no code implementations • 29 Aug 2023 • Tim Meinhardt, Matt Feiszli, Yuchen Fan, Laura Leal-Taixe, Rakesh Ranjan
Until recently, the Video Instance Segmentation (VIS) community operated under the common belief that offline methods are generally superior to a frame by frame online processing.
Ranked #5 on Video Instance Segmentation on YouTube-VIS validation (using extra training data)
1 code implementation • 15 Jul 2022 • Guillem Braso, Orcun Cetintas, Laura Leal-Taixe
We achieve state-of-the-art results for both tracking and segmentation in several publicly available datasets.
Multi-Object Tracking Multi-Object Tracking and Segmentation +2
no code implementations • 4 Apr 2022 • Ismail Elezi, Jenny Seidenschwarz, Laurin Wagner, Sebastiano Vascon, Alessandro Torcinovich, Marcello Pelillo, Laura Leal-Taixe
Deep metric learning has yielded impressive results in tasks such as clustering and image retrieval by leveraging neural networks to obtain highly discriminative feature embeddings, which can be used to group samples into different classes.
no code implementations • CVPR 2022 • Manuel Kolmet, Qunjie Zhou, Aljosa Osep, Laura Leal-Taixe
Natural language-based communication with mobile devices and home appliances is becoming increasingly popular and has the potential to become natural for communicating with mobile robots in the future.
1 code implementation • ICCV 2021 • Matteo Fabbri, Guillem Braso, Gianluca Maugeri, Orcun Cetintas, Riccardo Gasparini, Aljosa Osep, Simone Calderara, Laura Leal-Taixe, Rita Cucchiara
Deep learning-based methods for video pedestrian detection and tracking require large volumes of training data to achieve good performance.
1 code implementation • ICCV 2021 • Patrick Dendorfer, Sven Elflein, Laura Leal-Taixe
Pedestrian trajectory prediction is challenging due to its uncertain and multimodal nature.
no code implementations • CVPR 2022 • Ismail Elezi, Zhiding Yu, Anima Anandkumar, Laura Leal-Taixe, Jose M. Alvarez
Deep neural networks have reached high accuracy on object detection but their success hinges on large amounts of labeled data.
4 code implementations • 17 Jun 2021 • Mark Weber, Huiyu Wang, Siyuan Qiao, Jun Xie, Maxwell D. Collins, Yukun Zhu, Liangzhe Yuan, Dahun Kim, Qihang Yu, Daniel Cremers, Laura Leal-Taixe, Alan L. Yuille, Florian Schroff, Hartwig Adam, Liang-Chieh Chen
DeepLab2 is a TensorFlow library for deep labeling, aiming to provide a state-of-the-art and easy-to-use TensorFlow codebase for general dense pixel prediction problems in computer vision.
2 code implementations • CVPR 2022 • Tim Meinhardt, Alexander Kirillov, Laura Leal-Taixe, Christoph Feichtenhofer
The challenging task of multi-object tracking (MOT) requires simultaneous reasoning about track initialization, identity, and spatio-temporal trajectories.
Ranked #1 on Multi-Object Tracking on MOT17 (e2e-MOT metric)
4 code implementations • NeurIPS 2020 • Tim Meinhardt, Laura Leal-Taixe
In the semi-supervised setting, the first mask of each object is provided at test time.
Ranked #43 on Semi-Supervised Video Object Segmentation on YouTube-VOS 2018 (using extra training data)
1 code implementation • CVPR 2021 • Qunjie Zhou, Torsten Sattler, Laura Leal-Taixe
In this work, we propose a new perspective to estimate correspondences in a detect-to-refine manner, where we first predict patch-level match proposals and then refine them.
2 code implementations • 27 Oct 2020 • Manu Tom, Rajanie Prabha, Tianyu Wu, Emmanuel Baltsavias, Laura Leal-Taixe, Konrad Schindler
and generalisation scores of 71% (approx.)
5 code implementations • 16 Sep 2020 • Jonathon Luiten, Aljosa Osep, Patrick Dendorfer, Philip Torr, Andreas Geiger, Laura Leal-Taixe, Bastian Leibe
Multi-Object Tracking (MOT) has been notoriously difficult to evaluate.
1 code implementation • ISPRS Congress 2020 • Rajanie Prabha, Manu Tom, Mathias Rothermel, Emmanuel Baltsavias, Laura Leal-Taixe, Konrad Schindler
On average, it achieves intersection-over-union (IoU) values of ~71% across different cameras and ~69% across different winters, greatly outperforming prior work.
Change detection for remote sensing images Image Segmentation +4
2 code implementations • 18 Feb 2020 • Rajanie Prabha, Manu Tom, Mathias Rothermel, Emmanuel Baltsavias, Laura Leal-Taixe, Konrad Schindler
On average, it achieves intersection-over-union (IoU) values of ~71% across different cameras and ~69% across different winters, greatly outperforming prior work.
Change detection for remote sensing images Image Segmentation +4
2 code implementations • ECCV 2020 • Ismail Elezi, Sebastiano Vascon, Alessandro Torcinovich, Marcello Pelillo, Laura Leal-Taixe
Deep metric learning has yielded impressive results in tasks such as clustering and image retrieval by leveraging neural networks to obtain highly discriminative feature embeddings, which can be used to group samples into different classes.
Ranked #20 on Metric Learning on CUB-200-2011 (using extra training data)
1 code implementation • 4 Aug 2019 • Qunjie Zhou, Torsten Sattler, Marc Pollefeys, Laura Leal-Taixe
Using a classical feature-based approach within this framework, we show state-of-the-art performance.
2 code implementations • CVPR 2020 • Yihong Xu, Aljosa Osep, Yutong Ban, Radu Horaud, Laura Leal-Taixe, Xavier Alameda-Pineda
In this paper, we bridge this gap by proposing a differentiable proxy of MOTA and MOTP, which we combine in a loss function suitable for end-to-end training of deep multi-object trackers.
Ranked #4 on Multi-Object Tracking on 2D MOT 2015
no code implementations • 10 Jun 2019 • Patrick Dendorfer, Hamid Rezatofighi, Anton Milan, Javen Shi, Daniel Cremers, Ian Reid, Stefan Roth, Konrad Schindler, Laura Leal-Taixe
Standardized benchmarks are crucial for the majority of computer vision applications.
1 code implementation • CVPR 2019 • Torsten Sattler, Qunjie Zhou, Marc Pollefeys, Laura Leal-Taixe
We furthermore use our model to show that pose regression is more closely related to pose approximation via image retrieval than to accurate pose estimation via 3D structure.
13 code implementations • ICCV 2019 • Philipp Bergmann, Tim Meinhardt, Laura Leal-Taixe
Therefore, we motivate our approach as a new tracking paradigm and point out promising future research directions.
Ranked #1 on Online Multi-Object Tracking on 2D MOT 2015
1 code implementation • ECCV 2018 • Peter Ochs, Tim Meinhardt, Laura Leal-Taixe, Michael Moeller
A lifting layer increases the dimensionality of the input, naturally yields a linear spline when combined with a fully connected layer, and therefore closes the gap between low and high dimensional approximation problems.
no code implementations • 8 Jun 2017 • Dario Augusto Borges Oliveira, Laura Leal-Taixe, Raul Queiroz Feitosa, Bodo Rosenhahn
Further visual results also show the potential of our approach for identifying vascular networks topologies.
8 code implementations • 2 Mar 2016 • Anton Milan, Laura Leal-Taixe, Ian Reid, Stefan Roth, Konrad Schindler
Recently, a new benchmark for Multiple Object Tracking, MOTChallenge, was launched with the goal of collecting existing and new data and creating a framework for the standardized evaluation of multiple object tracking methods.
no code implementations • ICCV 2015 • Michele Fenzi, Laura Leal-Taixe, Jorn Ostermann, Tinne Tuytelaars
In this paper, we treat the problem of continuous pose estimation for object categories as a regression problem on the basis of only 2D training information.
no code implementations • CVPR 2015 • Anton Milan, Laura Leal-Taixe, Konrad Schindler, Ian Reid
Tracking-by-detection has proven to be the most successful strategy to address the task of tracking multiple targets in unconstrained scenarios.
no code implementations • CVPR 2014 • Laura Leal-Taixe, Michele Fenzi, Alina Kuznetsova, Bodo Rosenhahn, Silvio Savarese
We present a novel method for multiple people tracking that leverages a generalized model for capturing interactions among individuals.
no code implementations • CVPR 2013 • Michele Fenzi, Laura Leal-Taixe, Bodo Rosenhahn, Jorn Ostermann
In this paper, we propose a method for learning a class representation that can return a continuous value for the pose of an unknown class instance using only 2D data and weak 3D labelling information.