SFTrack++: A Fast Learnable Spectral Segmentation Approach for Space-Time Consistent Tracking

Elena Burceanu
NeurIPS 2020 Workshop on Pre-registration in Machine Learning, PMLR 148:126-138, 2021.

Abstract

We propose an object tracking method, SFTrack++, that smoothly learns to preserve the tracked object consistency over space and time dimensions by taking a spectral clustering approach over the graph of pixels from the video, using a fast 3D filtering formulation for finding the principal eigenvector of this graph’s adjacency matrix. To better capture complex aspects of the tracked object, we enrich our formulation to multi-channel inputs, which permit different points of view for the same input. The channel inputs are in our experiments, the output of multiple tracking methods. After combining them, instead of relying only on hidden layers representations to predict a good tracking bounding box, we explicitly learn an intermediate, more refined one, namely the segmentation map of the tracked object. This prevents the rough common bounding box approach to introduce noise and distractors in the learning process. We test our method, SFTrack++, on five tracking benchmarks: OTB, UAV, NFS, GOT-10k, and TrackingNet, using five top trackers as input. Our experimental results validate the pre-registered hypothesis. We obtain consistent and robust results, competitive on the three traditional benchmarks (OTB, UAV, NFS) and significantly on top of others (by over $1.1%$ on accuracy) on GOT-10k and TrackingNet, which are newer, larger, and more varied datasets.

Cite this Paper


BibTeX
@InProceedings{pmlr-v148-burceanu21a, title = {SFTrack++: A Fast Learnable Spectral Segmentation Approach for Space-Time Consistent Tracking}, author = {Burceanu, Elena}, booktitle = {NeurIPS 2020 Workshop on Pre-registration in Machine Learning}, pages = {126--138}, year = {2021}, editor = {Bertinetto, Luca and Henriques, João F. and Albanie, Samuel and Paganini, Michela and Varol, Gül}, volume = {148}, series = {Proceedings of Machine Learning Research}, month = {11 Dec}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v148/burceanu21a/burceanu21a.pdf}, url = {http://proceedings.mlr.press/v148/burceanu21a.html}, abstract = {We propose an object tracking method, SFTrack++, that smoothly learns to preserve the tracked object consistency over space and time dimensions by taking a spectral clustering approach over the graph of pixels from the video, using a fast 3D filtering formulation for finding the principal eigenvector of this graph’s adjacency matrix. To better capture complex aspects of the tracked object, we enrich our formulation to multi-channel inputs, which permit different points of view for the same input. The channel inputs are in our experiments, the output of multiple tracking methods. After combining them, instead of relying only on hidden layers representations to predict a good tracking bounding box, we explicitly learn an intermediate, more refined one, namely the segmentation map of the tracked object. This prevents the rough common bounding box approach to introduce noise and distractors in the learning process. We test our method, SFTrack++, on five tracking benchmarks: OTB, UAV, NFS, GOT-10k, and TrackingNet, using five top trackers as input. Our experimental results validate the pre-registered hypothesis. We obtain consistent and robust results, competitive on the three traditional benchmarks (OTB, UAV, NFS) and significantly on top of others (by over $1.1%$ on accuracy) on GOT-10k and TrackingNet, which are newer, larger, and more varied datasets.} }
Endnote
%0 Conference Paper %T SFTrack++: A Fast Learnable Spectral Segmentation Approach for Space-Time Consistent Tracking %A Elena Burceanu %B NeurIPS 2020 Workshop on Pre-registration in Machine Learning %C Proceedings of Machine Learning Research %D 2021 %E Luca Bertinetto %E João F. Henriques %E Samuel Albanie %E Michela Paganini %E Gül Varol %F pmlr-v148-burceanu21a %I PMLR %P 126--138 %U http://proceedings.mlr.press/v148/burceanu21a.html %V 148 %X We propose an object tracking method, SFTrack++, that smoothly learns to preserve the tracked object consistency over space and time dimensions by taking a spectral clustering approach over the graph of pixels from the video, using a fast 3D filtering formulation for finding the principal eigenvector of this graph’s adjacency matrix. To better capture complex aspects of the tracked object, we enrich our formulation to multi-channel inputs, which permit different points of view for the same input. The channel inputs are in our experiments, the output of multiple tracking methods. After combining them, instead of relying only on hidden layers representations to predict a good tracking bounding box, we explicitly learn an intermediate, more refined one, namely the segmentation map of the tracked object. This prevents the rough common bounding box approach to introduce noise and distractors in the learning process. We test our method, SFTrack++, on five tracking benchmarks: OTB, UAV, NFS, GOT-10k, and TrackingNet, using five top trackers as input. Our experimental results validate the pre-registered hypothesis. We obtain consistent and robust results, competitive on the three traditional benchmarks (OTB, UAV, NFS) and significantly on top of others (by over $1.1%$ on accuracy) on GOT-10k and TrackingNet, which are newer, larger, and more varied datasets.
APA
Burceanu, E.. (2021). SFTrack++: A Fast Learnable Spectral Segmentation Approach for Space-Time Consistent Tracking. NeurIPS 2020 Workshop on Pre-registration in Machine Learning, in Proceedings of Machine Learning Research 148:126-138 Available from http://proceedings.mlr.press/v148/burceanu21a.html.

Related Material