73 citations · 101 across the 13 of their papers we have counts for
14 papers
Symmetrical Joint Learning Support-query Prototypes for Few-shot Segmentation
Qun Li, Baoquan Sun, Fu Xiao +2
We propose Sym-Net, a novel framework for Few-Shot Segmentation (FSS) that addresses the critical issue of intra-class variation by jointly learning both query and support prototyp…
RepSGG: Novel Representations of Entities and Relationships for Scene Graph Generation
Hengyue Liu, Bir Bhanu
Scene Graph Generation (SGG) has achieved significant progress recently. However, most previous works rely heavily on fixed-size entity representations based on bounding box propos…
RECLIP: Resource-efficient CLIP by Training with Small Images
Runze Li, Dahun Kim, Bir Bhanu +1
We present RECLIP (Resource-efficient CLIP), a simple method that minimizes computational resource footprint for CLIP (Contrastive Language Image Pretraining). Inspired by the noti…
MonoIndoor++:Towards Better Practice of Self-Supervised Monocular Depth Estimation for Indoor Environments
Runze Li, Pan Ji, Yi Xu +1
Self-supervised monocular depth estimation has seen significant progress in recent years, especially in outdoor environments. However, depth prediction results are not satisfying i…
Dite-HRNet: Dynamic Lightweight High-Resolution Network for Human Pose Estimation
Qun Li, Ziyi Zhang, Fu Xiao +2
A high-resolution network exhibits remarkable capability in extracting multi-scale features for human pose estimation, but fails to capture long-range interactions between joints a…
Transferring Knowledge with Attention Distillation for Multi-Domain Image-to-Image Translation
Runze Li, Tomaso Fontanini, Luca Donati +2
Gradient-based attention modeling has been used widely as a way to visualize and understand convolutional neural networks. However, exploiting these visual explanations during the…