
As a natural extension of the image synthesis task, video synthesis has attracted a lot of interest recently. Many image synthesis works utilize class labels or text as guidance. However, neither labels nor text can provide explicit…
We survey human evaluation in papers presenting work on creative natural language generation that have been published in INLG 2020 and ICCC 2020. The most typical human evaluation method is a scaled survey, typically on a 5 point scale,…
Image captioning has become an essential Vision & Language research task. It is about predicting the most accurate caption given a specific image or video. The research community has achieved impressive results by continuously proposing new…
Recent text-to-image generative models can generate high-fidelity images from text inputs, but the quality of these generated images cannot be accurately evaluated by existing evaluation metrics. To address this issue, we introduce Human…
We address the task of evaluating image description generation systems. We propose a novel image-aware metric for this task: VIFIDEL. It estimates the faithfulness of a generated caption with respect to the content of the actual image,…
Recent advances in image editing have enabled models to handle complex instructions with impressive realism. However, existing evaluation frameworks lag behind: current benchmarks suffer from narrow task coverage, while standard metrics…
Personalized image generation holds great promise in assisting humans in everyday work and life due to its impressive ability to creatively generate personalized content across various contexts. However, current evaluations either are…
Large Vision Language Models (VLMs) effectively bridge the modality gap through extensive pretraining, acquiring sophisticated visual representations aligned with language. However, it remains underexplored whether these representations,…
Scene Graph Generation (SGG) unifies object localization and visual relationship reasoning by predicting boxes and subject-predicate-object triples. Yet most pipelines treat SGG as a one-shot, deterministic classification problem rather…
With the rapid development of generative models, Artificial Intelligence-Generated Contents (AIGC) have exponentially increased in daily lives. Among them, Text-to-Video (T2V) generation has received widespread attention. Though many T2V…
Editing images using natural language instructions has become a natural and expressive way to modify visual content; yet, evaluating the performance of such models remains challenging. Existing evaluation approaches often rely on image-text…
Humans often specify and create through visual artifacts: typography sheets, sketches, reference images, and annotated scenes. Yet modern visual generators still ask users to serialize this intent into text, a bottleneck that compresses…
Data visualizations help extract insights from datasets, but reaching these insights requires decomposing high level goals into low-level analytic tasks that can be complex due to varying degrees of data literacy and visualization…
Recent advances in text-to-video (T2V) generation highlight the critical role of high-quality video-text pairs in training models capable of producing coherent and instruction-aligned videos. However, strategies for optimizing video…
Evaluating the open-form textual responses generated by Large Language Models (LLMs) typically requires measuring the semantic similarity of the response to a (human generated) reference. However, there is evidence that current semantic…
Generating visual text in natural scene images is a challenging task with many unsolved problems. Different from generating text on artificially designed images (such as posters, covers, cartoons, etc.), the text in natural scene images…
Generating consistent and high-quality images from given texts is essential for visual-language understanding. Although impressive results have been achieved in generating high-quality images, text-image consistency is still a major concern…