Picture for Taehoon Kim

Taehoon Kim

A 0.65-pJ/bit 3.6-TB/s/mm I/O Interface with XTalk Minimizing Affine Signaling for Next-Generation HBM with High Interconnect Density

Apr 08, 2024
Viaarxiv icon

OurDB: Ouroboric Domain Bridging for Multi-Target Domain Adaptive Semantic Segmentation

Mar 18, 2024
Figure 1 for OurDB: Ouroboric Domain Bridging for Multi-Target Domain Adaptive Semantic Segmentation
Figure 2 for OurDB: Ouroboric Domain Bridging for Multi-Target Domain Adaptive Semantic Segmentation
Figure 3 for OurDB: Ouroboric Domain Bridging for Multi-Target Domain Adaptive Semantic Segmentation
Figure 4 for OurDB: Ouroboric Domain Bridging for Multi-Target Domain Adaptive Semantic Segmentation
Viaarxiv icon

D3T: Distinctive Dual-Domain Teacher Zigzagging Across RGB-Thermal Gap for Domain-Adaptive Object Detection

Add code
Mar 14, 2024
Figure 1 for D3T: Distinctive Dual-Domain Teacher Zigzagging Across RGB-Thermal Gap for Domain-Adaptive Object Detection
Viaarxiv icon

Exploiting Style Latent Flows for Generalizing Deepfake Detection Video Detection

Add code
Mar 11, 2024
Figure 1 for Exploiting Style Latent Flows for Generalizing Deepfake Detection Video Detection
Figure 2 for Exploiting Style Latent Flows for Generalizing Deepfake Detection Video Detection
Figure 3 for Exploiting Style Latent Flows for Generalizing Deepfake Detection Video Detection
Figure 4 for Exploiting Style Latent Flows for Generalizing Deepfake Detection Video Detection
Viaarxiv icon

NICE: CVPR 2023 Challenge on Zero-shot Image Captioning

Add code
Sep 11, 2023
Figure 1 for NICE: CVPR 2023 Challenge on Zero-shot Image Captioning
Figure 2 for NICE: CVPR 2023 Challenge on Zero-shot Image Captioning
Figure 3 for NICE: CVPR 2023 Challenge on Zero-shot Image Captioning
Figure 4 for NICE: CVPR 2023 Challenge on Zero-shot Image Captioning
Viaarxiv icon

RAMiT: Reciprocal Attention Mixing Transformer for Lightweight Image Restoration

Add code
May 22, 2023
Figure 1 for RAMiT: Reciprocal Attention Mixing Transformer for Lightweight Image Restoration
Figure 2 for RAMiT: Reciprocal Attention Mixing Transformer for Lightweight Image Restoration
Figure 3 for RAMiT: Reciprocal Attention Mixing Transformer for Lightweight Image Restoration
Figure 4 for RAMiT: Reciprocal Attention Mixing Transformer for Lightweight Image Restoration
Viaarxiv icon

Randomized Adversarial Style Perturbations for Domain Generalization

Apr 04, 2023
Figure 1 for Randomized Adversarial Style Perturbations for Domain Generalization
Figure 2 for Randomized Adversarial Style Perturbations for Domain Generalization
Figure 3 for Randomized Adversarial Style Perturbations for Domain Generalization
Figure 4 for Randomized Adversarial Style Perturbations for Domain Generalization
Viaarxiv icon

Cross-Class Feature Augmentation for Class Incremental Learning

Add code
Apr 04, 2023
Figure 1 for Cross-Class Feature Augmentation for Class Incremental Learning
Figure 2 for Cross-Class Feature Augmentation for Class Incremental Learning
Figure 3 for Cross-Class Feature Augmentation for Class Incremental Learning
Figure 4 for Cross-Class Feature Augmentation for Class Incremental Learning
Viaarxiv icon

Large-Scale Bidirectional Training for Zero-Shot Image Captioning

Add code
Nov 15, 2022
Figure 1 for Large-Scale Bidirectional Training for Zero-Shot Image Captioning
Figure 2 for Large-Scale Bidirectional Training for Zero-Shot Image Captioning
Figure 3 for Large-Scale Bidirectional Training for Zero-Shot Image Captioning
Figure 4 for Large-Scale Bidirectional Training for Zero-Shot Image Captioning
Viaarxiv icon

Rich CNN-Transformer Feature Aggregation Networks for Super-Resolution

Add code
Mar 16, 2022
Figure 1 for Rich CNN-Transformer Feature Aggregation Networks for Super-Resolution
Figure 2 for Rich CNN-Transformer Feature Aggregation Networks for Super-Resolution
Figure 3 for Rich CNN-Transformer Feature Aggregation Networks for Super-Resolution
Figure 4 for Rich CNN-Transformer Feature Aggregation Networks for Super-Resolution
Viaarxiv icon