検索

Lijin Yang

Matching Compound Prototypes for Few-Shot Action Recognition
DeCo : Decomposition and Reconstruction for Compositional Temporal Grounding via Coarse-to-Fine Contrastive Ranking
Weakly Supervised Temporal Sentence Grounding With Uncertainty-Guided Self-Training
Compound Prototype Matching for Few-shot Action Recognition
Interact before Align: Leveraging Cross-Modal Knowledge for Domain Adaptive Action Recognition
Leveraging Human Selective Attention for Medical Image Analysis with Limited Training Data
Stacked Temporal Attention: Improving First-person Action Recognition by Emphasizing Discriminative Clips
EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2021: Team M3EM Technical Report

Published with Hugo Blox Builder — the free, open source website builder that empowers creators.