Print Email Facebook Twitter Objects do not disappear Title Objects do not disappear: Video object detection by single-frame object location anticipation Author Liu, X. (TU Delft Pattern Recognition and Bioinformatics) van Gemert, J.C. (TU Delft Pattern Recognition and Bioinformatics) Nejadasl, Fatemeh Karimi (Universiteit van Amsterdam) Booij, O. (TU Delft Pattern Recognition and Bioinformatics) Pintea, S. (TU Delft Pattern Recognition and Bioinformatics) Contributor Ceballos, Cristina (editor) Date 2023 Abstract Objects in videos are typically characterized by continuous smooth motion. We exploit continuous smooth motion in three ways. 1) Improved accuracy by using object motion as an additional source of supervision, which we obtain by anticipating object locations from a static keyframe. 2) Improved efficiency by only doing the expensive feature computations on a small subset of all frames. Because neighboring video frames are often redundant, we only compute features for a single static keyframe and predict object locations in subsequent frames. 3) Reduced annotation cost, where we only annotate the keyframe and use smooth pseudo-motion between keyframes. We demonstrate computational efficiency, annotation efficiency, and improved mean average precision compared to the state-of-the-art on four datasets: ImageNet VID, EPIC KITCHENS-55, YouTube-BoundingBoxes and Waymo Open dataset. Our source code is available at https://github.com/L-KID/Video-object-detection-by-location-anticipation. To reference this document use: http://resolver.tudelft.nl/uuid:8b66a4c1-eabe-49a2-8af1-24ddd275ebbb DOI https://doi.org/10.1109/ICCV51070.2023.00640 Publisher IEEE, Piscataway Embargo date 2024-07-15 ISBN 979-8-3503-0719-1 Source Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision (ICCV) Event 2023 IEEE/CVF International Conference on Computer Vision (ICCV), 2023-10-01 → 2023-10-06, Paris, France Series Proceedings of the IEEE International Conference on Computer Vision, 1550-5499 Bibliographical note Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. Part of collection Institutional Repository Document type conference paper Rights © 2023 X. Liu, J.C. van Gemert, Fatemeh Karimi Nejadasl, O. Booij, S. Pintea Files file embargo until 2024-07-15