Viblo AI

Viblo AI

thg 1 16, 2024 8:00 SA 10 phút đọc

Paper reading | X3D: Expanding Architectures for Efficient Video Recognition

Deep Learning

350 0 0

2

Viblo AI

thg 1 11, 2024 8:00 SA 8 phút đọc

Paper reading | MaxViT: Multi-Axis Vision Transformer

Deep Learning

391 2 0

4

Viblo AI

thg 1 9, 2024 8:00 SA 16 phút đọc

Paper reading | CoAtNet: Marrying Convolution and Attention for All Data Sizes

Deep Learning

463 0 0

4

Viblo AI

thg 1 6, 2024 8:00 SA 8 phút đọc

Paper reading | CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model

Deep Learning ocr

506 2 0

2

Viblo AI

thg 1 4, 2024 8:00 SA 4 phút đọc

Paper reading | Tóm tắt mô hình ResNeSt: Split-Attention Networks

Deep Learning

279 0 0

2

Viblo AI

thg 1 2, 2024 8:00 SA 8 phút đọc

Paper reading | Tìm hiểu mô hình ResNeXt

Deep Learning

991 0 0

2

Viblo AI

thg 12 30, 2023 8:00 SA 13 phút đọc

Paper reading | Deep High-Resolution Representation Learning for Visual Recognition

Deep Learning

637 0 0

3

Viblo AI

thg 12 28, 2023 8:00 SA 14 phút đọc

Paper reading | EfficientNetV2: Smaller Models and Faster Training

Deep Learning

1.7K 0 0

2

Viblo AI

thg 12 26, 2023 8:00 SA 6 phút đọc

Paper reading | Xception phiên bản nâng cấp của Inception V3

Deep Learning image classification

1.8K 0 0

3

Viblo AI

thg 12 23, 2023 8:00 SA 13 phút đọc

Paper reading | Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture

Deep Learning Vision Transformer

856 1 0

4

Viblo AI

thg 12 21, 2023 8:00 SA 4 phút đọc

Paper reading | Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning

Deep Learning Resnet

1.5K 0 0

2

Viblo AI

thg 12 19, 2023 8:00 SA 8 phút đọc

Paper reading | GRAPH ATTENTION NETWORKS

Deep Learning

1.9K 1 0

5

Viblo AI

thg 12 16, 2023 8:00 SA 6 phút đọc

Paper reading | ACTION-Net: Multipath Excitation for Action Recognition

Deep Learning Efficient Video Understanding

140 0 1

2

Viblo AI

thg 12 14, 2023 8:00 SA 8 phút đọc

Paper reading | VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking

Video Understanding

354 0 0

2

Viblo AI

thg 11 8, 2023 9:00 SA 9 phút đọc

Paper reading | VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

Video Understanding

512 0 0

4

Viblo AI

thg 11 8, 2023 8:00 SA 7 phút đọc

Paper reading | Video Swin Transformer

Deep Learning Transformer

600 1 0

4

Viblo AI

thg 11 6, 2023 9:00 SA 10 phút đọc

Paper reading | ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices

Deep Learning

172 0 0

3

Viblo AI

thg 11 6, 2023 8:00 SA 12 phút đọc

Paper reading | Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning

Video Understanding

107 0 0

2

Viblo AI

thg 11 3, 2023 9:00 SA 12 phút đọc

Paper reading | Expanding Language-Image Pretrained Models for General Video Recognition

Deep Learning

107 1 0

0

Viblo AI

thg 11 3, 2023 8:00 SA 13 phút đọc

Paper reading | ZipIt! Merging Models from Different Tasks without Training

Deep Learning Machine Learning sharpComputerVision

67 1 0

2

@ai

Paper reading | X3D: Expanding Architectures for Efficient Video Recognition

Paper reading | MaxViT: Multi-Axis Vision Transformer

Paper reading | CoAtNet: Marrying Convolution and Attention for All Data Sizes

Paper reading | CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model

Paper reading | Tóm tắt mô hình ResNeSt: Split-Attention Networks

Paper reading | Tìm hiểu mô hình ResNeXt

Paper reading | Deep High-Resolution Representation Learning for Visual Recognition

Paper reading | EfficientNetV2: Smaller Models and Faster Training

Paper reading | Xception phiên bản nâng cấp của Inception V3

Paper reading | Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture

Paper reading | Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning

Paper reading | GRAPH ATTENTION NETWORKS

Paper reading | ACTION-Net: Multipath Excitation for Action Recognition

Paper reading | VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking

Paper reading | VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

Paper reading | Video Swin Transformer

Paper reading | ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices

Paper reading | Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning

Paper reading | Expanding Language-Image Pretrained Models for General Video Recognition

Paper reading | ZipIt! Merging Models from Different Tasks without Training

Tổ chức

Xu hướng bài viết