Related papers: Learning visual groups from co-occurrences in spac…

In a real-world setting, visual recognition systems can be brought to make predictions for images belonging to previously unknown class labels. In order to make semantically meaningful predictions for such inputs, we propose a two-step…

In this work we address the challenging problem of unsupervised learning from videos. Existing methods utilize the spatio-temporal continuity in contiguous video frames as regularization for the learning process. Typically, this temporal…

When approaching the semantic segmentation of overhead imagery in the decimeter spatial resolution range, successful strategies usually combine powerful methods to learn the visual appearance of the semantic classes (e.g. convolutional…

Open-world instance segmentation is the task of grouping pixels into object instances without any pre-determined taxonomy. This is challenging, as state-of-the-art methods rely on explicit class semantics obtained from large labeled…

In this work, we propose a novel approach that predicts the relationships between various entities in an image in a weakly supervised manner by relying on image captions and object bounding box annotations as the sole source of supervision.…

We consider the problem of predicting how the likelihood of an outcome of interest for a patient changes over time as we observe more of the patient data. To solve this problem, we propose a supervised contrastive learning framework that…

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…

This paper proposes a simple self-supervised approach for learning a representation for visual correspondence from raw video. We cast correspondence as prediction of links in a space-time graph constructed from video. In this graph, the…

A complex system comprises multiple interacting entities whose interdependencies form a unified whole, exhibiting emergent behaviours not present in individual components. Examples include the human brain, living cells, soft matter, Earth's…

In this paper, we propose spatial propagation networks for learning the affinity matrix for vision tasks. We show that by constructing a row/column linear propagation model, the spatially varying transformation matrix exactly constitutes an…

Person Re-identification is a research area with significant real world applications. Despite recent progress, existing methods face challenges in robust re-identification in the wild, e.g., by focusing only on a particular modality and on…

Visual Place Recognition is a task that aims to predict the coordinates of an image (called query) based solely on visual clues. Most commonly, a retrieval approach is adopted, where the query is matched to the most similar images from a…

Generative Adversarial Networks can learn the mapping of random noise to realistic images in a semi-supervised framework. This mapping ability can be used for semi-supervised image classification to detect images of an unknown class where…

In this paper, we propose an unsupervised video object co-segmentation framework based on the primary object proposals to extract the common foreground object(s) from a given video set. In addition to the objectness attributes and motion…

Understanding on-road vehicle behaviour from a temporal sequence of sensor data is gaining in popularity. In this paper, we propose a pipeline for understanding vehicle behaviour from a monocular image sequence or video. A monocular…

Visual representation is crucial for a visual tracking method's performances. Conventionally, visual representations adopted in visual tracking rely on hand-crafted computer vision descriptors. These descriptors were developed generically…

Existing self-supervised learning (SSL) methods primarily learn object-invariant representations but often neglect the spatial structure and relationships among object parts. To address this limitation, we introduce Spatial Prediction (SP),…

Recognizing precise geometrical configurations of groups of objects is a key capability of human spatial cognition, yet little studied in the deep learning literature so far. In particular, a fundamental problem is how a machine can learn…

One object class may show large variations due to diverse illuminations, backgrounds and camera viewpoints. Traditional object detection methods often perform worse under unconstrained video environments. To address this problem, many…

The ability to accurately predict the surrounding environment is a foundational principle of intelligence in biological and artificial agents. In recent years, a variety of approaches have been proposed for learning to predict the physical…