Search Results for author:
Found 13 papers, 2 papers with code
Fast Algorithms for Directed Graph Partitioning Using Flows and Reweighted Eigenvalues
We consider a new semidefinite programming relaxation for directed edge expansion, which is obtained by adding triangle inequalities to the reweighted eigenvalue formulation.
Experimental Design for Any $p$-Norm
We prove that a randomized local search approach provides a unified algorithm to solve this problem for all $p$.
MotionDeltaCNN: Sparse CNN Inference of Frame Differences in Moving Camera Videos with Spherical Buffers and Padded Convolutions
Moving cameras add new challenges in how to fuse newly unveiled image regions with already processed regions efficiently to minimize the update rate - without increasing memory overhead and without knowing the camera extrinsics of future frames.
Cheeger Inequalities for Directed Graphs and Hypergraphs Using Reweighted Eigenvalues
The first main result is a Cheeger inequality relating the vertex expansion $\vec{\psi}(G)$ of a directed graph $G$ to the vertex-capacitated maximum reweighted second eigenvalue $\vec{\lambda}_2^{v*}$: \[ \vec{\lambda}_2^{v*} \lesssim \vec{\psi}(G) \lesssim \sqrt{\vec{\lambda}_2^{v*} \cdot \log (\Delta/\vec{\lambda}_2^{v*})}.
UmeTrack: Unified multi-view end-to-end hand tracking for VR
In this paper, we present a unified end-to-end differentiable framework for multi-view, multi-frame hand tracking that directly predicts 3D hand pose in world space.
MotionDeltaCNN: Sparse CNN Inference of Frame Differences in Moving Camera Videos
Moving cameras add new challenges in how to fuse newly unveiled image regions with already processed regions efficiently to minimize the update rate - without increasing memory overhead and without knowing the camera extrinsics of future frames.
Neural Correspondence Field for Object Pose Estimation
Unlike classical correspondence-based methods which predict 3D object coordinates at pixels of the input image, the proposed method predicts 3D object coordinates at 3D query points sampled in the camera frustum.
Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities
Assembly101 is a new procedural activity dataset featuring 4321 videos of people assembling and disassembling 101 "take-apart" toy vehicles.
DeltaCNN: End-to-End CNN Inference of Sparse Frame Differences in Videos
With DeltaCNN, we present a sparse convolutional neural network framework that enables sparse frame-by-frame updates to accelerate video inference in practice.
EM-POSE: 3D Human Pose Estimation From Sparse Electromagnetic Trackers
To this end, we present a method to estimate SMPL parameters from 6-12 EM sensors.
UNOC: Understanding Occlusion for Embodied Presence in Virtual Reality
Tracking body and hand motions in the 3D space is essential for social and self-presence in augmented and virtual environments.
Lightweight Multi-View 3D Pose Estimation through Camera-Disentangled Representation
We present a lightweight solution to recover 3D pose from multi-view images captured with spatially calibrated cameras.
Ranked #4 on
3D Human Pose Estimation
on Total Capture
Going Deeper in Spiking Neural Networks: VGG and Residual Architectures
Over the past few years, Spiking Neural Networks (SNNs) have become popular as a possible pathway to enable low-power event-driven neuromorphic hardware.
