Two Video Data Sets for Tracking and Retrieval of Out of Distribution Objects
Kira Maag, Robin Chan, Svenja Uhlemeyer, Kamil Kowol, Hanno Gottschalk

TL;DR
This paper introduces two new video datasets for out of distribution object tracking, along with metrics and a baseline algorithm, to advance detection and tracking of novel objects in video sequences.
Contribution
The paper presents two novel video datasets for OOD tracking, proposes evaluation metrics, and develops a baseline algorithm for the task.
Findings
The SOS dataset contains over 1000 labeled frames with OOD objects.
The CARLA-WildLife dataset includes synthetic videos with multiple OOD objects.
A baseline algorithm demonstrates effective OOD object tracking.
Abstract
In this work we present two video test data sets for the novel computer vision (CV) task of out of distribution tracking (OOD tracking). Here, OOD objects are understood as objects with a semantic class outside the semantic space of an underlying image segmentation algorithm, or an instance within the semantic space which however looks decisively different from the instances contained in the training data. OOD objects occurring on video sequences should be detected on single frames as early as possible and tracked over their time of appearance as long as possible. During the time of appearance, they should be segmented as precisely as possible. We present the SOS data set containing 20 video sequences of street scenes and more than 1000 labeled frames with up to two OOD objects. We furthermore publish the synthetic CARLA-WildLife data set that consists of 26 video sequences containing…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsVideo Surveillance and Tracking Methods · Advanced Image and Video Retrieval Techniques · Remote-Sensing Image Classification
MethodsTest
