Related papers: Parsing Occluded People by Flexible Compositions

We consider the task of learning Ising models when the signs of different random variables are flipped independently with possibly unequal, unknown probabilities. In this paper, we focus on the problem of robust estimation of…

Structured prediction tasks pose a fundamental trade-off between the need for model complexity to increase predictive power and the limited computational resources for inference in the exponentially-sized output spaces such models require.…

Recent findings in neuroscience suggest that the human brain represents information in a geometric structure (for instance, through conceptual spaces). In order to communicate, we flatten the complex representation of entities and their…

In this paper, we propose and investigate algorithms for the structured orthogonal dictionary learning problem. First, we investigate the case when the dictionary is a Householder matrix. We give sample complexity results and show…

Human perception is structured around objects which form the basis for our higher-level cognition and impressive systematic generalization abilities. Yet most work on representation learning focuses on feature learning without even…

Referring expression comprehension (REC) aims to localize a target object in an image described by a referring expression phrased in natural language. Different from the object detection task that queried object labels have been…

Humans are remarkably flexible when understanding new sentences that include combinations of concepts they have never encountered before. Recent work has shown that while deep networks can mimic some human language abilities when presented…

Understanding and reconstructing occluded objects is a challenging problem, especially in open-world scenarios where categories and contexts are diverse and unpredictable. Traditional methods, however, are typically restricted to closed…

Tree ensembles, such as random forests and boosted trees, are renowned for their high prediction performance. However, their interpretability is critically limited due to the enormous complexity. In this study, we present a method to make a…

Occlusion presents a significant challenge in human pose estimation. The challenges posed by occlusion can be attributed to the following factors: 1) Data: The collection and annotation of occluded human pose samples are relatively…

In this work, we study the challenge of providing human-understandable descriptions for failure modes in trained image classification models. Existing works address this problem by first identifying clusters (or directions) of incorrectly…

Deep Learning models enjoy considerable success in Natural Language Processing. While deep architectures produce useful representations that lead to improvements in various tasks, they are often difficult to interpret. This makes the…

The ability to interpret machine learning models has become increasingly important now that machine learning is used to inform consequential decisions. We propose an approach called model extraction for interpreting complex, blackbox…

The majority of existing human parsing methods formulate the task as semantic segmentation, which regard each semantic category equally and fail to exploit the intrinsic physiological structure of human body, resulting in inaccurate…

The compositional structure of language enables humans to decompose complex phrases and map them to novel visual concepts, showcasing flexible intelligence. While several algorithms exhibit compositionality, they fail to elucidate how…

Visual modes of communication are ubiquitous in modern life --- from maps to data plots to political cartoons. Here we investigate drawing, the most basic form of visual communication. Participants were paired in an online environment to…

Object detection in natural environments is still a very challenging task, even though deep learning has brought a tremendous improvement in performance over the last years. A fundamental problem of object detection based on deep learning…

Current theories hold that brain function is highly related to long-range physical connections through axonal bundles, namely extrinsic connectiv-ity. However, obtaining a groupwise cortical parcellation based on extrinsic connectivity…

Segmenting highly-overlapping image objects is challenging, because there is typically no distinction between real object contours and occlusion boundaries on images. Unlike previous instance segmentation methods, we model image formation…

This paper describes a data-driven framework to parse musical sequences into dependency trees, which are hierarchical structures used in music cognition research and music analysis. The parsing involves two steps. First, the input sequence…