https://github.com/ninikolov/lha
공식 코드Large-scale Hierarchical Alignment for Data-driven Text Rewriting
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.
Large-scale Hierarchical Alignment for Data-driven Text Rewriting
Style Transfer by Relaxed Optimal Transport and Self-Similarity
Causal Inference via Style Transfer for Out-of-distribution Generalisation
NLP-KG: A System for Exploratory Search of Scientific Literature in Natural Language Processing
Rethinking Learning Approaches for Long-Term Action Anticipation
Talking Point based Ideological Discourse Analysis in News Events
CSPRD: A Financial Policy Retrieval Dataset for Chinese Stock Market
A Systematic Investigation on Deep Learning-Based Omnidirectional Image and Video Super-Resolution
Just What You Desire: Constrained Timeline Summarization with Self-Reflection for Enhanced Relevance
Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning
HowSumm: A Multi-Document Summarization Dataset Derived from WikiHow Articles
MSSRNet: Manipulating Sequential Style Representation for Unsupervised Text Style Transfer
Gated Temporal Diffusion for Stochastic Long-Term Dense Anticipation
Dependency Learning for Legal Judgment Prediction with a Unified Text-to-Text Transformer
Hierarchical and Multimodal Data for Daily Activity Understanding
STARD: A Chinese Statute Retrieval Dataset with Real Queries Issued by Non-professionals
Wikiformer: Pre-training with Structured Information of Wikipedia for Ad-hoc Retrieval
D2Styler: Advancing Arbitrary Style Transfer with Discrete Diffusion Methods
LawBench: Benchmarking Legal Knowledge of Large Language Models
BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.