Paper-Conference

MGRQ: Post-Training Quantization For Vision Transformer With Mixed Granularity Reconstruction
Post-training quantization (PTQ) efficiently compresses vision models, but unfortunately, it accompanies a certain degree of accuracy …
引用 DOI
RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers
Post-training quantization (PTQ), which only requires a tiny dataset for calibration without end-to-end retraining, is a light and …
引用 代码 DOI
Patch Similarity Aware Data-Free Quantization for Vision Transformers
Vision transformers have recently gained great success on various computer vision tasks; nevertheless, their high model complexity …
引用 代码 DOI
Calibration and Measurement of Large Distortion Binocular Camera Based on Fully Connected Neural Network
Camera calibration is of great significance in computer vision technology. Large distortion binocular camera is notoriously hard to …
引用 DOI
Refinement of Boundary Regression Using Uncertainty in Temporal Action Localization
Boundary localization is a key component of most temporal action localization frameworks for untrimmed video. Deep-learning methods …
引用 代码 DOI
Natural Scene Facial Expression Recognition with Dimension Reduction Network
As an external manifestation of human emotions, expression recognition plays an important role in human-computer interaction. Although …
引用 DOI
Segmentation of Complex Object based on A Standardization Coding Method
Accurate segmentation of complex objects from point cloud data is a useful but difficult task in many applications. In order to achieve …
引用 DOI
Natural Scene Facial Expression Recognition based on Differential Features
As an external manifestation of human emotions, expression recognition plays an important role in human-computer interaction. Although …
引用 DOI
Multi-loss-aware Channel Pruning of Deep Networks
Channel pruning, which seeks to reduce the model size by removing redundant channels, is a popular solution for deep networks …
引用 DOI
Cluster Regularized Quantization for Deep Networks Compression
Deep neural networks (DNNs) have achieved great success in a wide range of computer vision areas, but the applications to mobile …
引用 DOI