no code implementations • 2 Nov 2023 • Ali Athar, Enxu Li, Sergio Casas, Raquel Urtasun
4D panoptic segmentation is a challenging but practically useful task that requires every point in a LiDAR point-cloud sequence to be assigned a semantic class label, and individual objects to be segmented and tracked over time.
Ranked #1 on Panoptic Tracking on Panoptic nuScenes val
1 code implementation • CVPR 2023 • Ali Athar, Alexander Hermans, Jonathon Luiten, Deva Ramanan, Bastian Leibe
A single TarViS model can be trained jointly on a collection of datasets spanning different tasks, and can hot-swap between tasks during inference without any task-specific retraining.
Ranked #2 on Video Panoptic Segmentation on KITTI-STEP (using extra training data)
1 code implementation • 25 Sep 2022 • Ali Athar, Jonathon Luiten, Paul Voigtlaender, Tarasha Khurana, Achal Dave, Bastian Leibe, Deva Ramanan
Multiple existing benchmarks involve tracking and segmenting objects in video e. g., Video Object Segmentation (VOS) and Multi-Object Tracking and Segmentation (MOTS), but there is little interaction between them due to the use of disparate benchmark datasets and metrics (e. g. J&F, mAP, sMOTSA).
Ranked #4 on Long-tail Video Object Segmentation on BURST-val (using extra training data)
Long-tail Video Object Segmentation Multi-Object Tracking +6
1 code implementation • 1 Jun 2022 • Ali Athar, Jonathon Luiten, Alexander Hermans, Deva Ramanan, Bastian Leibe
Recently, "Masked Attention" was proposed in which a given object representation only attends to those image pixel features for which the segmentation mask of that object is active.
1 code implementation • CVPR 2022 • Ali Athar, Jonathon Luiten, Alexander Hermans, Deva Ramanan, Bastian Leibe
Existing state-of-the-art methods for Video Object Segmentation (VOS) learn low-level pixel-to-pixel correspondences between frames to propagate object masks across video.
1 code implementation • 15 Nov 2021 • Christian Schmidt, Ali Athar, Sabarinath Mahadevan, Bastian Leibe
We further show that D^2Conv3D out-performs trivial extensions of existing dilated and deformable convolutions to 3D.
2 code implementations • WACV 2021 • Christian Schmidt, Ali Athar, Sabarinath Mahadevan, Bastian Leibe
We further show that D2Conv3D out-performs trivial extensions of existing dilated and deformable convolutions to 3D.
1 code implementation • 26 Aug 2020 • Sabarinath Mahadevan, Ali Athar, Aljoša Ošep, Sebastian Hennen, Laura Leal-Taixé, Bastian Leibe
On the other hand, 3D convolutional networks have been successfully applied for video classification tasks, but have not been leveraged as effectively to problems involving dense per-pixel interpretation of videos compared to their 2D convolutional counterparts and lag behind the aforementioned networks in terms of performance.
Ranked #13 on Unsupervised Video Object Segmentation on DAVIS 2016 val
1 code implementation • ECCV 2020 • Ali Athar, Sabarinath Mahadevan, Aljoša Ošep, Laura Leal-Taixé, Bastian Leibe
In this paper, we propose a different approach that is well-suited to a variety of tasks involving instance segmentation in videos.
Ranked #5 on Unsupervised Video Object Segmentation on DAVIS 2017 (val) (using extra training data)
no code implementations • 9 Nov 2018 • Maryam Babaee, Ali Athar, Gerhard Rigoll
To this end, tracklet re-identification is performed by utilizing a novel multi-stage deep network that can jointly reason about the visual appearance and spatio-temporal properties of a pair of tracklets, thereby providing a robust measure of affinity.
no code implementations • 22 Aug 2018 • Ali Athar
Convolutional Neural Networks (CNNs) are becoming increasingly popular due to their superior performance in the domain of computer vision, in applications such as objection detection and recognition.