Paper-Conference

2000-FPS Multi-object Extraction based on Cell-based Labeling
Real-time multi-object extraction at 2000 fps was realized by designing a cell-based labeling algorithm. The algorithm can label the …
引用 DOI
2000 FPS Real-time Vision System with High-frame-rate Video Recording
This paper introduces a high-speed vision system called IDP Express, which can execute real-time image processing and high frame rate …
引用 DOI
Angle-based Search Space Shrinking for Neural Architecture Search
In this work, we present a simple and general search space shrinking method, called Angle-Based search space Shrinking (ABS), for …
引用 DOI
Sparsity Induction for Accurate Post-Training Pruning of Large Language Models
引用 DOI
SAQ-SAM: Semantically-Aligned Quantization for Segment Anything Model
Segment Anything Model (SAM) exhibits remarkable zero-shot segmentation capability; however, its prohibitive computational costs make …
引用 代码 DOI
DilateQuant: Accurate and Efficient Diffusion Quantization via Weight Dilation
Model quantization is a promising method for accelerating and compressing diffusion models. Nevertheless, since post-training …
引用 代码 DOI
A Visual-Feedback-Based Active Light-Section 3-D Reconstruction Method for Moving Objects
The three-dimensional (3D) reconstruction method based on structured light projection is widely employed in the industrial field due to …
引用 DOI
K-Sort Eval: Efficient Preference Evaluation for Visual Generation via Corrected VLM-as-a-Judge
The rapid development of visual generative models raises the need for more scalable and human-aligned evaluation methods. While the …
引用 代码 DOI
PTQ4ARVG: Post-Training Quantization for AutoRegressive Visual Generation Models
AutoRegressive Visual Generation (ARVG) models retain an architecture compatible with language models, while achieving performance …
引用 代码 DOI
Efficient-SAM2: Accelerating SAM2 with Object-Aware Visual Encoding and Memory Retrieval
Segment Anything Model 2 (SAM2) shows excellent performance in video object segmentation tasks; however, the heavy computational burden …
引用 代码 DOI