Hello, I'm Yeji Song

I am a Ph.D student at Seoul National University, under the supervision of Prof. Nojun Kwak.

My primary focus is on video & image generation, aiming to push the boundaries of their applications in real-world scenarios. Specifically, developing generative models that provide more diverse experiences to users is my central goal. My research interests also include a broader computer vision area, with experience spanning diffusion, video rendering, segmentation, and 3D object detection.


Publications

SAVE: Protagonist Diversification with Structure Agnostic Video Editing
Hover Here!

SAVE: Protagonist Diversification with Structure Agnostic Video Editing

ECCV, 2024 NEW!

We adopt motion personalization in video editing tasks, isolating the motion from a single source video and subsequently modifying the protagonist accordingly.

Harmonizing Visual and Textual Embeddings for Zero-Shot Text-to-Image Customization

Harmonizing Visual and Textual Embeddings for Zero-Shot Text-to-Image Customization

arXiv, 2024

There is a conflict among contextual embeddings in zero-shot T2I customization when varying the subject's pose. We resolve it by orthogonalization and attention swap.

Exploring Causal Mechanisms for Machine Text Detection Methods

Exploring Causal Mechanisms for Machine Text Detection Methods

NAACL Workshop, 2024

With the increasing importance of discriminating machine-text from human text, we show the existence of backdoor path that confounds the relationships between text and its detection score.

Finding Efficient Pruned Network via Refined Gradients for Pruned Weights

Finding Efficient Pruned Network via Refined Gradients for Pruned Weights

ACM MM, 2023

We advance dynamic pruning by employing refined gradients to update the pruned weights, enhancing both training stability and the model performance.

Towards Efficient Neural Scene Graphs by Learning Consistency Fields
Hover Here!

Towards Efficient Neural Scene Graphs by Learning Consistency Fields

BMVC, 2022

In video scene rendering, we reformulate neural radiance fields to additionally consider consistency fields, enabling more efficient and controllable scene manipulation.

Md3d: Mixture-density-based 3d object detection in point clouds

Md3d: Mixture-density-based 3d object detection in point clouds

IEEE Access, 2022

We utilize the Gaussian Mixture Model (GMM) in the 3D object detection task to predict the distribution of 3D bounding boxes, eliminating the need for laborious, hand-crafted anchor design.

Part-aware data augmentation for 3d object detection in point cloud

Part-aware data augmentation for 3d object detection in point cloud

Jaeseok Choi, Yeji Song, Nojun Kwak
IROS, 2021

We delve into data augmentation in 3D object detection, leveraging sophisticated and rich structural information present in 3D labels.