Yuexian Zou

16

Papers

80

Total Citations

Papers (16)

Image Conductor: Precision Control for Interactive Video Synthesis

Exploiting Auxiliary Caption for Video Grounding

Retrieval is Accurate Generation

Embracing Language Inclusivity and Diversity in CLIP through Continual Language Learning

CoLA: Weakly-Supervised Temporal Action Localization With Snippet Contrastive Learning

Exploring and Distilling Posterior and Prior Knowledge for Radiology Report Generation

Unsupervised Pre-Training for Temporal Action Localization Tasks

Iterative Proposal Refinement for Weakly-Supervised Video Grounding

Unify, Align and Refine: Multi-Level Semantic Alignment for Radiology Report Generation

G2L: Semantically Aligned and Uniform Video Grounding via Geodesic and Game Theory

LocVTP: Video-Text Pre-training for Temporal Localization

VASparse: Towards Efficient Visual Hallucination Mitigation via Visual-Aware Token Sparsification

Towards Explainable Joint Models via Information Theory for Multiple Intent Detection and Slot Filling

Aligner$^2$: Enhancing Joint Multiple Intent Detection and Slot Filling via Adjustive and Forced Cross-Task Alignment

Towards Multi-Intent Spoken Language Understanding via Hierarchical Attention and Optimal Transport

Prophet Attention: Predicting Attention with Future Attention