10 papers · 1 filter
DetM-Tracker: Deterministic and Memory-Efficient VIS for Autonomous Industrial Inspection
You-Rui Lin, Jen-Chieh Wu, Tzu-Ti Wei +2
Autonomous industrial inspection requires strictly deterministic real-time inference under tight memory and computational constraints. However, existing Video Instance Segmentation…
Zero-Shot Cross-Material Ptychographic Phase Reconstruction Using Deep Learning
Wen-Chun Lin, Yu-Chee Tseng, Jen-Jee Chen +1
Ptychographic phase reconstruction is commonly formulated as an iterative inverse problem, requiring repeated object-probe updates and resulting in substantial computational cost f…
AlloEgo-VLM: Disambiguating Allocentric and Egocentric Reference Frames in Vision-Language Models
Kuan-Lin Chen, Tzu-Ti Wei, Chao-Chi Liao +2
This study investigates the challenge of ambiguity faced by Vision-Language Models (VLMs) in understanding spatial semantics. Spatial cognition, shaped by cognitive psychology, spa…
DynoDINO: Harnessing Dynamic Latent Information from DINO Features for Multi-Phase Medical Image Segmentation
Yu-Pu Hsu, Jen-Jee Chen, Yu-Chee Tseng
Multi-phase Contrast-Enhanced Computed Tomography (CECT) plays a central role in the diagnosis and characterization of focal lesions by capturing temporal enhancement patterns acro…
ViewMind3D: Modular View-Aware Inference for Training-Free 3D-QA
Ping-Kun Chiang, Kun-Ru Wu, Po-han Li +3
Recent advances in large language models (LLMs) and vision-language models (VLMs) have enabled new possibilities for 3D question answering (3D-QA), a key capability for embodied AI…
WiFi2Cap: Semantic Action Captioning from Wi-Fi CSI via Limb-Level Semantic Alignment
Tzu-Ti Wei, Chu-Yu Huang, Yu-Chee Tseng +1
Privacy-preserving semantic understanding of human activities is important for indoor sensing, yet existing Wi-Fi CSI-based systems mainly focus on pose estimation or predefined ac…
Partial Ring Scan: Revisiting Scan Order in Vision State Space Models
Yi-Kuan Hsieh, Kuan-Chuan Peng, Xin li +3
State Space Models (SSMs) have emerged as efficient alternatives to attention for vision tasks, offering lineartime sequence processing with competitive accuracy. Vision SSMs, howe…
Block-based Symmetric Pruning and Fusion for Efficient Vision Transformers
Yi-Kuan Hsieh, Jun-Wei Hsieh, Xin Li +2
Vision Transformer (ViT) has achieved impressive results across various vision tasks, yet its high computational cost limits practical applications. Recent methods have aimed to re…
DaMO: A Data-Efficient Multimodal Orchestrator for Temporal Reasoning with Video LLMs
Bo-Cheng Chiu, Jen-Jee Chen, Yu-Chee Tseng +2
Large Language Models (LLMs) have recently been extended to the video domain, enabling sophisticated video-language understanding. However, existing Video LLMs often exhibit limita…
Scale-Aware Crowd Count Network with Annotation Error Correction
Yi-Kuan Hsieh, Jun-Wei Hsieh, Yu-Chee Tseng +2
Traditional crowd counting networks suffer from information loss when feature maps are downsized through pooling layers, leading to inaccuracies in counting crowds at a distance. E…