Search Results for author: Shaofei Wang

Found 20 papers, 4 papers with code

Self-Supervised Image Representation Learning: Transcending Masking with Paired Image Overlay

no code implementations23 Jan 2023 Yinheng Li, Han Ding, Shaofei Wang

Self-supervised learning has become a popular approach in recent years for its ability to learn meaningful representations without the need for data annotation.

Contrastive Learning Image Augmentation +2

ARAH: Animatable Volume Rendering of Articulated Human SDFs

no code implementations18 Oct 2022 Shaofei Wang, Katja Schwarz, Andreas Geiger, Siyu Tang

We demonstrate that our proposed pipeline can generate clothed avatars with high-quality pose-dependent geometry and appearance from a sparse set of multi-view RGB videos.

Compositional Human-Scene Interaction Synthesis with Semantic Control

1 code implementation26 Jul 2022 Kaifeng Zhao, Shaofei Wang, Yan Zhang, Thabo Beeler, Siyu Tang

Furthermore, inspired by the compositional nature of interactions that humans can simultaneously interact with multiple objects, we define interaction semantics as the composition of varying numbers of atomic action-object pairs.

Instance Segmentation Semantic Segmentation

Investor Behavior Modeling by Analyzing Financial Advisor Notes: A Machine Learning Perspective

no code implementations12 Jul 2021 Cynthia Pagliaro, Dhagash Mehta, Han-Tai Shiao, Shaofei Wang, Luwei Xiong

With the help of natural language processing (NLP) we analyze an unstructured (textual) dataset of financial advisors' summary notes, taken after every investor conversation, to gain first ever insights into advisor-investor interactions.

BIG-bench Machine Learning Decision Making

MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images

1 code implementation NeurIPS 2021 Shaofei Wang, Marko Mihajlovic, Qianli Ma, Andreas Geiger, Siyu Tang

In contrast, we propose an approach that can quickly generate realistic clothed human avatars, represented as controllable neural SDFs, given only monocular depth images.


Locally Aware Piecewise Transformation Fields for 3D Human Mesh Registration

no code implementations CVPR 2021 Shaofei Wang, Andreas Geiger, Siyu Tang

We combine PTF with multi-class occupancy networks, obtaining a novel learning-based framework that learns to simultaneously predict shape and per-point correspondences between the posed space and the canonical space for clothed human.

Surface Reconstruction Translation

Extend the FFmpeg Framework to Analyze Media Content

no code implementations5 Mar 2021 Xintian Wu, Pengfei Qu, Shaofei Wang, Lin Xie, Jie Dong

This paper introduces a new set of video analytics plugins developed for the FFmpeg framework.

End-to-end Training of CNN-CRF via Differentiable Dual-Decomposition

1 code implementation6 Dec 2019 Shaofei Wang, Vishnu Lokhande, Maneesh Singh, Konrad Kording, Julian Yarkony

These algorithms can efficiently and exactly solve sub-problems and directly optimize a convex upper bound of the real problem, providing optimality certificates on the way.

Image Segmentation Semantic Segmentation

Movement science needs different pose tracking algorithms

no code implementations24 Jul 2019 Nidhi Seethapathi, Shaofei Wang, Rachit Saluja, Gunnar Blohm, Konrad P. Kording

Over the last decade, computer science has made progress towards extracting body pose from single camera photographs or videos.

Pose Tracking

Accelerating Dynamic Programs via Nested Benders Decomposition with Application to Multi-Person Pose Estimation

no code implementations ECCV 2018 Shaofei Wang, Alexander Ihler, Konrad Kording, Julian Yarkony

We present a novel approach to solve dynamic programs (DP), which are frequent in computer vision, on tree-structured graphs with exponential node state space.

Multi-Person Pose Estimation

Accelerating Message Passing for MAP with Benders Decomposition

no code implementations13 May 2018 Julian Yarkony, Shaofei Wang

To circumvent the difficulty of enumerating the vector product of state spaces of hyper-variables we introduce a novel Benders decomposition approach.

Efficient Multi-Person Pose Estimation with Provable Guarantees

no code implementations21 Nov 2017 Shaofei Wang, Konrad Paul Kording, Julian Yarkony

We test our approach on the MPII-Multiperson dataset, showing that our approach obtains comparable results with the state-of-the-art algorithm for joint node labeling and grouping problems, and that NBD achieves considerable speed-ups relative to a naive dynamic programming approach.

Multi-Person Pose Estimation

Efficient Column Generation for Cell Detection and Segmentation

no code implementations21 Sep 2017 Chong Zhang, Shaofei Wang, Miguel A. Gonzalez-Ballester, Julian Yarkony

To solve this integer program, we propose a column generation formulation where the pricing program is solved via exact optimization of very small scale integer programs.

Instance Segmentation Semantic Segmentation

Multi-Person Pose Estimation via Column Generation

no code implementations18 Sep 2017 Shaofei Wang, Chong Zhang, Miguel A. Gonzalez-Ballester, Alexander Ihler, Julian Yarkony

We give a novel integer program formulation of the multi-person pose estimation problem, in which variables correspond to assignments of parts in the image to poses in a two-tier, hierarchical way.

Multi-Person Pose Estimation

Efficient Pose and Cell Segmentation using Column Generation

no code implementations1 Dec 2016 Shaofei Wang, Chong Zhang, Miguel A. Gonzalez-Ballester, Julian Yarkony

We study the problems of multi-person pose segmentation in natural images and instance segmentation in biological images with crowded cells.

Cell Segmentation Efficient Exploration +2

Learning Optimal Parameters for Multi-target Tracking with Contextual Interactions

no code implementations5 Oct 2016 Shaofei Wang, Charless C. Fowlkes

In this learning framework, we evaluate two different approaches to finding an optimal set of tracks under a quadratic model objective, one based on an LP relaxation and the other based on novel greedy variants of dynamic programming that handle pairwise interactions.

Association Metric Learning +1

Learning Multi-target Tracking with Quadratic Object Interactions

no code implementations5 Dec 2014 Shaofei Wang, Charless C. Fowlkes

We describe a model for multi-target tracking based on associating collections of candidate detections across frames of a video.

Structured Prediction

Cannot find the paper you are looking for? You can Submit a new open access paper.