Related papers: Active Annotation of Informative Overlapping Frame…
Analyzing large complex image collections in domains like forensics, accident investigation, or social media analysis involves interpreting intricate, overlapping relationships among images. Traditional clustering and classification methods…
Video surgery timelines are an important part of tool-assisted surgeries, as they allow surgeons to quickly focus on key parts of the procedure. Current methods involve the surgeon filling out a post-operation (OP) report, which is often…
A novel onboard tracking approach enabling vision-based relative localization and communication using Active blinking Marker Tracking (AMT) is introduced in this article. Active blinking markers on multi-robot team members improve the…
Video-based representations have gained prominence in planning and decision-making due to their ability to encode rich spatiotemporal dynamics and geometric relationships. These representations enable flexible and generalizable solutions…
A fundamental problem in robotic perception is matching identical objects or data, with applications such as loop closure detection, place recognition, object tracking, and map fusion. While the problem becomes considerably more challenging…
Recent advances in data-centric artificial intelligence highlight inherent limitations in object recognition datasets. One of the primary issues stems from the semantic gap problem, which results in complex many-to-many mappings between…
Sketch recognition allows natural and efficient interaction in pen-based interfaces. A key obstacle to building accurate sketch recognizers has been the difficulty of creating large amounts of annotated training data. Several authors have…
Video annotation is a critical and time-consuming task in computer vision research and applications. This paper presents a novel annotation pipeline that uses pre-extracted features and dimensionality reduction to accelerate the temporal…
Matching-based networks have achieved state-of-the-art performance for video object segmentation (VOS) tasks by storing every-k frames in an external memory bank for future inference. Storing the intermediate frames' predictions provides…
Superpixels have become very popular in many computer vision applications. Nevertheless, they remain underexploited since the superpixel decomposition may produce irregular and non stable segmentation results due to the dependency to the…
3-D image registration, which involves aligning two or more images, is a critical step in a variety of medical applications from diagnosis to therapy. Image registration is commonly performed by optimizing an image matching metric as a cost…
Real-world image matting is essential for applications in content creation and augmented reality. However, it remains challenging due to the complex nature of scenes and the scarcity of high-quality datasets. To address these limitations,…
Deep learning based visual trackers entail offline pre-training on large volumes of video datasets with accurate bounding box annotations that are labor-expensive to achieve. We present a new framework to facilitate bounding box annotations…
RGBD images with high quality annotations in the form of geometric (i.e., segmentation) and structural (i.e., how do the segments are mutually related in 3D) information provide valuable priors to a large number of scene and image…
Video colorization task has recently attracted wide attention. Recent methods mainly work on the temporal consistency in adjacent frames or frames with small interval. However, it still faces severe challenge of the inconsistency between…
We present a universal framework to model contextualized sentence representations with visual awareness that is motivated to overcome the shortcomings of the multimodal parallel data with manual annotations. For each sentence, we first…
Despite the advances achieved by neural models in sequence to sequence learning, exploited in a variety of tasks, they still make errors. In many use cases, these are corrected by a human expert in a posterior revision process. The…
Active learning methods, like uncertainty sampling, combined with probabilistic prediction techniques have achieved success in various problems like image classification and text classification. For more complex multivariate prediction…
Temporal correspondence - linking pixels or objects across frames - is a fundamental supervisory signal for the video models. For the panoptic understanding of dynamic scenes, we further extend this concept to every segment. Specifically,…
Inferring detailed 3D geometry of the scene is crucial for robotics applications, simulation, and 3D content creation. However, such information is hard to obtain, and thus very few datasets support it. In this paper, we propose an…