4 papers
DeepTable: Structural Attention Biases and Tree Path Encoding for Hierarchical Table Understanding
Jyun-Ying Yen, Cheng-Kuan Lin, Yu-Chee Tseng
Large language models (LLMs) have demonstrated strong performance in table understanding. However, they typically process table content and headers as linearized token sequences. T…
NOVA: Normal-Side Modeling for Training-Free Zero-Shot Video Anomaly Detection
Wei-Chih Yin, Yun-Ching Kao, Cheng-Kuan Lin +1
Training-free zero-shot video anomaly detection (ZS-VAD) leverages vision-language models (VLMs) to localize anomaly instances from a predefined anomaly vocabulary, without providi…
Dynamic Participation in Federated Learning: Benchmarks and a Knowledge Pool Plugin
Ming-Lun Lee, Fu-Shiang Yang, Cheng-Kuan Lin +3
Federated learning (FL) enables clients to collaboratively train a shared model in a distributed manner, setting it apart from traditional deep learning paradigms. However, most ex…
MP-PolarMask: A Faster and Finer Instance Segmentation for Concave Images
Ke-Lei Wang, Pin-Hsuan Chou, Young-Ching Chou +3
While there are a lot of models for instance segmentation, PolarMask stands out as a unique one that represents an object by a Polar coordinate system. With an anchor-box-free desi…