Search Results - "Honari, Sina"

Lightweight Multi-View 3D Pose Estimation Through Camera-Disentangled Representation by Remelli, Edoardo, Han, Shangchen, Honari, Sina, Fua, Pascal, Wang, Robert

“…We present a lightweight solution to recover 3D pose from multi-view images captured with spatially calibrated cameras. Building upon recent advances in…”
Get full text

Detecting Road Obstacles by Erasing Them by Lis, Krzysztof, Honari, Sina, Fua, Pascal, Salzmann, Mathieu

“…Vehicles can encounter a myriad of obstacles on the road, and it is impossible to record them all beforehand to train a detector. Instead, we select image…”
Get full text

Temporal Representation Learning on Monocular Videos for 3D Human Pose Estimation by Honari, Sina, Constantin, Victor, Rhodin, Helge, Salzmann, Mathieu, Fua, Pascal

“…In this article we propose an unsupervised feature extraction method to capture temporal information on monocular videos, where we detect and encode subject of…”
Get full text

Recombinator Networks: Learning Coarse-to-Fine Feature Aggregation by Honari, Sina, Yosinski, Jason, Vincent, Pascal, Pal, Christopher

“…Deep neural networks with alternating convolutional, max-pooling and decimation layers are widely used in state of the art architectures for computer vision…”
Get full text

Improving Landmark Localization with Semi-Supervised Learning by Honari, Sina, Molchanov, Pavlo, Tyree, Stephen, Vincent, Pascal, Pal, Christopher, Kautz, Jan

“…We present two techniques to improve landmark localization in images from partially annotated datasets. Our primary goal is to leverage the common situation…”
Get full text

Visual question answering from another perspective: CLEVR mental rotation tests by Beckham, Christopher, Weiss, Martin, Golemo, Florian, Honari, Sina, Nowrouzezahrai, Derek, Pal, Christopher

“…•We propose a version of CLEVR that is inspired by mental rotation tests.•Latent feature volumes can be used instead of feature maps for VQA tasks grounded in…”
Get full text

Overcoming the Domain Gap in Neural Action Representations by Günel, Semih, Aymanns, Florian, Honari, Sina, Ramdya, Pavan, Fua, Pascal

“…Relating behavior to brain activity in animals is a fundamental goal in neuroscience, with practical applications in building robust brain-machine interfaces…”
Get full text

Adversarial Parametric Pose Prior by Davydov, Andrey, Remizova, Anastasia, Constantin, Victor, Honari, Sina, Salzmann, Mathieu, Fua, Pascal

“…The Skinned Multi-Person Linear (SMPL) model represents human bodies by mapping pose and shape parameters to body meshes. However, not all pose and shape…”
Get full text

Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goals by Yuan, Shanxin, Garcia-Hernando, Guillermo, Stenger, Bjorn, Moon, Gyeongsik, Chang, Ju Yong, Lee, Kyoung Mu, Molchanov, Pavlo, Kautz, Jan, Honari, Sina, Ge, Liuhao, Yuan, Junsong, Chen, Xinghao, Wang, Guijin, Yang, Fan, Akiyama, Kai, Wu, Yang, Wan, Qingfu, Madadi, Meysam, Escalera, Sergio, Li, Shile, Lee, Dongheui, Oikonomidis, Iason, Argyros, Antonis, Kim, Tae-Kyun

“…In this paper, we strive to answer two questions: What is the current state of 3D hand pose estimation from depth images? And, what are the next challenges…”
Get full text

Perspective Aware Road Obstacle Detection by Lis, Krzysztof, Honari, Sina, Fua, Pascal, Salzmann, Mathieu

“…While road obstacle detection techniques have become increasingly effective, they typically ignore the fact that, in practice, the apparent size of the…”
Get full text

Improving facial analysis and performance driven animation through disentangling identity and expression by Rim, David, Honari, Sina, Hasan, Md Kamrul, J. Pal, Christopher

“…We present techniques for improving performance driven facial animation, emotion recognition, and facial key-point or landmark prediction using learned…”
Get full text

Towards Unsupervised Blind Face Restoration using Diffusion Prior by Kuai, Tianshu, Honari, Sina, Gilitschenski, Igor, Levinshtein, Alex

“…Blind face restoration methods have shown remarkable performance, particularly when trained on large-scale synthetic datasets with supervised learning. These…”
Get full text

Occlusion Resilient 3D Human Pose Estimation by Roy, Soumava Kumar, Badanin, Ilia, Honari, Sina, Fua, Pascal

“…Occlusions remain one of the key challenges in 3D body pose estimation from single-camera video sequences. Temporal consistency has been extensively used to…”
Get full text

Unsupervised 3D Keypoint Discovery with Multi-View Geometry by Honari, Sina, Zhao, Chen, Salzmann, Mathieu, Fua, Pascal

“…Analyzing and training 3D body posture models depend heavily on the availability of joint labels that are commonly acquired through laborious manual annotation…”
Get full text

Occlusion Resilient 3D Human Pose Estimation by Roy, Soumava Kumar, Badanin, Ilia, Honari, Sina, Fua, Pascal

“…Occlusions remain one of the key challenges in 3D body pose estimation from single-camera video sequences. Temporal consistency has been extensively used to…”
Get full text

On Triangulation as a Form of Self-Supervision for 3D Human Pose Estimation by Roy, Soumava Kumar, Citraro, Leonardo, Honari, Sina, Fua, Pascal

“…Supervised approaches to 3D pose estimation from single images are remarkably effective when labeled data is abundant. However, as the acquisition of…”
Get full text

Perspective Aware Road Obstacle Detection by Lis, Krzysztof, Honari, Sina, Fua, Pascal, Salzmann, Mathieu

“…IEEE Robotics and Automation Letters ( Volume: 8, Issue: 4, April 2023, Pages: 2150-2157) While road obstacle detection techniques have become increasingly…”
Get full text

Temporal Representation Learning on Monocular Videos for 3D Human Pose Estimation by Honari, Sina, Constantin, Victor, Rhodin, Helge, Salzmann, Mathieu, Fua, Pascal

“…IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022 In this paper we propose an unsupervised feature extraction method to capture temporal…”
Get full text

Unsupervised 3D Keypoint Discovery with Multi-View Geometry by Honari, Sina, Zhao, Chen, Salzmann, Mathieu, Fua, Pascal

“…Analyzing and training 3D body posture models depend heavily on the availability of joint labels that are commonly acquired through laborious manual annotation…”
Get full text

On Triangulation as a Form of Self-Supervision for 3D Human Pose Estimation by Roy, Soumava Kumar, Citraro, Leonardo, Honari, Sina, Fua, Pascal

“…Supervised approaches to 3D pose estimation from single images are remarkably effective when labeled data is abundant. However, as the acquisition of…”
Get full text