Ziwei Liu

Dynamic Graph CNN for Learning on Point Clouds

2019 · ACM Transactions on Graphics

Point clouds provide a flexible geometric representation suitable for countless applications in computer graphics; they also comprise the raw output of most 3D data acquisition devices. While hand-designed features on point clouds have long been …

Unsupervised Object-Level Representation Learning from Scene Images

2021 · arXiv (Cornell University)

Contrastive self-supervised learning has largely narrowed the gap to supervised pre-training on ImageNet. However, its success highly relies on the object-centric priors of ImageNet, i.e., different augmented views of the same image correspond to the …

Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistency

2021 · 2021 IEEE/CVF International Conference on Computer Vision (ICCV)

Deep learning-based 3D object detection has achieved unprecedented success with the advent of large-scale autonomous driving datasets. However, drastic performance degradation remains a critical challenge for cross-domain deployment. In addition, existing 3D domain adaptive detection …

Balanced MSE for Imbalanced Visual Regression

2022 · arXiv (Cornell University)

Data imbalance exists ubiquitously in real-world visual regressions, e.g., age estimation and pose estimation, hurting the model's generalizability and fairness. Thus, imbalanced regression gains increasing research attention recently. Compared to imbalanced classification, imbalanced regression focuses …

Detecting and Recovering Sequential DeepFake Manipulation

2022 · arXiv (Cornell University)

Since photorealistic faces can be readily generated by facial manipulation technologies nowadays, potential malicious abuse of these technologies has drawn great concerns. Numerous deepfake detection methods are thus proposed. However, existing methods only focus on …

Duolando: Follower GPT with Off-Policy Reinforcement Learning for Dance Accompaniment

2024 · arXiv (Cornell University)

We introduce a novel task within the field of 3D dance generation, termed dance accompaniment, which necessitates the generation of responsive movements from a dance partner, the "follower", synchronized with the lead dancer's movements and …