https://github.com/AmirSh15/SSL_graph_audio
공식 코드Self-supervised Graphs for Audio Representation Learning with Limited Labeled Data
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Emotion Recognition is an important area of research to enable effective human-computer interaction. Human emotions can be detected using speech signal, facial expressions, body language, and electroencephalography (EEG). Source: Using Deep Autoencoders for Facial Expression Recognition
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Self-supervised Graphs for Audio Representation Learning with Limited Labeled Data
Dynamic Emotion Modeling with Learnable Graphs and Graph Inception Network
ResEmoteNet: Bridging Accuracy and Loss Reduction in Facial Emotion Recognition
Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting
SAME but Different: Fast and High-Quality Gibbs Parameter Estimation
LasHeR: A Large-scale High-diversity Benchmark for RGBT Tracking
Text Augmentation for Language Models in High Error Recognition Scenario
A Physics-informed Diffusion Model for High-fidelity Flow Field Reconstruction
AffinityNet: semi-supervised few-shot learning for disease type prediction
Semi-Supervised Bilingual Lexicon Induction with Two-way Interaction
LoRD: Local 4D Implicit Representation for High-Fidelity Dynamic Human Modeling
Evaluating Robustness over High Level Driving Instruction for Autonomous Driving
Comparing the market microstructure between two South African exchanges
Exploiting GAN Internal Capacity for High-Quality Reconstruction of Natural Images
Tracing Back Music Emotion Predictions to Sound Sources and Intuitive Perceptual Qualities
Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoireing
High-Fidelity Variable-Rate Image Compression via Invertible Activation Transformation
QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection
Ref-NMS: Breaking Proposal Bottlenecks in Two-Stage Referring Expression Grounding
Circuitscape in Julia: High Performance Connectivity Modelling to Support Conservation Decisions
Transformer based neural networks for emotion recognition in conversations
BachGAN: High-Resolution Image Synthesis from Salient Object Layout
Engagement Detection with Multi-Task Training in E-Learning Environments
Generating Annotated High-Fidelity Images Containing Multiple Coherent Objects
Differentially Private Synthetic Mixed-Type Data Generation For Unsupervised Learning
Leveraged Mel spectrograms using Harmonic and Percussive Components in Speech Emotion Recognition
Polarized Self-Attention: Towards High-quality Pixel-wise Regression
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.