22 citations · 30 across the 4 of their papers we have counts for
4 papers
Cross-Video Contextual Knowledge Exploration and Exploitation for Ambiguity Reduction in Weakly Supervised Temporal Action Localization
Songchun Zhang, Chunhui Zhao
Weakly supervised temporal action localization (WSTAL) aims to localize actions in untrimmed videos using video-level labels. Despite recent advances, existing approaches mainly fo…
Dyna-DepthFormer: Multi-frame Transformer for Self-Supervised Depth Estimation in Dynamic Scenes
Songchun Zhang, Chunhui Zhao
Self-supervised methods have showed promising results on depth estimation task. However, previous methods estimate the target depth map and camera ego-motion simultaneously, underu…
Bias-Eliminated Semantic Refinement for Any-Shot Learning
Liangjun Feng, Chunhui Zhao, Xi Li
When training samples are scarce, the semantic embedding technique, ie, describing class labels with attributes, provides a condition to generate visual features for unseen objects…
Semi-supervised Medical Image Segmentation via Geometry-aware Consistency Training
Zihang Liu, Chunhui Zhao
The performance of supervised deep learning methods for medical image segmentation is often limited by the scarcity of labeled data. As a promising research direction, semi-supervi…