Search Results for author:
Found 28 papers, 18 papers with code
MOT16: A Benchmark for Multi-Object Tracking
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.
To Learn or Not to Learn: Visual Localization from Essential Matrices
Using a classical feature-based approach within this framework, we show state-of-the-art performance.
DeepLab2: A TensorFlow Library for Deep Labeling
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.
HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking
Multi-Object Tracking (MOT) has been notoriously difficult to evaluate.
Tracking without bells and whistles
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
How To Train Your Deep Multi-Object Tracker
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
Make One-Shot Video Object Segmentation Efficient Again
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)
TrackFormer: Multi-Object Tracking with Transformers
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)
Patch2Pix: Epipolar-Guided Pixel-Level Correspondences
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.
The Group Loss for Deep Metric Learning
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)
Understanding the Limitations of CNN-based Absolute Camera Pose Regression
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.
MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Prediction
Pedestrian trajectory prediction is challenging due to its uncertain and multimodal nature.
MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?
Deep learning-based methods for video pedestrian detection and tracking require large volumes of training data to achieve good performance.
Multi-Object Tracking and Segmentation via Neural Message Passing
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
Lake Ice Monitoring with Webcams and Crowd-Sourced Images
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
Ice Monitoring in Swiss Lakes from Optical Satellites and Webcams using Machine Learning
and generalisation scores of 71% (approx.)
Lifting Layers: Analysis and Applications
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.
Photi-LakeIce Dataset
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
Automatic tracking of vessel-like structures from a single starting point
Further visual results also show the potential of our approach for identifying vascular networks topologies.
Class Generative Models Based on Feature Regression for Pose Estimation of Object Categories
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.
Learning an Image-based Motion Context for Multiple People Tracking
We present a novel method for multiple people tracking that leverages a generalized model for capturing interactions among individuals.
Joint Tracking and Segmentation of Multiple Targets
Tracking-by-detection has proven to be the most successful strategy to address the task of tracking multiple targets in unconstrained scenarios.
Continuous Pose Estimation With a Spatial Ensemble of Fisher Regressors
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.
CVPR19 Tracking and Detection Challenge: How crowded can it get?
Standardized benchmarks are crucial for the majority of computer vision applications.
Not All Labels Are Equal: Rationalizing The Labeling Costs for Training Object Detection
Deep neural networks have reached high accuracy on object detection but their success hinges on large amounts of labeled data.
Text2Pos: Text-to-Point-Cloud Cross-Modal Localization
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.
The Group Loss++: A deeper look into group loss for deep metric learning
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.
NOVIS: A Case for End-to-End Near-Online Video Instance Segmentation
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)
