Related papers: A Lightweight Domain Adaptive Absolute Pose Regres…

We present a novel approach to perform the unsupervised domain adaptation for object detection through forward-backward cyclic (FBC) training. Recent adversarial training based domain adaptation methods have shown their effectiveness on…

An accurate and robust large-scale localization system is an integral component for active areas of research such as autonomous vehicles and augmented reality. To this end, many learning algorithms have been proposed that predict 6DOF…

Domain gaps between training data (source) and real-world environments (target) often degrade the performance of object detection models. Most existing methods aim to bridge this gap by aligning features across source and target domains but…

Can we detect common objects in a variety of image domains without instance-level annotations? In this paper, we present a framework for a novel task, cross-domain weakly supervised object detection, which addresses this question. For this…

We propose a direct, regression-based approach to 2D human pose estimation from single images. We formulate the problem as a sequence prediction task, which we solve using a Transformer network. This network directly learns a regression…

Harvesting dense pixel-level annotations to train deep neural networks for semantic segmentation is extremely expensive and unwieldy at scale. While learning from synthetic data where labels are readily available sounds promising,…

This work presents a novel Convolutional Neural Network (CNN) architecture and a training procedure to enable robust and accurate pose estimation of a noncooperative spacecraft. First, a new CNN architecture is introduced that has scored a…

We propose an approach for unsupervised adaptation of object detectors from label-rich to label-poor domains which can significantly reduce annotation costs associated with detection. Recently, approaches that align distributions of source…

Landmark localization is a challenging problem in computer vision with a multitude of applications. Recent deep learning based methods have shown improved results by regressing likelihood maps instead of regressing the coordinates directly.…

A cross-domain visual place recognition (VPR) task is proposed in this work, i.e., matching images of the same architectures depicted in different domains. VPR is commonly treated as an image retrieval task, where a query image from an…

Visual localization occupies an important position in many areas such as Augmented Reality, robotics and 3D reconstruction. The state-of-the-art visual localization methods perform pose estimation using geometry based solver within the…

This paper proposes a statistical approach to 2D pose estimation from human images. The main problems with the standard supervised approach, which is based on a deep recognition (image-to-pose) model, are that it often yields anatomically…

Recent research on learned visual descriptors has shown promising improvements in correspondence estimation, a key component of many 3D vision tasks. However, existing descriptor learning frameworks typically require ground-truth…

In this paper, we tackle the domain adaptive object detection problem, where the main challenge lies in significant domain gaps between source and target domains. Previous work seeks to plainly align image-level and instance-level shifts to…

Due to the fast processing-speed and robustness it can achieve, skeleton-based action recognition has recently received the attention of the computer vision community. The recent Convolutional Neural Network (CNN)-based methods have shown…

Applying an object detector, which is neither trained nor fine-tuned on data close to the final application, often leads to a substantial performance drop. In order to overcome this problem, it is necessary to consider a shift between…

Modern deep neural networks (DNNs) are highly accurate on many recognition tasks for overhead (e.g., satellite) imagery. However, visual domain shifts (e.g., statistical changes due to geography, sensor, or atmospheric conditions) remain a…

Fully convolutional models for dense prediction have proven successful for a wide range of visual tasks. Such models perform well in a supervised setting, but performance can be surprisingly poor under domain shifts that appear mild to a…

Object pose estimation is important for object manipulation and scene understanding. In order to improve the general applicability of pose estimators, recent research focuses on providing estimates for novel objects, that is objects unseen…

In this work, we propose a method for object recognition and pose estimation from depth images using convolutional neural networks. Previous methods addressing this problem rely on manifold learning to learn low dimensional viewpoint…