Related papers: Weakly-supervised learning of visual relations

In this work, we introduce a novel weakly supervised object detection (WSOD) paradigm to detect objects belonging to rare classes that have not many examples using transferable knowledge from human-object interactions (HOI). While WSOD…

To alleviate the cost of obtaining accurate bounding boxes for training today's state-of-the-art object detection models, recent weakly supervised detection work has proposed techniques to learn from image-level labels. However, requiring…

The 3D weakly-supervised visual grounding task aims to localize oriented 3D boxes in point clouds based on natural language descriptions without requiring annotations to guide model learning. This setting presents two primary challenges:…

We present a semi-supervised approach that localizes multiple unknown object instances in long videos. We start with a handful of labeled boxes and iteratively learn and label hundreds of thousands of object instances. We propose criteria…

To determine if a skill can be executed in any given environment, a robot needs to learn the preconditions for the skill. As robots begin to operate in dynamic and unstructured environments, precondition models will need to generalize to…

Weakly supervised object detection aims at reducing the amount of supervision required to train detection models. Such models are traditionally learned from images/videos labelled only with the object class and not the object bounding box.…

Recognizing relations between entities is a pivotal task of relational learning. Learning relation representations from distantly-labeled datasets is difficult because of the abundant label noise and complicated expressions in human…

Vision-language (VL) Pre-training (VLP) has shown to well generalize VL models over a wide range of VL downstream tasks, especially for cross-modal retrieval. However, it hinges on a huge amount of image-text pairs, which requires tedious…

Training deep neural networks to estimate the viewpoint of objects requires large labeled training datasets. However, manually labeling viewpoints is notoriously hard, error-prone, and time-consuming. On the other hand, it is relatively…

We study the problem of learning to estimate the 3D object pose from a few labelled examples and a collection of unlabelled data. Our main contribution is a learning framework, neural view synthesis and matching, that can transfer the 3D…

Visual knowledge bases such as Visual Genome power numerous applications in computer vision, including visual question answering and captioning, but suffer from sparse, incomplete relationships. All scene graph models to date are limited to…

Identifying different objects (man and cup) is an important problem on its own, but identifying the relationship between them (holding) is critical for many real world use cases. This paper describes an approach to reduce a visual…

After learning a new object category from image-level annotations (with no object bounding boxes), humans are remarkably good at precisely localizing those objects. However, building good object localizers (i.e., detectors) currently…

3D visual grounding aims to localize the target object in a 3D point cloud by a free-form language description. Typically, the sentences describing the target object tend to provide information about its relative relation between other…

Weakly supervised object detection (WSOD) using only image-level annotations has attracted a growing attention over the past few years. Whereas such task is typically addressed with a domain-specific solution focused on natural images, we…

Extracting relational triples from unstructured text is crucial for large-scale knowledge graph construction. However, few existing works excel in solving the overlapping triple problem where multiple relational triples in the same sentence…

Pre-trained vision-language models learn massive data to model unified representations of images and natural languages, which can be widely applied to downstream machine learning tasks. In addition to zero-shot inference, in order to better…

Achieving visual reasoning is a long-term goal of artificial intelligence. In the last decade, several studies have applied deep neural networks (DNNs) to the task of learning visual relations from images, with modest results in terms of…

Weakly supervised object localization (WSOL) aims at predicting object locations in an image using only image-level category labels. Common challenges that image classification models encounter when localizing objects are, (a) they tend to…

Weakly Supervised Object Detection (WSOD), using only image-level annotations to train object detectors, is of growing importance in object recognition. In this paper, we propose a novel deep network for WSOD. Unlike previous networks that…