← Back to papers
2025 ICCV ICCV 2025

SUV: Suppressing Undesired Video Content via Semantic Modulation Based on Text Embeddings

Authors

Xiang Lv , Mingwen Shao , Lingzhuang Meng , Chang Liu , Yecong Wan , Xinyuan Chen

Related papers

MA-CIR: A Multimodal Arithmetic Benchmark for Composed Image Retrieval 2025
SimMLM: A Simple Framework for Multi-modal Learning with Missing Modality 2025
MonSTeR: a Unified Model for Motion, Scene, Text Retrieval 2025
ASGS: Single-Domain Generalizable Open-Set Object Detection via Adaptive Subgraph Searching 2025
Robust Dataset Condensation using Supervised Contrastive Learning 2025