https://github.com/yingift/mstar
공식 코드MSTAR: Box-free Multi-query Scene Text Retrieval with Attention Recycling
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
MSTAR: Box-free Multi-query Scene Text Retrieval with Attention Recycling
Real-World Light Field Image Super-Resolution via Degradation Modulation
Real-World Light Field Image Super-Resolution via Degradation Modulation
Unsupervised and Unregistered Hyperspectral Image Super-Resolution with Mutual Dirichlet-Net
IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection
Semi-supervised 3D Object Detection with Proficient Teachers
ProposalContrast: Unsupervised Pre-training for LiDAR-based 3D Object Detection
SSDA3D: Semi-supervised Domain Adaptation for 3D Object Detection from Point Cloud
Cyclic-Bootstrap Labeling for Weakly Supervised Object Detection
RfD-Net: Point Scene Understanding by Semantic Instance Reconstruction
MetaF2N: Blind Image Super-Resolution by Learning Efficient Model Adaptation from Faces
DATE: Dual Assignment for End-to-End Fully Convolutional Object Detection
Rethinking the Evaluation of Visible and Infrared Image Fusion
DetToolChain: A New Prompting Paradigm to Unleash Detection Ability of MLLM
RODNet: Radar Object Detection Using Cross-Modal Supervision
Towards Real-World Burst Image Super-Resolution: Benchmark and Method
Neural Maximum A Posteriori Estimation on Unpaired Data for Motion Deblurring
Distortion-aware Transformer in 360° Salient Object Detection
SNAP: A Benchmark for Testing the Effects of Capture Conditions on Fundamental Vision Tasks
DDet: Dual-path Dynamic Enhancement Network for Real-World Image Super-Resolution
L4DR: LiDAR-4DRadar Fusion for Weather-Robust 3D Object Detection
V2X-R: Cooperative LiDAR-4D Radar Fusion for 3D Object Detection with Denoising Diffusion
CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graph Diffusion
Enhancing Traffic Object Detection in Variable Illumination with RGB-Event Fusion
X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion
Efficient Multi-Scale Attention Module with Cross-Spatial Learning
DSLA: Dynamic smooth label assignment for efficient anchor-free object detection
Video Repurposing from User Generated Content: A Large-scale Dataset and Benchmark
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.