https://github.com/mrsempress/obmo
공식 코드OBMO: One Bounding Box Multiple Objects for Monocular 3D Object Detection
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
OBMO: One Bounding Box Multiple Objects for Monocular 3D Object Detection
End-to-End Zero-Shot HOI Detection via Vision and Language Knowledge Distillation
Multi-Source Spatial Knowledge Understanding for Immersive Visual Text-to-Speech
Identifying Label Errors in Object Detection Datasets by Loss Inspection
Lighting and Rotation Invariant Real-time Vehicle Wheel Detector based on YOLOv5
Improving Single Domain-Generalized Object Detection: A Focus on Diversification and Alignment
TDIOT: Target-driven Inference for Deep Video Object Tracking
FASTer: Focal Token Acquiring-and-Scaling Transformer for Long-term 3D Object Detection
Compressing Deep CNNs using Basis Representation and Spectral Fine-tuning
CIA: Controllable Image Augmentation Framework Based on Stable Diffusion
EPSANet: An Efficient Pyramid Squeeze Attention Block on Convolutional Neural Network
IR-LPR: Large Scale of Iranian License Plate Recognition Dataset
Faster OreFSDet : A Lightweight and Effective Few-shot Object Detector for Ore Images
Spatial-wise Dynamic Distillation for MLP-like Efficient Visual Fault Detection of Freight Trains
Disjoint Masking with Joint Distillation for Efficient Masked Image Modeling
T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos
Object Detection from Video Tubelets with Convolutional Neural Networks
BSH-Det3D: Improving 3D Object Detection with BEV Shape Heatmap
A tomographic workflow to enable deep learning for X-ray based foreign object detection
Security Fence Inspection at Airports Using Object Detection
Object Pose Estimation using Mid-level Visual Representations
STREAMLINE: Streaming Active Learning for Realistic Multi-Distributional Settings
VME: A Satellite Imagery Dataset and Benchmark for Detecting Vehicles in the Middle East and Beyond
SNIP: Single-shot Network Pruning based on Connection Sensitivity
MDHA: Multi-Scale Deformable Transformer with Hybrid Anchors for Multi-View 3D Object Detection
Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation
Stable Remaster: Bridging the Gap Between Old Content and New Displays
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.