컴퓨터비전 주요 논문 리스트업

컴퓨터비전 분야에서의 주요 논문을 한번에 정리하기 위한 공간입니다.

목차
1	이미지 분류(Image Classification)
2	비디오 분류(Video Classification)
3	RNN based Models
4	트랜스포머(Transformers)
5	객체 탐지(Obejet Detection)
6	세그멘테이션(Segmentation)
7	메트릭 러닝(Metric Learning)
8	멀티모달 학습(Multimodal Learning)
9	생성 모델(Generative Models)

 

📌 1. 이미지 분류 (Image Classification)

논문 제목	모델/키워드	링크
ImageNet Classification with Deep Convolutional Neural Networks	AlexNet	paper
Visualizing and Understanding Convolutional Networks	ZFNet	paper
Very Deep Convolutional Networks for Large-Scale Image Recognition	VGG	paper
Going Deeper with Convolutions	GoogLeNet (Inception v1)	paper
Deep Residual Learning for Image Recognition	ResNet	paper
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning	Inception-v2/v3/v4	paper

 

📌 2. 비디오 분류 (Video Classification)

논문 제목	모델/키워드	링크
Two-Stream Convolutional Networks for Action Recognition in Videos	Two-stream	paper
Convolutional Two-Stream Network Fusion for Video Action Recognition	Two-stream fusion	paper
Temporal Segment Networks: Towards Good Practices for Deep Action Recognition	TSN	paper
Hidden Two-Stream Convolutional Networks for Action Recognition	Hidden Two-Stream	paper
Learning Spatiotemporal Features with 3D Convolutional Networks	C3D	paper
A Closer Look at Spatiotemporal Convolutions for Action Recognition	R(2+1)D	paper
Temporal 3D ConvNets: New Architecture and Transfer Learning for Video Classification	T3D	paper
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset	I3D	paper
Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification	S3D	paper
SlowFast Networks for Video Recognition	SlowFast	paper
X3D: Expanding Architectures for Efficient Video Recognition	X3D	paper
A Multiscale Vision Transformer	MViT	paper

 

📌 3. 순환 신경망 및 비디오 모델 (RNN + Video)

논문 제목	모델/키워드	링크
Base RNN Models
Learning representations by back-propagating errors	RNN(BPTT)	paper
Long Short-Term Memory	LSTM	paper
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation	GRU	paper
RNN-based Spatio-Temperal Modeling
Long-term Recurrent Convolutional Networks for Visual Recognition and Description	LRCN	paper
Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting	ConvLSTM	paper
Show, Attend and Tell	Visual Attention	paper

 

📌 4. 트랜스포머 (Transformers)

논문 제목	모델/키워드	링크
Attention Is All You Need	Transformer	paper
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding	BERT	paper
An Image is Worth 16x16 Words	ViT	paper
Training data-efficient image transformers & distillation	DeiT	paper
Swin Transformer	Swin	paper
TimeSformer	TimeSFormer	paper
ViViT: A Video Vision Transformer	ViViT	paper

 

📌 5. 객체 탐지 (Object Detection)

논문 제목	모델/키워드	링크
Rich feature hierarchies for accurate object detection and semantic segmentation	R-CNN	paper
Fast R-CNN	Fast R-CNN	paper
Faster R-CNN	Faster R-CNN	paper
You Only Look Once	YOLO	paper
SSD: Single Shot MultiBox Detector	SSD	paper
End-to-End Object Detection with Transformers	DETR	paper

 

📌 6. 세그멘테이션 (Segmentation)

논문 제목	모델/키워드	링크
Learning Deconvolution Network for Semantic Segmentation	DeconvNet	paper
U-Net: Convolutional Networks for Biomedical Image Segmentation	U-Net	paper
Mask R-CNN	Mask R-CNN	paper
Segmenter: Transformer for Semantic Segmentation	Segmenter	paper
DPT: Dense Prediction Transformer	DPT	paper

 

📌 7. 메트릭 러닝 (Metric Learning)

논문 제목	모델/키워드	링크
FaceNet: A Unified Embedding for Face Recognition and Clustering	Triplet Loss	paper
A Simple Framework for Contrastive Learning of Visual Representations	SimCLR	paper

 

📌 8. 멀티모달 학습 (Multimodal Learning)

논문 제목	모델/키워드	링크
ViLBERT: Pretraining Task-Agnostic V-L Representations	ViLBERT	paper
CLIP: Learning Transferable Visual Models From Natural Language Supervision	CLIP	paper
VATT: Learning Multimodal Representations with Video, Audio and Text	VATT	paper
VideoBERT: A Joint Model for Video and Language Representation Learning	VideoBERT	paper

 

📌 9. 생성 모델 (Generative Models)

논문 제목	모델/키워드	링크
Pixel Recurrent Neural Networks	PixelRNN	paper
Auto-Encoding Variational Bayes	VAE	paper
Generative Adversarial Nets	GAN	paper
Unsupervised Representation Learning with Deep Convolutional GANs	DCGAN	paper
Wasserstein GAN	WGAN	paper
Image-to-Image Translation with Conditional Adversarial Networks	Pix2pix	paper
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks	CycleGAN	paper
StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation	StarGAN	paper
A Style-Based Generator Architecture for Generative Adversarial Networks	StyleGAN	paper
NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis	NeRF	paper