Jinmeng Wu — accepted AI-conference papers

2025

Improving Open-vocabulary Video Visual Relation Detection with Decomposed Prompt Learning and Relation Adjustment

Ming Pei, Yi Tan, Yanbin Hao, Hao Zhang, Jinmeng Wu, Basura Fernando +1

ICASSP 2025accepted

Open-vocabulary video visual relation detection (VidVRD) expands the scope of detecting object relations in videos to include unseen categories. It marks considerable advancement in recognizing novel relations solely by training on a base set, thus extending the frontiers of automated video understa…

Cited by 0 Source ↗Scholar ↗

2024

PointTFA: Training-Free Clustering Adaption for Large 3D Point Cloud Models

Jinmeng Wu, Chong Cao, Hao Zhang, Basura Fernando, Yanbin Hao, Hanyu Hong

IJCAI 2024poster

The success of contrastive learning models like CLIP, known for aligning 2D image-text pairs, has inspired the development of triplet alignment for Large 3D Point Cloud Models (3D-PCM). Examples like ULIP integrate images, text, and point clouds into a unified semantic space. However, despite showin…

Cited by 2 Source ↗PDF ↗code ↗Scholar ↗