https://github.com/melgor/pyface
MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Image Captioning is the task of describing the content of an image in words. This task lies at the intersection of computer vision and natural language processing. Most image captioning systems use an encoder-decoder framework, where an input image is encoded into an intermediate representation of the information in the image, and then decoded into a descriptive text sequence. The most popular benchmarks are nocaps and COCO, and models are typically evaluated according to a BLEU or CIDER metric.
( Image credit: Reflective Decoding Network for Image Captioning, ICCV'19)
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition
Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
M3P: Learning Universal Representations via Multitask Multilingual Multimodal Pre-training
Don't fear the unlabelled: safe semi-supervised learning via simple debiasing
Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks
Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning
A Critical Review of Recurrent Neural Networks for Sequence Learning
PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning
Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)
CoCa: Contrastive Captioners are Image-Text Foundation Models
CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching
Unified Unsupervised Salient Object Detection via Knowledge Transfer
What is the Role of Recurrent Neural Networks (RNNs) in an Image Caption Generator?
RISE: Randomized Input Sampling for Explanation of Black-box Models
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.