Viewpoints and keypoints
S Tulsiani, J Malik - … of the IEEE Conference on Computer …, 2015 - openaccess.thecvf.com
We characterize the problem of pose estimation for rigid objects in terms of determining
viewpoint to explain coarse pose and keypoint prediction to capture the finer details. We …
viewpoint to explain coarse pose and keypoint prediction to capture the finer details. We …
Fast single shot detection and pose estimation
For applications in navigation and robotics, estimating the 3D pose of objects is as important
as detection. Many approaches to pose estimation rely on detecting or tracking parts or …
as detection. Many approaches to pose estimation rely on detecting or tracking parts or …
When and how convolutional neural networks generalize to out-of-distribution category–viewpoint combinations
S Madan, T Henry, J Dozier, H Ho, N Bhandari… - Nature Machine …, 2022 - nature.com
Object recognition and viewpoint estimation lie at the heart of visual understanding. Recent
studies have suggested that convolutional neural networks (CNNs) fail to generalize to out …
studies have suggested that convolutional neural networks (CNNs) fail to generalize to out …
Designing deep convolutional neural networks for continuous object orientation estimation
Deep Convolutional Neural Networks (DCNN) have been proven to be effective for various
computer vision problems. In this work, we demonstrate its effectiveness on a continuous …
computer vision problems. In this work, we demonstrate its effectiveness on a continuous …
Sparse template-based 6-D pose estimation of metal parts using a monocular camera
Z He, Z Jiang, X Zhao, S Zhang… - IEEE Transactions on …, 2019 - ieeexplore.ieee.org
The six-dimensional (6-D) pose estimation of smooth metal parts is a common and important
task in intelligent manufacturing. Computer-aided design (CAD)-based monocular vision …
task in intelligent manufacturing. Computer-aided design (CAD)-based monocular vision …
Learning category-specific deformable 3d models for object reconstruction
S Tulsiani, A Kar, J Carreira… - IEEE transactions on …, 2016 - ieeexplore.ieee.org
We address the problem of fully automatic object localization and reconstruction from a
single image. This is both a very challenging and very important problem which has, until …
single image. This is both a very challenging and very important problem which has, until …
Video emotion recognition with transferred deep feature encodings
Despite growing research interest, emotion understanding for user-generated videos
remains a challenging problem. Major obstacles include the diversity and complexity of …
remains a challenging problem. Major obstacles include the diversity and complexity of …
MEBOW: Monocular estimation of body orientation in the wild
Body orientation estimation provides crucial visual cues in many applications, including
robotics and autonomous driving. It is particularly desirable when 3-D pose estimation is …
robotics and autonomous driving. It is particularly desirable when 3-D pose estimation is …
Pedestrian planar LiDAR pose (PPLP) network for oriented pedestrian detection based on planar LiDAR and monocular images
Pedestrian detection is an important task for human-robot interaction and autonomous
driving applications. Most previous pedestrian detection methods rely on data collected from …
driving applications. Most previous pedestrian detection methods rely on data collected from …
The three R's of computer vision: Recognition, reconstruction and reorganization
We argue for the importance of the interaction between recognition, reconstruction and re-
organization, and propose that as a unifying framework for computer vision. In this view …
organization, and propose that as a unifying framework for computer vision. In this view …