1. Learning to Generate Diverse Dance Motions with Transformer

Jiaman Li, Yihang Yin, Hang Chu, Yi Zhou, Tingwu Wang, Sanja Fidler, Hao Li

• retweets: 10, favorites: 56 (08/21/2020 08:46:56)
• links: abs | pdf
• cs.CV | cs.GR

With the ongoing pandemic, virtual concerts and live events using digitized performances of musicians are getting traction on massive multiplayer online worlds. However, well choreographed dance movements are extremely complex to animate and would involve an expensive and tedious production process. In addition to the use of complex motion capture systems, it typically requires a collaborative effort between animators, dancers, and choreographers. We introduce a complete system for dance motion synthesis, which can generate complex and highly diverse dance sequences given an input music sequence. As motion capture data is limited for the range of dance motions and styles, we introduce a massive dance motion data set that is created from YouTube videos. We also present a novel two-stream motion transformer generative model, which can generate motion sequences with high flexibility. We also introduce new evaluation metrics for the quality of synthesized dance motions, and demonstrate that our system can outperform state-of-the-art methods. Our system provides high-quality animations suitable for large crowds for virtual concerts and can also be used as reference for professional animation pipelines. Most importantly, we show that vast online videos can be effective in training dance motion models.

Learning to Generate Diverse Dance Motions with Transformer
pdf: https://t.co/c0rvdUcNgA
abs: https://t.co/XqtDaAxGSK pic.twitter.com/f70oHqAhLs

— AK (@ak92501) August 20, 2020

2. A Simple Deterministic Algorithm for Edge Connectivity

Thatchaphol Saranurak

• retweets: 1, favorites: 56 (08/21/2020 08:46:56)
• links: abs | pdf
• cs.DS

We show a deterministic algorithm for computing edge connectivity of a simple graph with $m$ edges in $m^{1+o(1)}$ time. Although the fastest deterministic algorithm by Henzinger, Rao, and Wang [SODA’17] has a faster running time of $O(m\log^{2}m\log\log m)$, we believe that our algorithm is conceptually simpler. The key tool for this simplication is the expander decomposition. We exploit it in a very straightforward way compared to how it has been previously used in the literature.

Computing min cuts in 2 pageshttps://t.co/nPF3kBgiUn

— Thatchaphol (@eig) August 20, 2020

3. Popularity Bias in Recommendation: A Multi-stakeholder Perspective

Himan Abdollahpouri

• retweets: 9, favorites: 42 (08/21/2020 08:46:56)
• links: abs | pdf
• cs.IR

Traditionally, especially in academic research in recommender systems, the focus has been solely on the satisfaction of the end-user. While user satisfaction has, indeed, been associated with the success of the business, it is not the only factor. In many recommendation domains, there are other stakeholders whose needs should be taken into account in the recommendation generation and evaluation. In this dissertation, I describe the notion of multi-stakeholder recommendation. In particular, I study one of the most important challenges in recommendation research, popularity bias, from a multi-stakeholder perspective since, as I show later in this dissertation, it impacts different stakeholders in a recommender system. Popularity bias is a well-known phenomenon in recommender systems where popular items are recommended even more frequently than their popularity would warrant, amplifying long-tail effects already present in many recommendation domains. Prior research has examined various approaches for mitigating popularity bias and enhancing the recommendation of long-tail items overall. The effectiveness of these approaches, however, has not been assessed in multi-stakeholder environments. In this dissertation, I study the impact of popularity bias in recommender systems from a multi-stakeholder perspective. In addition, I propose several algorithms each approaching the popularity bias mitigation from a different angle and compare their performances using several metrics with some other state-of-the-art approaches in the literature. I show that, often, the standard evaluation measures of popularity bias mitigation in the literature do not reflect the real picture of an algorithm’s performance when it is evaluated from a multi-stakeholder point of view.

My PhD dissertation is now online.

“Popularity Bias in Recommendation: A Multi-stakeholder Perspective”https://t.co/bbCmzkju39#recsys

— Himan Abdollahpouri (@HAbdollahpouri) August 20, 2020