https://github.com/mingkaid/rl-prompt
공식 코드RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
What is Human Pose Estimation? Human pose estimation is the process of estimating the configuration of the body (pose) from a single, typically monocular, image. Background. Human pose estimation is one of the key problems in computer vision that has been studied for well over 15 years. The reason for its importance is the abundance of applications that can benefit from such a technology. For example, human pose estimation allows for higher-level reasoning in the context of human-computer interaction and activity recognition; it is also one of the basic building blocks for marker-less motion capture (MoCap) technology. MoCap technology is useful for applications ranging from character animation to clinical analysis of gait pathologies.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning
Collaborative Distillation for Ultra-Resolution Universal Style Transfer
It is Not as Good as You Think! Evaluating Simultaneous Machine Translation on Interpretation Data
Affective Feedback Synthesis Towards Multimodal Text and Image Data
Style Pooling: Automatic Text Style Obfuscation for Improved Classification Fairness
Investigating Text Shortening Strategy in BERT: Truncation vs Summarization
Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation
Wikipedia graph mining: dynamic structure of collective memory
PoseFix: Model-agnostic General Human Pose Refinement Network
Benchmarking Foundation Models on Exceptional Cases: Dataset Creation and Validation
Which Factors are associated with Open Access Publishing? A Springer Nature Case Study
A Dynamic Spatial-temporal Attention Network for Early Anticipation of Traffic Accidents
Monkey See, Monkey Do: Harnessing Self-attention in Motion Diffusion for Zero-shot Motion Transfer
Unifying Human Motion Synthesis and Style Transfer with Denoising Diffusion Probabilistic Models
MSciNLI: A Diverse Benchmark for Scientific Natural Language Inference
Co-training for Low Resource Scientific Natural Language Inference
Information Mining for COVID-19 Research From a Large Volume of Scientific Literature
ERQA: Edge-Restoration Quality Assessment for Video Super-Resolution
Combining Contrastive and Supervised Learning for Video Super-Resolution Detection
Neural Article Pair Modeling for Wikipedia Sub-article Matching
YuE: Scaling Open Foundation Models for Long-Form Music Generation
MUSIED: A Benchmark for Event Detection from Multi-Source Heterogeneous Informal Texts
Text-Driven Neural Collaborative Filtering Model for Paper Source Tracing
AnthroScore: A Computational Linguistic Measure of Anthropomorphism
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.