[ACM MM'24 Oral] RainMamba: Enhanced Locality Learning with State Space Models for Video Deraining

[ACM MM 2024] Improving Composed Image Retrieval via Contrastive Learning with Scaling Positives and Negatives

Noise of Web (NoW) is a challenging noisy correspondence learning (NCL) benchmark containing 100K image-text pairs for robust image-text matching/retrieval models.

[ACM MM 2024] Dual-Hybrid Attention Network for Specular Highlight Removal

[ACMMM'24] MoBA: Mixture of Bi-directional Adapter for Multi-modal Sarcasm Detection

Official Code of ACM MM'24 Paper "Unsupervised Multi-view Pedestrian Detection"