Related papers: Attributes as Operators: Factorizing Unseen Attrib…

Humans perceive the seemingly chaotic world in a structured and compositional way with the prerequisite of being able to segregate conceptual entities from the complex visual scenes. The mechanism of grouping basic visual elements of scenes…

In this paper, we study a new representation-learning task, which we termed as disassembling object representations. Given an image featuring multiple objects, the goal of disassembling is to acquire a latent representation, of which each…

Visual attribute imbalance is a common yet underexplored issue in image classification, significantly impacting model performance and generalization. In this work, we first define the first-level and second-level attributes of images and…

As robots become more ubiquitous and capable, it becomes ever more important to enable untrained users to easily interact with them. Recently, this has led to study of the language grounding problem, where the goal is to extract…

Attributes act as intermediate representations that enable parameter sharing between classes, a must when training data is scarce. We propose to view attribute-based image classification as a label-embedding problem: each class is embedded…

Open Set Recognition (OSR) extends image classification to an open-world setting, by simultaneously classifying known classes and identifying unknown ones. While conventional OSR approaches can detect Out-of-Distribution (OOD) samples, they…

This paper investigates the problem of zero-shot action recognition, in the setting where no training videos with seen actions are available. For this challenging scenario, the current leading approach is to transfer knowledge from the…

Many machine learning algorithms represent input data with vector embeddings or discrete codes. When inputs exhibit compositional structure (e.g. objects built from parts or procedures from subroutines), it is natural to ask whether this…

Descriptors, which are representations of compounds, play an essential role in machine learning of materials data. Although many representations of elements and structures of compounds are known, these representations are difficult to use…

Children can rapidly generalize compositionally-constructed rules to unseen test sets. On the other hand, deep reinforcement learning (RL) agents need to be trained over millions of episodes, and their ability to generalize to unseen…

The classification of textual data often yields important information. Most classifiers work in a closed world setting where the classifier is trained on a known corpus, and then it is tested on unseen examples that belong to one of the…

Open-vocabulary segmentation models often struggle to generalize to unseen combinations of object categories and attributes, because fine-grained descriptions are typically encoded as holistic sentences that entangle multiple semantic…

This paper proposes a novel method for understanding daily hand-object manipulation by developing computer vision-based techniques. Specifically, we focus on recognizing hand grasp types, object attributes and manipulation actions within an…

Capturing contextual dependencies has proven useful to improve the representational power of deep neural networks. Recent approaches that focus on modeling global context, such as self-attention and non-local operation, achieve this goal by…

It is very attractive to formulate vision in terms of pattern theory \cite{Mumford2010pattern}, where patterns are defined hierarchically by compositions of elementary building blocks. But applying pattern theory to real world images is…

Connected operators are filtering tools that act by merging elementary regions of an image. A popular strategy is based on tree-based image representations: for example, one can compute an attribute on each node of the tree and keep only…

Articulated objects are pervasive in daily life. However, due to the intrinsic high-DoF structure, the joint states of the articulated objects are hard to be estimated. To model articulated objects, two kinds of shape deformations namely…

Domain adaptation for visual recognition has undergone great progress in the past few years. Nevertheless, most existing methods work in the so-called closed-set scenario, assuming that the classes depicted by the target images are exactly…

Attributes, or semantic features, have gained popularity in the past few years in domains ranging from activity recognition in video to face verification. Improving the accuracy of attribute classifiers is an important first step in any…

Deep learning methods typically require vast amounts of training data to reach their full potential. While some publicly available datasets exists, domain specific data always needs to be collected and manually labeled, an expensive, time…