PPaperPicks

Jae-Pil Heo

22 papers at tracked venues · 20 at CORE A* · active 20242025

Venues

Frequent coauthors

Papers

  1. Ambiguity-Restrained Text-Video Representation Learning for Partially Relevant Video Retrieval
  2. Auto-Encoded Supervision for Perceptual Image Super-Resolution
  3. Bridging the Semantic Granularity Gap Between Text and Frame Representations for Partially Relevant Video Retrieval
  4. Diffusion Feature Field for Text-based 3D Editing with Gaussian Splatting
  5. Fine-Tuning Visual Autoregressive Models for Subject-Driven Generation
  6. Foreground-Covering Prototype Generation and Matching for SAM-Aided Few-Shot Segmentation
  7. Mitigating Semantic Collapse in Partially Relevant Video Retrieval
  8. Prediction-Feedback DETR for Temporal Action Detection
  9. Prototypes Are Balanced Units for Efficient and Effective Partially Relevant Video Retrieval
  10. Selective Contrastive Learning for Weakly Supervised Affordance Grounding
  11. Temporal Alignment-Free Video Matching for Few-shot Action Recognition
  12. Translation of Text Embedding Via Delta Vector to Suppress Strongly Entangled Content in Text-to-Image Diffusion Models
  13. Activating Self-Attention for Multi-Scene Absolute Pose Regression
  14. Diversity-Aware Channel Pruning for StyleGAN Compression
  15. GSGAN: Adversarial Learning for Hierarchical Generation of 3D Gaussian Splats
  16. Mitigating Background Shift in Class-Incremental Semantic Segmentation
  17. Noise-Free Optimization in Early Training Steps for Image Super-resolution
  18. Progressive Proxy Anchor Propagation for Unsupervised Semantic Segmentation
  19. Style Injection in Diffusion: A Training-Free Approach for Adapting Large-Scale Diffusion Models for Style Transfer
  20. Task-Disruptive Background Suppression for Few-Shot Segmentation
  21. Towards Squeezing-Averse Virtual Try-On via Sequential Deformation
  22. VLCounter: Text-Aware Visual Representation for Zero-Shot Object Counting