Related papers: Local Space-Time Smoothing for Version Controlled …
Due to the nature of human language, historical documents are hard to comprehend by contemporary people. This limits their accessibility to scholars specialized in the time period in which the documents were written. Modernization aims at…
Real-world text applications often involve composing a wide range of text control operations, such as editing the text w.r.t. an attribute, manipulating keywords and structure, and generating new text of desired properties. Prior work…
This paper focuses on self-supervised video representation learning. Most existing approaches follow the contrastive learning pipeline to construct positive and negative pairs by sampling different clips. However, this formulation tends to…
Real-world data is complex and often consists of objects that can be decomposed into multiple entities (e.g. images into pixels, graphs into interconnected nodes). Randomized smoothing is a powerful framework for making models provably…
Spatially dense self-supervised learning is a rapidly growing problem domain with promising applications for unsupervised segmentation and pretraining for dense downstream tasks. Despite the abundance of temporal data in the form of videos,…
The creation of manipulated multimedia content involving human characters has reached in the last years unprecedented realism, calling for automated techniques to expose synthetically generated faces in images and videos. This work explores…
With the rapid development of multimedia processing and deep learning technologies, especially in the field of video understanding, video quality assessment (VQA) has achieved significant progress. Although researchers have moved from…
Recent large-scale text-driven synthesis models have attracted much attention thanks to their remarkable capabilities of generating highly diverse images that follow given text prompts. Such text-based synthesis methods are particularly…
Deployed machine learning systems must continuously evolve as data, architectures, and regulations change, often without access to original training data or model internals. In such settings, black-box copying provides a practical…
The rapid advancement of large language models (LLMs) and multimodal learning has transformed digital content creation and manipulation. Traditional visual editing tools require significant expertise, limiting accessibility. Recent strides…
The robotic manipulation of composite rigid-deformable objects (i.e. those with mixed non-homogeneous stiffness properties) is a challenging problem with clear practical applications that, despite the recent progress in the field, it has…
Controllable video generation has emerged as a versatile tool for autonomous driving, enabling realistic synthesis of traffic scenarios. However, existing methods depend on control signals at inference time to guide the generative model…
Recent progress in generative models has significantly advanced image editing capabilities, yet precise and intuitive user control remains difficult. Specifically, users often struggle to communicate both exact spatial layouts and specific…
Time-varying optimization is fundamental to decision-making in dynamic environments, where objectives evolve over time due to exogenous signals or data streams. However, algorithms designed for static problems yield suboptimal decisions in…
In state space models, smoothing refers to the task of estimating a latent stochastic process given noisy measurements related to the process. We propose an unbiased estimator of smoothing expectations. The lack-of-bias property has…
More than 80% of today's data is unstructured in nature, and these unstructured datasets evolve over time. A large part of these datasets are text documents generated by media outlets, scholarly articles in digital libraries, findings from…
Despite significant progress on current state-of-the-art image generation models, synthesis of document images containing multiple and complex object layouts is a challenging task. This paper presents a novel approach, called DocSynth, to…
Text-to-video diffusion models have advanced video generation significantly. However, customizing these models to generate videos with tailored motions presents a substantial challenge. In specific, they encounter hurdles in (a) accurately…
Understanding large amounts of spatiotemporal data from particle-based simulations, such as molecular dynamics, often relies on the computation and analysis of aggregate measures. These, however, by virtue of aggregation, hide structural…
The Slow Space Editor is a 2D tool for creating 3D spaces. It was built as part of a research-through-design project that investigates how Virtual and Mixed Reality (XR) environments might be used for reflection and attention restoration.…