Related papers: RepGN:Object Detection with Relational Proposal Gr…
Occluded person re-identification (ReID) aims to match occluded person images to holistic ones across dis-joint cameras. In this paper, we propose a novel framework by learning high-order relation and topology information for discriminative…
State-of-the-art object detection systems rely on an accurate set of region proposals. Several recent methods use a neural network architecture to hypothesize promising object locations. While these approaches are computationally efficient,…
We propose a novel approach for generating region proposals for performing face-detection. Instead of classifying anchor boxes using features from a pixel in the convolutional feature map, we adopt a pooling-based approach for generating…
Representation learning on graphs, also called graph embedding, has demonstrated its significant impact on a series of machine learning applications such as classification, prediction and recommendation. However, existing work has largely…
Visual scene graph generation is a challenging task. Previous works have achieved great progress, but most of them do not explicitly consider the class imbalance issue in scene graph generation. Models learned without considering the class…
Current top performing object detectors employ detection proposals to guide the search for objects, thereby avoiding exhaustive sliding window search across images. Despite the popularity and widespread use of detection proposals, it is…
Relation extraction (RE) aims to predict a relation between a subject and an object in a sentence, while knowledge graph link prediction (KGLP) aims to predict a set of objects, O, given a subject and a relation from a knowledge graph.…
We present a conceptually simple framework for object instance segmentation called Contour Proposal Network (CPN), which detects possibly overlapping objects in an image while simultaneously fitting closed object contours using an…
We propose an approach to predict the 3D shape and pose for the objects present in a scene. Existing learning based methods that pursue this goal make independent predictions per object, and do not leverage the relationships amongst them.…
Scene graph generation (SGG) is built on top of detected objects to predict object pairwise visual relations for describing the image content abstraction. Existing works have revealed that if the links between objects are given as prior…
Cross-View Geo-Localisation within urban regions is challenging in part due to the lack of geo-spatial structuring within current datasets and techniques. We propose utilising graph representations to model sequences of local observations…
Graph convolutional networks (GCNs) have been widely used for representation learning on graph data, which can capture structural patterns on a graph via specifically designed convolution and readout operations. In many graph classification…
Predictive tasks on relational databases are critical in real-world applications spanning e-commerce, healthcare, and social media. To address these tasks effectively, Relational Deep Learning (RDL) encodes relational data as graphs,…
Graph neural networks (GNNs) have gained prominence in recommendation systems in recent years. By representing the user-item matrix as a bipartite and undirected graph, GNNs have demonstrated their potential to capture short- and…
We propose an object detection system that relies on a multi-region deep convolutional neural network (CNN) that also encodes semantic segmentation-aware features. The resulting CNN-based representation aims at capturing a diverse set of…
The convolution layer has been the dominant feature extractor in computer vision for years. However, the spatial aggregation in convolution is basically a pattern matching process that applies fixed filters which are inefficient at modeling…
Session-based recommendations which predict the next action by understanding a user's interaction behavior with items within a relatively short ongoing session have recently gained increasing popularity. Previous research has focused on…
Current CNN-based algorithms for recovering the 3D pose of an object in an image assume knowledge about both the object category and its 2D localization in the image. In this paper, we relax one of these constraints and propose to solve the…
Inter-image association modeling is crucial for co-salient object detection. Despite satisfactory performance, previous methods still have limitations on sufficient inter-image association modeling. Because most of them focus on image…
Understanding the world in 3D is a critical component of urban autonomous driving. Generally, the combination of expensive LiDAR sensors and stereo RGB imaging has been paramount for successful 3D object detection algorithms, whereas…