https://github.com/maelic/sgg-benchmark
공식 코드REACT: Real-time Efficiency and Accuracy Compromise for Tradeoffs in Scene Graph Generation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
REACT: Real-time Efficiency and Accuracy Compromise for Tradeoffs in Scene Graph Generation
Neuromorphic Drone Detection: an Event-RGB Multimodal Approach
An Efficient and Scalable Deep Learning Approach for Road Damage Detection
Continual Learning for Out-of-Distribution Pedestrian Detection
ANNA: A Deep Learning Based Dataset in Heterogeneous Traffic for Autonomous Vehicles
Monitoring and Adapting the Physical State of a Camera for Autonomous Vehicles
SelfDocSeg: A Self-Supervised vision-based Approach towards Document Segmentation
Simple Image-level Classification Improves Open-vocabulary Object Detection
Inner-IoU: More Effective Intersection over Union Loss with Auxiliary Bounding Box
Select-Mosaic: Data Augmentation Method for Dense Small Object Scenes
Shape-IoU: More Accurate Metric considering Bounding Box Shape and Scale
FasterVideo: Efficient Online Joint Object Detection And Tracking
SAILOR: Scaling Anchors via Insights into Latent Object Representation
DOTIE -- Detecting Objects through Temporal Isolation of Events using a Spiking Architecture
Camera clustering for scalable stream-based active distillation
A semi-supervised Teacher-Student framework for surgical tool detection and localization
Towards Accurate Ground Plane Normal Estimation from Ego-Motion
LLM-Empowered Embodied Agent for Memory-Augmented Task Planning in Household Robotics
RADIATE: A Radar Dataset for Automotive Perception in Bad Weather
Improving Object Detection for Time-Lapse Imagery Using Temporal Features in Wildlife Monitoring
Self-Supervised Learning as a Means To Reduce the Need for Labeled Data in Medical Image Analysis
MetaCOG: A Hierarchical Probabilistic Model for Learning Meta-Cognitive Visual Representations
SafeSea: Synthetic Data Generation for Adverse & Low Probability Maritime Conditions
Seamless Iterative Semi-Supervised Correction of Imperfect Labels in Microscopy Images
Beyond the Field-of-View: Enhancing Scene Visibility and Perception with Clip-Recurrent Transformer
Harmonic Convolutional Networks based on Discrete Cosine Transform
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.