https://github.com/Scalsol/mega.pytorch
공식 코드Memory Enhanced Global-Local Aggregation for Video 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.
Memory Enhanced Global-Local Aggregation for Video Object Detection
Antibody Watch: Text Mining Antibody Specificity from the Literature
Joint Anchor-Feature Refinement for Real-Time Accurate Object Detection in Images and Videos
DETRPose: Real-time end-to-end transformer model for multi-person pose estimation
Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring
Line-Circle-Square (LCS): A Multilayered Geometric Filter for Edge-Based Detection
RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks
Highly Efficient Salient Object Detection with 100K Parameters
Geometry-Aware Attenuation Learning for Sparse-View CBCT Reconstruction
A General Gaussian Heatmap Label Assignment for Arbitrary-Oriented Object Detection
Defending Against Backdoor Attacks in Natural Language Generation
Towards Compact ConvNets via Structure-Sparsity Regularized Filter Pruning
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Joint Matrix Decomposition for Deep Convolutional Neural Networks Compression
WHC: Weighted Hybrid Criterion for Filter Pruning on Convolutional Neural Networks
NIPD: A Federated Learning Person Detection Benchmark Based on Real-World Non-IID Data
SAPNet: Segmentation-Aware Progressive Network for Perceptual Contrastive Deraining
Investigating Attention Mechanism in 3D Point Cloud Object Detection
VoLTA: Vision-Language Transformer with Weakly-Supervised Local-Feature Alignment
Who Blames Whom in a Crisis? Detecting Blame Ties from News Articles Using Neural Networks
LRVS-Fashion: Extending Visual Search with Referring Instructions
Prediction Surface Uncertainty Quantification in Object Detection Models for Autonomous Driving
DFNet: Discriminative feature extraction and integration network for salient object detection
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.