Picture for Joonseok Lee

Joonseok Lee

Diff4Steer: Steerable Diffusion Prior for Generative Music Retrieval with Semantic Guidance

Add code
Dec 06, 2024
Viaarxiv icon

Finding NeMo: Negative-mined Mosaic Augmentation for Referring Image Segmentation

Add code
Nov 03, 2024
Viaarxiv icon

Scalable Frame Sampling for Video Classification: A Semi-Optimal Policy Approach with Reduced Search Space

Add code
Sep 09, 2024
Viaarxiv icon

Isometric Representation Learning for Disentangled Latent Space of Diffusion Models

Add code
Jul 16, 2024
Viaarxiv icon

General Item Representation Learning for Cold-start Content Recommendations

Add code
Apr 22, 2024
Viaarxiv icon

Modality-Aware Representation Learning for Zero-shot Sketch-based Image Retrieval

Add code
Jan 10, 2024
Viaarxiv icon

Activity Grammars for Temporal Action Segmentation

Add code
Dec 07, 2023
Viaarxiv icon

Towards Robust and Smooth 3D Multi-Person Pose Estimation from Monocular Videos in the Wild

Add code
Sep 15, 2023
Viaarxiv icon

VisAlign: Dataset for Measuring the Degree of Alignment between AI and Humans in Visual Perception

Add code
Aug 03, 2023
Viaarxiv icon

V2Meow: Meowing to the Visual Beat via Music Generation

Add code
May 11, 2023
Figure 1 for V2Meow: Meowing to the Visual Beat via Music Generation
Figure 2 for V2Meow: Meowing to the Visual Beat via Music Generation
Figure 3 for V2Meow: Meowing to the Visual Beat via Music Generation
Figure 4 for V2Meow: Meowing to the Visual Beat via Music Generation
Viaarxiv icon