activity
20172022
most citedGated-GAN: Adversarial Gated Networks for Multi-Collection Style Transfer

144 citations · 619 across the 42 of their papers we have counts for

collaborators

50 papers

cs.IR202226 cited

Modeling Dynamic User Preference via Dictionary Learning for Sequential Recommendation

Chao Chen, Dongsheng Li, Junchi Yan +1

Capturing the dynamics in user preference is crucial to better predict user future behaviors because user preferences often drift over time. Many existing recommendation algorithms…

cs.IR20223 cited

Learning Self-Modulating Attention in Continuous Time Space with Applications to Sequential Recommendation

Chao Chen, Haoyu Geng, Nianzu Yang +4

User interests are usually dynamic in the real world, which poses both theoretical and practical challenges for learning accurate preferences from rich behavior data. Among existin…

cs.CV20223 cited

Facial Geometric Detail Recovery via Implicit Representation

Xingyu Ren, Alexandros Lattas, Baris Gecer +4

Learning a dense 3D model with fine-scale details from a single facial image is highly challenging and ill-posed. To address this problem, many approaches fit smooth geometries thr…

cs.CV202243 cited

DFA-NeRF: Personalized Talking Head Generation via Disentangled Face Attributes Neural Rendering

Shunyu Yao, RuiZhe Zhong, Yichao Yan +2

While recent advances in deep neural networks have made it possible to render high-quality images, generating photo-realistic and personalized talking head remains challenging. Wit…

cs.CV2021

Out-of-Domain Human Mesh Reconstruction via Dynamic Bilevel Online Adaptation

Shanyan Guan, Jingwei Xu, Michelle Z. He +3

We consider a new problem of adapting a human mesh reconstruction model to out-of-domain streaming videos, where performance of existing SMPL-based models are significantly affecte…

cs.CV20211 cited

Efficient Person Search: An Anchor-Free Approach

Yichao Yan, Jinpeng Li, Jie Qin +2

Person search aims to simultaneously localize and identify a query person from realistic, uncropped images. To achieve this goal, state-of-the-art models typically add a re-id bran…