Related papers: Crafting GBD-Net for Object Detection

Graph Neural Networks (GNNs) are widely used on a variety of graph-based machine learning tasks. For node-level tasks, GNNs have strong power to model the homophily property of graphs (i.e., connected nodes are more similar) while their…

Object segmentation for robotic grasping under dynamic conditions often faces challenges such as occlusion, low light conditions, motion blur and object size variance. To address these challenges, we propose a Deep Learning network that…

Modeling visual question answering(VQA) through scene graphs can significantly improve the reasoning accuracy and interpretability. However, existing models answer poorly for complex reasoning questions with attributes or relations, which…

Exploiting multi-scale representations is critical to improve edge detection for objects at different scales. To extract edges at dramatically different scales, we propose a Bi-Directional Cascade Network (BDCN) structure, where an…

RGB-D semantic segmentation can be advanced with convolutional neural networks due to the availability of Depth data. Although objects cannot be easily discriminated by just the 2D appearance, with the local pixel difference and geometric…

Generic Boundary Detection (GBD) aims at locating the general boundaries that divide videos into semantically coherent and taxonomy-free units, and could serve as an important pre-processing step for long-form video understanding. Previous…

Object detection with 3D radar is essential for 360-degree automotive perception, but radar's long wavelengths produce sparse and irregular reflections that challenge traditional grid and sequence-based convolutional and transformer…

Generic event boundary detection (GEBD) aims to split video into chunks at a broad and diverse set of actions as humans naturally perceive event boundaries. In this study, we present an approach that considers the correlation between…

Segmentation-based tracking has been actively studied in computer vision and multimedia. Superpixel based object segmentation and tracking methods are usually developed for this task. However, they independently perform feature…

Learning discriminative image feature embeddings is of great importance to visual recognition. To achieve better feature embeddings, most current methods focus on designing different network structures or loss functions, and the estimated…

Object detection serves as a significant step in improving performance of complex downstream computer vision tasks. It has been extensively studied for many years now and current state-of-the-art 2D object detection techniques proffer…

Most existing RGB-D semantic segmentation methods focus on the feature level fusion, including complex cross-modality and cross-scale fusion modules. However, these methods may cause misalignment problem in the feature fusion process and…

Region-based object detection infers object regions for one or more categories in an image. Due to the recent advances in deep learning and region proposal methods, object detectors based on convolutional neural networks (CNNs) have been…

Convolutional neural networks (CNNs) have massively impacted visual recognition in 2D images, and are now ubiquitous in state-of-the-art approaches. CNNs do not easily extend, however, to data that are not represented by regular grids, such…

Cascade is a widely used approach that rejects obvious negative samples at early stages for learning better classifier and faster inference. This paper presents chained cascade network (CC-Net). In this CC-Net, the cascaded classifier at a…

We address the problem of semantic correspondence, that is, establishing a dense flow field between images depicting different instances of the same object or scene category. We propose to use images annotated with binary foreground masks…

Benefiting from the great success of deep learning in computer vision, CNN-based object detection methods have drawn significant attentions. Various frameworks have been proposed which show awesome and robust performance for a large range…

Recent researches on panoptic segmentation resort to a single end-to-end network to combine the tasks of instance segmentation and semantic segmentation. However, prior models only unified the two related tasks at the architectural level…

Graph Convolutional Network (GCN) is an emerging technique that performs learning and reasoning on graph data. It operates feature learning on the graph structure, through aggregating the features of the neighbor nodes to obtain the…

Learning fine-grained details is a key issue in image aesthetic assessment. Most of the previous methods extract the fine-grained details via random cropping strategy, which may undermine the integrity of semantic information. Extensive…