Search Results for author:
Found 12 papers, 4 papers with code
AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation
Expressive human pose and shape estimation (a. k. a.
AGSPNet: A framework for parcel-scale crop fine-grained semantic change detection from UAV high-resolution imagery with agricultural geographic scene constraints
Real-time and accurate information on fine-grained changes in crop cultivation is of great significance for crop growth monitoring, yield prediction and agricultural structure adjustment.
Evaluating the potential impacts of grey seal predation and fishery bycatch/discards on cod productivity on the Western Scotian Shelf and in the Bay of Fundy
We developed a statistical catch-at-age model for 4X5Y cod that accounted for both grey seal predation and estimated bycatch/discards to evaluate the degree to which either of these factors may influence cod mortality.
Learning Dense UV Completion for Human Mesh Recovery
Our method utilizes a dense correspondence map to separate visible human features and completes human features on a structured UV map dense human with an attention-based feature completion module.
Integrating Listwise Ranking into Pairwise-based Image-Text Retrieval
Given a query caption, the goal is to rank candidate images by relevance, from large to small.
Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstruction
As it is hard to calibrate single-view RGB images in the wild, existing 3D human mesh reconstruction (3DHMR) methods either use a constant large focal length or estimate one based on the background environment context, which can not tackle the problem of the torso, limb, hand or face distortion caused by perspective camera projection when the camera is close to the human body.
Ranked #5 on
3D Human Pose Estimation
on 3DPW
AudioEar: Single-View Ear Reconstruction for Personalized Spatial Audio
To this end, we propose to achieve personalized spatial audio by reconstructing 3D human ears with single-view images.
Representation-Agnostic Shape Fields
In this study, we present Representation-Agnostic Shape Fields (RASF), a generalizable and computation-efficient shape embedding module for 3D deep learning.
Learning Multiscale Correlations for Human Motion Prediction
We evaluate our approach on two standard benchmark datasets for human motion prediction: Human3. 6M and CMU motion capture dataset.
Distributionally Robust Joint Chance-Constrained Programming with Wasserstein Metric
Specifically, when the constraint function is affine in both the decision variable and the uncertainty, then the resulting approximation model is equivalent to a tractable mixed-integer convex reformulation for joint binary DRCCP.
Optimization and Control
From Aircraft Tracking Data to Network Delay Model: A Data-Driven Approach Considering En-Route Congestion
In this study, we propose a new flight delay model, Multi-layer Air Traffic Network Delay (MATND) model, to capture the impact of en-route congestion on flight delays over an air traffic network.
An Incremental Clustering Method for Anomaly Detection in Flight Data
It trains an initial GMM model based on historical offlline data.
