Related papers: Seeing the roads through the trees: A benchmark fo…
This dissertation addresses visual scene understanding and enhances segmentation performance and generalization, training efficiency of networks, and holistic understanding. First, we investigate semantic segmentation in the context of…
Exposing latent knowledge in geospatial trajectories has the potential to provide a better understanding of the movements of individuals and groups. Motivated by such a desire, this work presents the context tree, a new hierarchical data…
Sketch semantic segmentation is a well-explored and pivotal problem in computer vision involving the assignment of pre-defined part labels to individual strokes. This paper presents ContextSeg - a simple yet highly effective approach to…
Detecting travel modes from global navigation satellite system (GNSS) trajectories is essential for understanding individual travel behavior and a prerequisite for achieving sustainable transport systems. While studies have acknowledged the…
The Learnable Tree Filter presents a remarkable approach to model structure-preserving relations for semantic segmentation. Nevertheless, the intrinsic geometric constraint forces it to focus on the regions with close spatial distance,…
Outdoor scene parsing models are often trained on ideal datasets and produce quality results. However, this leads to a discrepancy when applied to the real world. The quality of scene parsing, particularly sky classification, decreases in…
Automated and accurate 3D medical image segmentation plays an essential role in assisting medical professionals to evaluate disease progresses and make fast therapeutic schedules. Although deep convolutional neural networks (DCNNs) have…
To autonomously navigate and plan interactions in real-world environments, robots require the ability to robustly perceive and map complex, unstructured surrounding scenes. Besides building an internal representation of the observed scene…
Segmenting unseen object instances in cluttered environments is an important capability that robots need when functioning in unstructured environments. While previous methods have exhibited promising results, they still tend to provide…
Dynamic Scene Graph Generation (DSGG) models how object relations evolve over time in videos. However, existing methods are trained only on annotated object pairs and lack guidance for non-related pairs, making it difficult to identify…
This work explores the use of spatial context as a source of free and plentiful supervisory signal for training a rich visual representation. Given only a large, unlabeled image collection, we extract random pairs of patches from each image…
Understanding sequential information is a fundamental task for artificial intelligence. Current neural networks attempt to learn spatial and temporal information as a whole, limited their abilities to represent large scale spatial…
Semantic segmentation of outdoor street scenes plays a key role in applications such as autonomous driving, mobile robotics, and assistive technology for visually-impaired pedestrians. For these applications, accurately distinguishing…
We present an interpretable framework for path prediction that leverages dependencies between agents' behaviors and their spatial navigation environment. We exploit two sources of information: the past motion trajectory of the agent of…
We aim for domestic robots to perform long-term indoor service. Under the object-level scene dynamics induced by daily human activities, a robot needs to robustly localize itself in the environment subject to scene uncertainties. Previous…
Recently, deep convolutional neural network (DCNN) achieved increasingly remarkable success and rapidly developed in the field of natural image recognition. Compared with the natural image, the scale of remote sensing image is larger and…
This paper addresses the problem of holistic road scene understanding based on the integration of visual and range data. To achieve the grand goal, we propose an approach that jointly tackles object-level image segmentation and semantic…
Autonomous vehicles are the next revolution in the automobile industry and they are expected to revolutionize the future of transportation. Understanding the scenario in which the autonomous vehicle will operate is critical for its…
We investigate applying convolutional neural network (CNN) architecture to facilitate aerial hyperspectral scene understanding and present a new hyperspectral dataset-AeroRIT-that is large enough for CNN training. To date the majority of…
Semantic segmentation is an essential step for many vision applications in order to understand a scene and the objects within. Recent progress in hyperspectral imaging technology enables the application in driving scenarios and the hope is…