Related papers: Improving Classification of Occluded Objects throu…

Text in natural images contains rich semantics that are often highly relevant to objects or scene. In this paper, we focus on the problem of fully exploiting scene text for visual understanding. The main idea is combining word…

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…

For computer vision systems to operate in dynamic situations, they need to be able to represent and reason about object permanence. We introduce a framework for learning to estimate 4D visual representations from monocular RGB-D, which is…

Vision systems that deploy Deep Neural Networks (DNNs) are known to be vulnerable to adversarial examples. Recent research has shown that checking the intrinsic consistencies in the input data is a promising way to detect adversarial…

Images of heavily occluded objects in cluttered scenes, such as fruit clusters in trees, are hard to segment. To further retrieve the 3D size and 6D pose of each individual object in such cases, bounding boxes are not reliable from multiple…

Deep Convolutional Neural Networks (DCNN) have been proven to be effective for various computer vision problems. In this work, we demonstrate its effectiveness on a continuous object orientation estimation task, which requires prediction of…

Scene change detection is an image processing problem related to partitioning pixels of a digital image into foreground and background regions. Mostly, visual knowledge-based computer intelligent systems, like traffic monitoring, video…

Existing deep learning-based 3D object detectors typically rely on the appearance of individual objects and do not explicitly pay attention to the rich contextual information of the scene. In this work, we propose Contextualized Multi-Stage…

Object detection is a fundamental problem in image understanding. One popular solution is the R-CNN framework and its fast versions. They decompose the object detection problem into two cascaded easier tasks: 1) generating object proposals…

The performance of a trained object detection neural network depends a lot on the image quality. Generally, images are pre-processed before feeding them into the neural network and domain knowledge about the image dataset is used to choose…

A major challenge in scene graph classification is that the appearance of objects and relations can be significantly different from one image to another. Previous works have addressed this by relational reasoning over all objects in an…

The recurring context in which objects appear holds valuable information that can be employed to predict their existence. This intuitive observation indeed led many researchers to endow appearance-based detectors with explicit reasoning…

Dataset pruning -- selecting a small yet informative subset of training data -- has emerged as a promising strategy for efficient machine learning, offering significant reductions in computational cost and storage compared to alternatives…

Modern object detection and instance segmentation networks stumble when picking out humans in crowded or highly occluded scenes. Yet, these are often scenarios where we require our detectors to work well. Many works have approached this…

Flexible industrial production systems will play a central role in the future of manufacturing due to higher product individualization and customization. A key component in such systems is the robotic grasping of known or unknown objects in…

Recently, significant progresses have been made in object detection on common benchmarks (i.e., Pascal VOC). However, object detection in real world is still challenging due to the serious data imbalance. Images in real world are dominated…

Deep learning architectures are showing great promise in various computer vision domains including image classification, object detection, event detection and action recognition. In this study, we investigate various aspects of…

Human-Object Interaction Detection is a crucial aspect of human-centric scene understanding, with important applications in various domains. Despite recent progress in this field, recognizing subtle and detailed interactions remains…

Given the complexities inherent in visual scenes, such as object occlusion, a comprehensive understanding often requires observation from multiple viewpoints. Existing multi-viewpoint object-centric learning methods typically employ random…

Despite deep convolutional neural networks' great success in object classification, it suffers from severe generalization performance drop under occlusion due to the inconsistency between training and testing data. Because of the large…