https://github.com/gmberton/VPR-methods-evaluation
EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
A methodology that involves selecting relevant data or examples from a large dataset to support tasks like prediction, learning, or inference. It enhances models by providing context or additional information, often used in systems like retrieval-augmented generation or in-context learning.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition
ConveRT: Efficient and Accurate Conversational Representations from Transformers
Crisscrossed Captions: Extended Intramodal and Intermodal Semantic Similarity Judgments for MS-COCO
BIRB: A Generalization Benchmark for Information Retrieval in Bioacoustics
View-Invariant, Occlusion-Robust Probabilistic Embedding for Human Pose
Learning SO(3) Equivariant Representations with Spherical CNNs
Text-to-Image Generation Grounded by Fine-Grained User Attention
Ask the Right Questions: Active Question Reformulation with Reinforcement Learning
Composing Text and Image for Image Retrieval - An Empirical Odyssey
VSE++: Improving Visual-Semantic Embeddings with Hard Negatives
Deep Learning-Based Automatic Downbeat Tracking: A Brief Review
Binary Document Image Super Resolution for Improved Readability and OCR Performance
Particular object retrieval with integral max-pooling of CNN activations
2nd Place and 2nd Place Solution to Kaggle Landmark Recognition andRetrieval Competition 2019
From Local to Global: A Graph RAG Approach to Query-Focused Summarization
End-to-end Lyrics Alignment for Polyphonic Music Using an Audio-to-Character Recognition Model
Distilling Knowledge from Reader to Retriever for Question Answering
Music Artist Classification with Convolutional Recurrent Neural Networks
Pseudo Relevance Feedback with Deep Language Models and Dense Retrievers: Successes and Pitfalls
Variational Interaction Information Maximization for Cross-domain Disentanglement
Learning Deep Representations of Fine-grained Visual Descriptions
Learning Deep Representations of Fine-grained Visual Descriptions
SCDV : Sparse Composite Document Vectors using soft clustering over distributional representations
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.