[SIGGRAPH 2021] Learning Skeletal Articulations with Neural Blend Shapes

We develop a neural technique for articulating 3D characters using enveloping with a pre-defined skeletal structure, which is essential for animating a character with motion capture (mocap) data.

CFCS Quantum Day Agenda

CFCS Quantum Day organized by Center on Frontiers of Computing Studies (CFCS), Peking University will be held virtually on May 12th, 2021.

[CVPR 2021] Forecasting Irreversible Disease via Progression Learning

In this paper, we provide an answer with a novel framework, namely \textbf{D}isease \textbf{F}orecast via \textbf{P}rogression \textbf{L}earning (\textbf{DFPL}), which exploits the irreversibility prior (i.e., cannot be reversed once diagnosed).

[CVPR 2021] Causal Hidden Markov Model for Time Series Disease Forecasting

We propose a causal hidden Markov model to achieve robust prediction of irreversible disease at an early stage, which is safety-critical and vital for medical treatment in early stages.

[CVPR 2021] Context Modeling in 3D Human Pose Estimation: A Unified Perspective

We propose ContextPose based on attention mechanism that allows enforcing soft limb length constraints in a deep network. The approach effectively reduces the chance of getting absurd 3D pose estimates with incorrect limb lengths and achieves state-of-the-art results on two benchmark datasets. More importantly, the introduction of limb length constraints into deep networks enables the approach to achieve much better generalization performance.

[CVPR 2021 Oral] Robust Neural Routing Through Space Partitions for Camera Relocalization in Dynamic Indoor Environments

Our proposed algorithm is evaluated on the RIO-10 benchmark developed for camera relocalization in dynamic indoor environment. It achieves robust neural routing through space partitions and outperforms the state-of-the-art approaches by around 30\% on camera pose accuracy, while running comparably fast for evaluation.

[Call for Speakers] The 7th CFCS Youth Forum on Frontiers of Computing

The 7th CFCS Youth Forum on Frontiers of Computing will take place on April 17-18th, 2021. This forum invites young scholars and rising stars in all computer science fields to gather at Peking University to exchange scientific discoveries and new technologies, to learn about the center and academic career at PKU, and to interact with the PKU Turing Class students. Due to the COVID-19 pandemic, this event will be held online.

[Repost] Turing Award Winner: Planning for 100 Years – Education in China

Last month, the Turing Award winner John Hopcroft, a visiting professor at Peking University and the Director of PKU Center on Frontiers of Computing Studies, made a keynote speech on The Role of Improving Education in China's Economic Growth at the 2020 Computer Education Conference of China.

[SODA 2021] Efficient Linear and Affine Codes for Correcting Insertions/Deletions

[SODA 2021] Efficient Document Exchange and Error Correcting Codes with Asymmetric Information

[AAAI 2021] The Smoothed Complexity of Computing Kemeny and Slater Rankings

In this paper, we develop the first smoothed complexity results for winner determination in voting.

[TOG 2020] MotioNet: 3D Human Motion Reconstruction from Monocular Video with Skeleton Consistency

We introduce MotioNet, a deep neural network that directly reconstructs the motion of a 3D human skeleton from monocular video.

The 16th Conference on Web and Internet Economics is Successfully Held Online

WINE 2020 focuses on the latest development and cutting-edge issues of internet economics and related disciplines, covering the topics of mechanism design, game theory, auctions, pricing, social choice theory, and etc.

[Distinguished Lecture Series] Professor Leif Kobbelt: Surface maps and layouts

On December 11th, 2020, Professor Leif Kobbelt from RWTH Aachen University was invited to deliver an online lecture titled " Surface maps and layouts" at No. 5 Courtyard of Jingyuan, organized by CFCS, Peking University.

[NeurIPS 2020] Learning Multi-Agent Coordination for Enhancing Target Coverage in Directional Sensor Networks

We propose a Hierarchical Target-oriented Multi-Agent Coordination (HiT-MAC), which decomposes the target coverage problem into two-level tasks: targets assignment by a coordinator and tracking assigned targets by executors.

The 3rd Mini Research Symposium of CFCS and Turing Class is Held

On December 5th, 2020, the 3rd Mini Research Symposium of CFCS and Turing Class was held at Peking University. 23 students from CFCS and Turing Class signed up to present their latest research works and to give tutorials introducing their research fields.

[Distinguished Lecture Series] Professor Alan Yuille: Adversarial Examiners and Generative Models

On November 24th, 2020, Professor Alan Yuille from Johns Hopkins University was invited to deliver an online lecture titled " Adversarial Examiners and Generative Models " at No. 5 Courtyard of Jingyuan, organized by CFCS, Peking University.

[NeurIPS 2020] Learning Utilities and Equilibria in Non-Truthful Auctions

We give almost matching(up to polylog factors) lower bound on the sample complexity for learning utilities.

PKU Student Supercomputing Team Won the Silver Medal in SC20 Student Cluster Competition

In the early morning of November 20th, the results of Supercomputing Conference 2020 (SC20) Student Cluster Competition finals were announced. The team formed by students from the School of EECS, Peking University, won the silver medal. It is worth mentioning that 5 out of the 6 members in the team come from the Turing Class. Congratulations!

[NeurIPS 2020] Explainable Voting

We discuss the significance of our results for AI and machine learning,including their potential to bolster an emerging paradigm of automated decisionmaking called virtual democracy.