Search Results for author:
Found 22 papers, 8 papers with code
Continuous-Time Human Motion Field from Events
In this work, we predict a continuous-time human motion field directly from events by leveraging a recurrent feed-forward neural network to predict human motion in the latent space of possible human motions.
EqNIO: Subequivariant Neural Inertial Odometry
We then map the IMU data into this frame, thereby achieving an invariant canonicalization that can be directly used with off-the-shelf inertial odometry networks.
Motion-prior Contrast Maximization for Dense Continuous-Time Motion Estimation
In optical flow estimation, our method elevates a simple UNet to achieve state-of-the-art performance among self-supervised methods on the DSEC optical flow benchmark.
TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos
We propose TRAM, a two-stage method to reconstruct a human's global trajectory and motion from in-the-wild videos.
Ranked #1 on
3D Human Pose Estimation
on EMDB
Track Everything Everywhere Fast and Robustly
We propose a novel test-time optimization approach for efficiently and robustly tracking any pixel at any time in a video.
Un-EvMoSeg: Unsupervised Event-based Independent Motion Segmentation
Event cameras are a novel type of biologically inspired vision sensor known for their high temporal resolution, high dynamic range, and low power consumption.
Event-based Continuous Color Video Decompression from Single Frames
We present ContinuityCam, a novel approach to generate a continuous video from a single static RGB image and an event camera stream.
EV-Catcher: High-Speed Object Catching Using Low-latency Event-based Neural Networks
Event-based sensors have recently drawn increasing interest in robotic perception due to their lower latency, higher dynamic range, and lower bandwidth requirements compared to standard CMOS-based imagers.
EvAC3D: From Event-based Apparent Contours to 3D Models via Continuous Visual Hulls
3D reconstruction from multiple views is a successful computer vision field with multiple deployments in applications.
Improving Load Forecast in Energy Markets During COVID-19
The abrupt outbreak of the COVID-19 pandemic was the most significant event in 2020, which had profound and lasting impacts across the world.
Cross-lingual Text Classification with Heterogeneous Graph Neural Network
Cross-lingual text classification aims at training a classifier on the source language and transferring the knowledge to target languages, which is very useful for low-resource languages.
Geodesic-HOF: 3D Reconstruction Without Cutting Corners
To address this issue, we propose learning an image-conditioned mapping function from a canonical sampling domain to a high dimensional space where the Euclidean distance is equal to the geodesic distance on the object.
Surface HOF: Surface Reconstruction from a Single Image Using Higher Order Function Networks
Our approach is to learn a Higher Order Function (HOF) which takes an image of an object as input and generates a mapping function.
EventGAN: Leveraging Large Scale Image Datasets for Event Cameras
Event cameras provide a number of benefits over traditional cameras, such as the ability to track incredibly fast motions, high dynamic range, and low power consumption.
Motion Equivariance OF Event-based Camera Data with the Temporal Normalization Transform
In this work, we focus on using convolution neural networks (CNN) to perform object recognition on the event data.
Modeling question asking using neural program generation
People ask questions that are far richer, more informative, and more creative than current AI systems.
An Atomistic Machine Learning Package for Surface Science and Catalysis
We present work flows and a software module for machine learning model building in surface science and heterogeneous catalysis.
Motion Equivariant Networks for Event Cameras with the Temporal Normalization Transform
In this work, we propose a novel transformation for events from an event camera that is equivariant to optical flow under convolutions in the 3-D spatiotemporal domain.
Robustness Meets Deep Learning: An End-to-End Hybrid Pipeline for Unsupervised Learning of Egomotion
In this work, we propose a method that combines unsupervised deep learning predictions for optical flow and monocular disparity with a model based optimization procedure for instantaneous camera pose.
FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation
The relation of each sentence is first recognized by distant supervision methods, and then filtered by crowdworkers.
Distributional Inclusion Vector Embedding for Unsupervised Hypernymy Detection
Modeling hypernymy, such as poodle is-a dog, is an important generalization aid to many NLP tasks, such as entailment, coreference, relation extraction, and question answering.
Topic Sensitive Neural Headline Generation
Neural models have recently been used in text summarization including headline generation.
