Related papers: Placepedia: Comprehensive Place Understanding with…
Despite recent progress in computer vision, fine-grained interpretation of satellite images remains challenging because of a lack of labeled training data. To overcome this limitation, we propose using Wikipedia as a previously untapped…
Online social networks contain a constantly increasing amount of images - most of them focusing on people. Due to cultural and climate factors, fashion trends and physical appearance of individuals differ from city to city. In this paper we…
An essential prerequisite for unleashing the potential of supervised deep learning algorithms in the area of 3D scene understanding is the availability of large-scale and richly annotated datasets. However, publicly available datasets are…
This paper presents a framework for localization or grounding of phrases in images using a large collection of linguistic and visual cues. We model the appearance, size, and position of entity bounding boxes, adjectives that contain…
Image geolocalization is the task of identifying the location depicted in a photo based only on its visual information. This task is inherently challenging since many photos have only few, possibly ambiguous cues to their geolocation.…
Detecting 3D objects keypoints is of great interest to the areas of both graphics and computer vision. There have been several 2D and 3D keypoint datasets aiming to address this problem in a data-driven way. These datasets, however, either…
Human perception of the world is shaped by a multitude of viewpoints and modalities. While many existing datasets focus on scene understanding from a certain perspective (e.g. egocentric or third-person views), our dataset offers a panoptic…
Many approaches have dealt with the hypothesis that the environment contain information, mostly focusing on how humans decode information from the environment in visual perception, navigation, and spatial decision-making. A question yet to…
Robotic task planning in real-world environments requires not only object recognition but also a nuanced understanding of spatial relationships between objects. We present a spatial-relationship-aware dataset of nearly 1,000 robot-acquired…
Networks have been widely used as the data structure for abstracting real-world systems as well as organizing the relations among entities. Network embedding models are powerful tools in mapping nodes in a network into continuous…
Learning effective representations of urban environments requires capturing spatial structure beyond fixed administrative boundaries. Existing geospatial representation learning approaches typically aggregate Points of Interest(POI) into…
Designing socially active streets has long been a goal of urban planning, yet existing quantitative research largely measures pedestrian volume rather than the quality of social interactions. We hypothesize that street view imagery -- an…
Important high-level vision tasks such as human-object interaction, image captioning and robotic manipulation require rich semantic descriptions of objects at part level. Based upon previous work on part localization, in this paper, we…
Location recognition is commonly treated as visual instance retrieval on "street view" imagery. The dataset items and queries are panoramic views, i.e. groups of images taken at a single location. This work introduces a novel…
Visual place recognition is a critical task in computer vision, especially for localization and navigation systems. Existing methods often rely on contrastive learning: image descriptors are trained to have small distance for similar images…
We present a dataset of 998 3D models of everyday tabletop objects along with their 847,000 real world RGB and depth images. Accurate annotations of camera poses and object poses for each image are performed in a semi-automated fashion to…
While recent research in image understanding has often focused on recognizing more types of objects, understanding more about the objects is just as important. Recognizing object parts and attributes has been extensively studied before, yet…
Geo-spatial analysis of our world benefits from a multimodal approach, as every single geographic location can be described in numerous ways (images from various viewpoints, textual descriptions, geographic coordinates, etc.). Current…
The task of a visual landmark recognition system is to identify photographed buildings or objects in query photos and to provide the user with relevant information on them. With their increasing coverage of the world's landmark buildings…
Object localization, and more specifically object pose estimation, in large industrial spaces such as warehouses and production facilities, is essential for material flow operations. Traditional approaches rely on artificial artifacts…