相关论文: Joint Multi-Dimensional Model for Global and Time-…

Data is the engine of modern computer vision, which necessitates collecting large-scale datasets. This is expensive, and guaranteeing the quality of the labels is a major challenge. In this paper, we investigate efficient annotation…

Inferring the correct answers to binary tasks based on multiple noisy answers in an unsupervised manner has emerged as the canonical question for micro-task crowdsourcing or more generally aggregating opinions. In graphon estimation, one is…

We consider a crowdsourcing data acquisition scenario, such as federated learning, where a Center collects data points from a set of rational Agents, with the aim of training a model. For linear regression models, we show how a payment…

Many, if not most, systems of interest in science are naturally described as nonlinear dynamical systems. Empirically, we commonly access these systems through time series measurements. Often such time series may consist of discrete random…

Estimating the dimensionality of the latent representation needed for prediction -- the task-relevant dimension -- is a difficult, largely unsolved problem with broad scientific applications. We cast it as an Information Bottleneck…

We propose the ambiguity problem for the foreground object segmentation task and motivate the importance of estimating and accounting for this ambiguity when designing vision systems. Specifically, we distinguish between images which lead…

Most crowdsourcing learning methods treat disagreement between annotators as noisy labelings while inter-disagreement among experts is often a good indicator for the ambiguity and uncertainty that is inherent in natural language. In this…

Crowd-sourcing has become a popular means of acquiring labeled data for a wide variety of tasks where humans are more accurate than computers, e.g., labeling images, matching objects, or analyzing sentiment. However, relying solely on the…

Domain Generalization techniques aim to enhance model robustness by simulating novel data distributions during training, typically through various augmentation or stylization strategies. However, these methods frequently suffer from limited…

Crowdsourcing technologies rely on groups of people to input information that may be critical for decision-making. This work examines obfuscation in the context of reporting technologies. We show that widespread use of reporting platforms…

Tracking multiple time-varying states based on heterogeneous observations is a key problem in many applications. Here, we develop a statistical model and algorithm for tracking an unknown number of targets based on the probabilistic fusion…

Recently, multi-instrument music generation has become a hot topic. Different from single-instrument generation, multi-instrument generation needs to consider inter-track harmony besides intra-track coherence. This is usually achieved by…

Interpreting implicit discourse relations involves complex reasoning, requiring the integration of semantic cues with background knowledge, as overt connectives like because or then are absent. These relations often allow multiple…

Aggregating signals from a collection of noisy sources is a fundamental problem in many domains including crowd-sourcing, multi-agent planning, sensor networks, signal processing, voting, ensemble learning, and federated learning. The core…

Mapping the extent of flood events is a necessary and important aspect of disaster management. In recent years, deep learning methods have evolved as an effective tool to quickly label high resolution imagery and provide necessary flood…

Prediction polling is an increasingly popular form of crowdsourcing in which multiple participants estimate the probability or magnitude of some future event. These estimates are then aggregated into a single forecast. Historically,…

In this paper, we explore different ways of training a model for handwritten text recognition when multiple imperfect or noisy transcriptions are available. We consider various training configurations, such as selecting a single…

This paper presents a generic Bayesian framework that enables any deep learning model to actively learn from targeted crowds. Our framework inherits from recent advances in Bayesian deep learning, and extends existing work by considering…

The commonly used latent space embedding techniques, such as Principal Component Analysis, Factor Analysis, and manifold learning techniques, are typically used for learning effective representations of homogeneous data. However, they do…

In recent advances of deep generative models, face reenactment -manipulating and controlling human face, including their head movement-has drawn much attention for its wide range of applicability. Despite its strong expressiveness, it is…