activity
20182023
most citedSee through Gradients: Image Batch Recovery via GradInversion

30 citations · 67 across the 8 of their papers we have counts for

collaborators

11 papers

cs.CV20218 cited

Adversarial Motion Modelling helps Semi-supervised Hand Pose Estimation

Adrian Spurr, Pavlo Molchanov, Umar Iqbal +2

Hand pose estimation is difficult due to different environmental conditions, object- and self-occlusion as well as diversity in hand shape and appearance. Exhaustively covering thi…

cs.CV2021

KAMA: 3D Keypoint Aware Body Mesh Articulation

Umar Iqbal, Kevin Xie, Yunrong Guo +2

We present KAMA, a 3D Keypoint Aware Mesh Articulation approach that allows us to estimate a human body mesh from the positions of 3D body keypoints. To this end, we learn to estim…

cs.LG202130 cited

See through Gradients: Image Batch Recovery via GradInversion

Hongxu Yin, Arun Mallya, Arash Vahdat +3

Training deep neural networks requires gradient estimation from data batches to update parameters. Gradients per parameter are averaged over a set of data and this has been presume…

cs.CV2020

Parameter Efficient Multimodal Transformers for Video Representation Learning

Sangho Lee, Youngjae Yu, Gunhee Kim +3

The recent success of Transformers in the language domain has motivated adapting it to a multimodal setting, where a new visual model is trained in tandem with an already pretraine…

cs.CV2020

Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the Wild

Umar Iqbal, Pavlo Molchanov, Jan Kautz

One major challenge for monocular 3D human pose estimation in-the-wild is the acquisition of training data that contains unconstrained images annotated with accurate 3D poses. In t…

cs.CV2020

Weakly Supervised 3D Hand Pose Estimation via Biomechanical Constraints

Adrian Spurr, Umar Iqbal, Pavlo Molchanov +2

Estimating 3D hand pose from 2D images is a difficult, inverse problem due to the inherent scale and depth ambiguities. Current state-of-the-art methods train fully supervised deep…