9 citations · 9 across the 7 of their papers we have counts for
7 papers
SeGPruner: Semantic-Geometric Visual Token Pruner for 3D Question Answering
Wenli Li, Kai Zhao, Haoran Jiang +3
Vision-language models (VLMs) have been widely adopted for 3D question answering (3D QA). In typical pipelines, visual tokens extracted from multiple viewpoints are concatenated wi…
Heuristic Self-Paced Learning for Domain Adaptive Semantic Segmentation under Adverse Conditions
Shiqin Wang, Haoyang Chen, Huaizhou Huang +6
The learning order of semantic classes significantly impacts unsupervised domain adaptation for semantic segmentation, especially under adverse weather conditions. Most existing cu…
InstanceRSR: Real-World Super-Resolution via Instance-Aware Representation Alignment
Zixin Guo, Kai Zhao, Luyan Zhang
Existing real-world super-resolution (RSR) methods based on generative priors have achieved remarkable progress in producing high-quality and globally consistent reconstructions. H…
Motion-Aware Vision-Reference Alignment for Referring Multi-Object Tracking
Weiyi Lv, Ning Zhang, Hanyang Sun +5
Referring Multi-Object Tracking (RMOT) extends conventional multi-object tracking (MOT) by introducing natural language references for multi-modal fusion tracking. RMOT benchmarks…
Attention Debiasing for Token Pruning in Vision Language Models
Kai Zhao, Wubang Yuan, Yuchen Lin +5
Vision-language models (VLMs) typically encode substantially more visual tokens than text tokens, resulting in significant token redundancy. Pruning uninformative visual tokens is…
Open-Vocabulary Camouflaged Object Segmentation with Cascaded Vision Language Models
Kai Zhao, Wubang Yuan, Zheng Wang +4
Open-Vocabulary Camouflaged Object Segmentation (OVCOS) seeks to segment and classify camouflaged objects from arbitrary categories, presenting unique challenges due to visual ambi…
Dominant Shuffle: A Simple Yet Powerful Data Augmentation for Time-series Prediction
Kai Zhao, Zuojie He, Alex Hung +1
Recent studies have suggested frequency-domain Data augmentation (DA) is effec tive for time series prediction. Existing frequency-domain augmentations disturb the original data wi…