Yong Zheng, Kumar Neelotpal Shukla, Jasmine Xu et al.
MOPO-LSI is an open-source Multi-Objective Portfolio Optimization Library for Sustainable Investments. This document provides a user guide for MOPO-LSI version 1.0, including problem setup, workflow and the hyper-parameters in configurations.
Jiadong Liang, Bojun Xiong, Jie Tian et al.
This paper primarily investigates the task of expression-only portrait video performance editing based on a driving video, which plays a crucial role in animation and film industries. Most existing research mainly focuses on portrait animation, which aims to animate a static portrait image according to the facial motion from the driving video. As a consequence, it remains challenging for them to disentangle the facial expression from head pose rotation and thus lack the ability to edit facial expression independently. In this paper, we propose PerformRecast, a versatile expression-only video editing method which is dedicated to recast the performance in existing film and animation. The key insight of our method comes from the characteristics of 3D Morphable Face Model (3DMM), which models the face identity, facial expression and head pose of 3D face mesh with separate parameters. Therefore, we improve the keypoints transformation formula in previous methods to make it more consistent with 3DMM model, which achieves a better disentanglement and provides users with much more fine-grained control. Furthermore, to avoid the misalignment around the boundary of face in generated results, we decouple the facial and non-facial regions of input portrait images and pre-train a teacher model to provide separate supervision for them. Extensive experiments show that our method produces high-quality results which are more faithful to the driving video, outperforming existing methods in both controllability and efficiency. Our code, data and trained models are available at https://youku-aigc.github.io/PerformRecast.
Yong Zheng
Context-aware recommender systems extend traditional recommenders by adapting their suggestions to users' contextual situations. CARSKit is a Java-based open-source library specifically designed for the context-aware recommendation, where the state-of-the-art context-aware recommendation algorithms have been implemented. This report provides the basic user's guide to CARSKit, including how to prepare the data set, how to configure the experimental settings, and how to evaluate the algorithms, as well as interpreting the outputs. The instructions in this guide are applicable for CARSKit v0.3.5 and above.
Yong Zheng, David, Wang
Recommender systems (RecSys) have been well developed to assist user decision making. Traditional RecSys usually optimize a single objective (e.g., rating prediction errors or ranking quality) in the model. There is an emerging demand in multi-objective optimization recently in RecSys, especially in the area of multi-stakeholder and multi-task recommender systems. This article provides an overview of multi-objective recommendations, followed by the discussions with case studies. The document is considered as a supplementary material for our tutorial on multi-objective recommendations at ACM SIGKDD 2021.
Diego Sánchez-Moreno, Yong Zheng, María N. Moreno-García
Online streaming services have become the most popular way of listening to music. The majority of these services are endowed with recommendation mechanisms that help users to discover songs and artists that may interest them from the vast amount of music available. However, many are not reliable as they may not take into account contextual aspects or the ever-evolving user behavior. Therefore, it is necessary to develop systems that consider these aspects. In the field of music, time is one of the most important factors influencing user preferences and managing its effects, and is the motivation behind the work presented in this paper. Here, the temporal information regarding when songs are played is examined. The purpose is to model both the evolution of user preferences in the form of evolving implicit ratings and user listening behavior. In the collaborative filtering method proposed in this work, daily listening habits are captured in order to characterize users and provide them with more reliable recommendations. The results of the validation prove that this approach outperforms other methods in generating both context-aware and context-free recommendations
Yong Zheng
Recommender systems have been widely applied to assist user's decision making by providing a list of personalized item recommendations. Context-aware recommender systems (CARS) additionally take context information into considering in the recommendation process, since user's tastes on the items may vary from contexts to contexts. Several context-aware recommendation algorithms have been proposed and developed to improve the quality of recommendations. However, there are limited research which explore and discuss the capability of interpreting the contextual effects by the recommendation models. In this paper, we specifically focus on different contextual modeling approaches, reshape the structure of the models, and exploit how to utilize the existing contextual modeling to interpret the contextual effects in the recommender systems. We compare the explanations of contextual effects, as well as the recommendation performance over two-real world data sets in order to examine the quality of interpretations.
Yong Zheng
Recommender systems have been successfully applied to assist decision making by producing a list of item recommendations tailored to user preferences. Traditional recommender systems only focus on optimizing the utility of the end users who are the receiver of the recommendations. By contrast, multi-stakeholder recommendation attempts to generate recommendations that satisfy the needs of both the end users and other parties or stakeholders. This paper provides an overview and discussion about the multi-stakeholder recommendations from the perspective of practical applications, available data sets, corresponding research challenges and potential solutions.