activity
20192022
most citedNeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation

14 citations · 35 across the 13 of their papers we have counts for

collaborators

16 papers

cs.CV2022

Robust Category-Level 6D Pose Estimation with Coarse-to-Fine Rendering of Neural Features

Wufei Ma, Angtian Wang, Alan Yuille +1

We consider the problem of category-level 6D pose estimation from a single RGB image. Our approach represents an object category as a cuboid mesh and learns a generative model of t…

cs.CV20223 cited

SwapMix: Diagnosing and Regularizing the Over-Reliance on Visual Context in Visual Question Answering

Vipul Gupta, Zhuowan Li, Adam Kortylewski +3

While Visual Question Answering (VQA) has progressed rapidly, previous works raise concerns about robustness of current VQA models. In this work, we study the robustness of VQA mod…

cs.CV20213 cited

Neural View Synthesis and Matching for Semi-Supervised Few-Shot Learning of 3D Pose

Angtian Wang, Shenxiao Mei, Alan Yuille +1

We study the problem of learning to estimate the 3D object pose from a few labelled examples and a collection of unlabelled data. Our main contribution is a learning framework, neu…

cs.CV20212 cited

A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representation

Jiteng Mu, Weichao Qiu, Adam Kortylewski +3

Recent work has made significant progress on using implicit functions, as a continuous representation for 3D rigid object shape reconstruction. However, much less effort has been d…

cs.LG20212 cited

Understanding Catastrophic Forgetting and Remembering in Continual Learning with Optimal Relevance Mapping

Prakhar Kaushik, Alex Gain, Adam Kortylewski +1

Catastrophic forgetting in neural networks is a significant problem for continual learning. A majority of the current methods replay previous data during training, which violates t…

cs.CV202114 cited

NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation

Angtian Wang, Adam Kortylewski, Alan Yuille

3D pose estimation is a challenging but important task in computer vision. In this work, we show that standard deep learning approaches to 3D pose estimation are not robust when ob…