12 citations · 17 across the 7 of their papers we have counts for
4 papers · 2 filters
Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training
Yipeng Gao, Zeyu Wang, Wei-Shi Zheng +2
Contrastive learning has emerged as a promising paradigm for 3D open-world understanding, i.e., aligning point cloud representation to image and text embedding space individually.…
Diversifying Spatial-Temporal Perception for Video Domain Generalization
Kun-Yu Lin, Jia-Run Du, Yipeng Gao +2
Video domain generalization aims to learn generalizable video classification models for unseen target domains by training in a source domain. A critical challenge of video domain g…
ASAG: Building Strong One-Decoder-Layer Sparse Detectors via Adaptive Sparse Anchor Generation
Shenghao Fu, Junkai Yan, Yipeng Gao +2
Recent sparse detectors with multiple, e.g. six, decoder layers achieve promising performance but much inference time due to complex heads. Previous works have explored using dense…
DilateFormer: Multi-Scale Dilated Transformer for Visual Recognition
Jiayu Jiao, Yu-Ming Tang, Kun-Yu Lin +4
As a de facto solution, the vanilla Vision Transformers (ViTs) are encouraged to model long-range dependencies between arbitrary image patches while the global attended receptive f…