Search Results for author: Mengtian Li

Found 10 papers, 4 papers with code

Implicit Neural Deformation for Multi-View Face Reconstruction

no code implementations5 Dec 2021 Moran Li, Haibin Huang, Yi Zheng, Mengtian Li, Nong Sang, Chongyang Ma

In this work, we present a new method for 3D face reconstruction from multi-view RGB images.

3D Face Reconstruction

Neighborhood-Aware Neural Architecture Search

no code implementations13 May 2021 Xiaofang Wang, Shengcao Cao, Mengtian Li, Kris M. Kitani

To facilitate the application to gradient-based algorithms, we also propose a differentiable representation for the neighborhood of architectures.

Neural Architecture Search

Towards Streaming Perception

1 code implementation ECCV 2020 Mengtian Li, Yu-Xiong Wang, Deva Ramanan

While past work has studied the algorithmic trade-off between latency and accuracy, there has not been a clear metric to compare different methods along the Pareto optimal latency-accuracy curve.

Frame Instance Segmentation +4

Budgeted Training: Rethinking Deep Neural Network Training Under Resource Constraints

no code implementations ICLR 2020 Mengtian Li, Ersin Yumer, Deva Ramanan

We also revisit existing approaches for fast convergence and show that budget-aware learning schedules readily outperform such approaches under (the practical but under-explored) budgeted training setting.

General Classification Image Classification +5

Photo-Sketching: Inferring Contour Drawings from Images

2 code implementations2 Jan 2019 Mengtian Li, Zhe Lin, Radomir Mech, Ersin Yumer, Deva Ramanan

Edges, boundaries and contours are important subjects of study in both computer graphics and computer vision.

Boundary Detection BSDS500

Brute-Force Facial Landmark Analysis With A 140,000-Way Classifier

no code implementations6 Feb 2018 Mengtian Li, Laszlo Jeni, Deva Ramanan

While most prior work treats this as a regression problem, we instead formulate it as a discrete $K$-way classification task, where a classifier is trained to return one of $K$ discrete alignments.

General Classification

Guaranteed Parameter Estimation for Discrete Energy Minimization

no code implementations11 Jan 2017 Mengtian Li, Daniel Huber

In this work, we propose a method to overcome this limitation through exploiting the properties of the joint problem of training time inference and learning.

Scene Parsing

Complexity of Discrete Energy Minimization Problems

no code implementations29 Jul 2016 Mengtian Li, Alexander Shekhovtsov, Daniel Huber

Specifically, we show that general energy minimization, even in the 2-label pairwise case, and planar energy minimization with three or more labels are exp-APX-complete.

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