Yeji Song
YOU?
Author Swipe
View article: Differential privacy in statistical queries for synthetic trajectories generated by generative adversarial networks
Differential privacy in statistical queries for synthetic trajectories generated by generative adversarial networks Open
View article: Harmonizing Visual and Textual Embeddings for Zero-Shot Text-to-Image Customization
Harmonizing Visual and Textual Embeddings for Zero-Shot Text-to-Image Customization Open
In a surge of text-to-image (T2I) models and their customization methods that generate new images of a user-provided subject, current works focus on alleviating the costs incurred by a lengthy per-subject optimization. These zero-shot cust…
View article: Smart Contract Vulnerability Detection Using Large Language Models and Graph Structural Analysis
Smart Contract Vulnerability Detection Using Large Language Models and Graph Structural Analysis Open
View article: Harmonizing Visual and Textual Embeddings for Zero-Shot Text-to-Image Customization
Harmonizing Visual and Textual Embeddings for Zero-Shot Text-to-Image Customization Open
In a surge of text-to-image (T2I) models and their customization methods that generate new images of a user-provided subject, current works focus on alleviating the costs incurred by a lengthy per-subject optimization. These zero-shot cust…
View article: SAVE: Protagonist Diversification with Structure Agnostic Video Editing
SAVE: Protagonist Diversification with Structure Agnostic Video Editing Open
Driven by the upsurge progress in text-to-image (T2I) generation models, text-to-video (T2V) generation has experienced a significant advance as well. Accordingly, tasks such as modifying the object or changing the style in a video have be…
View article: Towards Efficient Neural Scene Graphs by Learning Consistency Fields
Towards Efficient Neural Scene Graphs by Learning Consistency Fields Open
Neural Radiance Fields (NeRF) achieves photo-realistic image rendering from novel views, and the Neural Scene Graphs (NSG) \cite{ost2021neural} extends it to dynamic scenes (video) with multiple objects. Nevertheless, computationally heavy…
View article: MD3D: Mixture-Density-Based 3D Object Detection in Point Clouds
MD3D: Mixture-Density-Based 3D Object Detection in Point Clouds Open
The design factors of anchor boxes, such as shape, placement, and target assignment policy, greatly influence the performance and latency of the 3D object detectors. Unlike image-based 2D anchors, 3D anchors must be placed in a 3D space an…
View article: Dynamic Collective Intelligence Learning: Finding Efficient Sparse Model via Refined Gradients for Pruned Weights
Dynamic Collective Intelligence Learning: Finding Efficient Sparse Model via Refined Gradients for Pruned Weights Open
With the growth of deep neural networks (DNN), the number of DNN parameters has drastically increased. This makes DNN models hard to be deployed on resource-limited embedded systems. To alleviate this problem, dynamic pruning methods have …
View article: Part-Aware Data Augmentation for 3D Object Detection in Point Cloud
Part-Aware Data Augmentation for 3D Object Detection in Point Cloud Open
Data augmentation has greatly contributed to improving the performance in image recognition tasks, and a lot of related studies have been conducted. However, data augmentation on 3D point cloud data has not been much explored. 3D label has…