WonJun Moon

12

Papers

70

Total Citations

1

Affiliations

Affiliations

Sungkyunkwan univeresity

Papers (12)

VLCounter: Text-Aware Visual Representation for Zero-Shot Object Counting

Mitigating Background Shift in Class-Incremental Semantic Segmentation

Ambiguity-Restrained Text-Video Representation Learning for Partially Relevant Video Retrieval

Temporal Alignment-Free Video Matching for Few-shot Action Recognition

Prototypes are Balanced Units for Efficient and Effective Partially Relevant Video Retrieval

Selective Contrastive Learning for Weakly Supervised Affordance Grounding

Bridging the Semantic Granularity Gap Between Text and Frame Representations for Partially Relevant Video Retrieval

Task Discrepancy Maximization for Fine-Grained Few-Shot Classification

Query-Dependent Video Representation for Moment Retrieval and Highlight Detection

Leveraging Hidden Positives for Unsupervised Semantic Segmentation

Tailoring Self-Supervision for Supervised Learning

Difficulty-Aware Simulator for Open Set Recognition