Laura Leal-Taixé

papers

2,465

total citations

papers (26)

TrackFormer: Multi-Object Tracking With Transformers

CVPR 2022arXiv

968

citations

STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos

ECCV 2020arXiv

187

citations

MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Prediction

ICCV 2021arXiv

139

citations

MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?

ICCV 2021arXiv

126

citations

DynamicEarthNet: Daily Multi-Spectral Satellite Dataset for Semantic Change Segmentation

CVPR 2022arXiv

120

citations

Quo Vadis: Is Trajectory Forecasting the Key Towards Long-Term Multi-Object Tracking?

NEURIPS 2022arXiv

citations

The Group Loss for Deep Metric Learning

ECCV 2020arXiv

citations

Not All Labels Are Equal: Rationalizing the Labeling Costs for Training Object Detection

CVPR 2022arXiv

citations

The Center of Attention: Center-Keypoint Grouping via Attention for Multi-Person Pose Estimation

ICCV 2021arXiv

citations

Forecasting From LiDAR via Future Object Detection

CVPR 2022arXiv

citations

Make One-Shot Video Object Segmentation Efficient Again

NEURIPS 2020arXiv

citations

Text2Pos: Text-to-Point-Cloud Cross-Modal Localization

CVPR 2022arXiv

citations

A Unified Framework for Implicit Sinkhorn Differentiation

CVPR 2022arXiv

citations

Walking Your LiDOG: A Journey Through Multiple Domains for LiDAR Semantic Segmentation

ICCV 2023arXiv

citations

Towards a Unified Copernicus Foundation Model for Earth Vision

ICCV 2025arXiv

citations

Soft Augmentation for Image Classification

CVPR 2023arXiv

citations

Learning to Discover and Detect Objects

NEURIPS 2022arXiv

citations

G-MSM: Unsupervised Multi-Shape Matching With Graph-Based Affinity Priors

CVPR 2023arXiv

citations

The Unreasonable Effectiveness of Fully-Connected Layers for Low-Data Regimes

NEURIPS 2022arXiv

citations

(Just) A Spoonful of Refinements Helps the Registration Error Go Down

ICCV 2021arXiv

citations

Laura Leal-Taixé

papers (26)

TrackFormer: Multi-Object Tracking With Transformers

STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos

MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Prediction

MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?

DynamicEarthNet: Daily Multi-Spectral Satellite Dataset for Semantic Change Segmentation

Unifying Short and Long-Term Tracking With Graph Hierarchies

Deep Shells: Unsupervised Shape Correspondence with Optimal Transport

Simple Cues Lead to a Strong Multi-Object Tracker

PolarMOT: How Far Can Geometric Relations Take Us in 3D Multi-Object Tracking?

Opening Up Open World Tracking

Is Geometry Enough for Matching in Visual Localization?

Quo Vadis: Is Trajectory Forecasting the Key Towards Long-Term Multi-Object Tracking?

The Group Loss for Deep Metric Learning

Not All Labels Are Equal: Rationalizing the Labeling Costs for Training Object Detection

The Center of Attention: Center-Keypoint Grouping via Attention for Multi-Person Pose Estimation

Forecasting From LiDAR via Future Object Detection

Make One-Shot Video Object Segmentation Efficient Again

Text2Pos: Text-to-Point-Cloud Cross-Modal Localization

A Unified Framework for Implicit Sinkhorn Differentiation

Walking Your LiDOG: A Journey Through Multiple Domains for LiDAR Semantic Segmentation

Towards a Unified Copernicus Foundation Model for Earth Vision

Soft Augmentation for Image Classification

Learning to Discover and Detect Objects

G-MSM: Unsupervised Multi-Shape Matching With Graph-Based Affinity Priors

The Unreasonable Effectiveness of Fully-Connected Layers for Low-Data Regimes

(Just) A Spoonful of Refinements Helps the Registration Error Go Down

papers (26)

TrackFormer: Multi-Object Tracking With Transformers

STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos

MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Prediction

MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?

DynamicEarthNet: Daily Multi-Spectral Satellite Dataset for Semantic Change Segmentation

Unifying Short and Long-Term Tracking With Graph Hierarchies

Deep Shells: Unsupervised Shape Correspondence with Optimal Transport

Simple Cues Lead to a Strong Multi-Object Tracker

PolarMOT: How Far Can Geometric Relations Take Us in 3D Multi-Object Tracking?

Opening Up Open World Tracking

Is Geometry Enough for Matching in Visual Localization?

Quo Vadis: Is Trajectory Forecasting the Key Towards Long-Term Multi-Object Tracking?

The Group Loss for Deep Metric Learning

Not All Labels Are Equal: Rationalizing the Labeling Costs for Training Object Detection

The Center of Attention: Center-Keypoint Grouping via Attention for Multi-Person Pose Estimation

Forecasting From LiDAR via Future Object Detection

Make One-Shot Video Object Segmentation Efficient Again

Text2Pos: Text-to-Point-Cloud Cross-Modal Localization

A Unified Framework for Implicit Sinkhorn Differentiation

Walking Your LiDOG: A Journey Through Multiple Domains for LiDAR Semantic Segmentation

Towards a Unified Copernicus Foundation Model for Earth Vision

Soft Augmentation for Image Classification

Learning to Discover and Detect Objects

G-MSM: Unsupervised Multi-Shape Matching With Graph-Based Affinity Priors

The Unreasonable Effectiveness of Fully-Connected Layers for Low-Data Regimes

(Just) A Spoonful of Refinements Helps the Registration Error Go Down