https://github.com/594422814/ContrastCorr
공식 코드Contrastive Transformation for Self-supervised Correspondence Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Video Object Detection aims to detect targets in videos using both spatial and temporal information. It's usually deeply integrated with tasks such as Object Detection and Object Tracking.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Contrastive Transformation for Self-supervised Correspondence Learning
Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking
Bridging the Gap Between End-to-end and Non-End-to-end Multi-Object Tracking
Weakly Supervised Convolutional LSTM Approach for Tool Tracking in Laparoscopic Videos
Learning What and Where: Disentangling Location and Identity Tracking Without Supervision
AiATrack: Attention in Attention for Transformer Visual Tracking
MixFormer: End-to-End Tracking with Iterative Mixed Attention
TSM: Temporal Shift Module for Efficient Video Understanding
ApproxDet: Content and Contention-Aware Approximate Object Detection for Mobiles
Do Different Tracking Tasks Require Different Appearance Models?
Associate Everything Detected: Facilitating Tracking-by-Detection to the Unknown
Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework
Referring Video Object Segmentation via Language-aligned Track Selection
Attention over learned object embeddings enables complex visual reasoning
Distractor-aware Siamese Networks for Visual Object Tracking
NeighborTrack: Improving Single Object Tracking by Bipartite Matching with Neighbor Tracklets
STMTrack: Template-free Visual Tracking with Space-time Memory Networks
ODTrack: Online Dense Temporal Token Learning for Visual Tracking
Robust Estimation of Similarity Transformation for Visual Object Tracking
Fast Template Matching and Update for Video Object Tracking and Segmentation
ProContEXT: Exploring Progressive Context Transformer for Tracking
Exploring Enhanced Contextual Information for Video-Level Object Tracking
Learning Spatial-Temporal Regularized Correlation Filters for Visual Tracking
NT-VOT211: A Large-Scale Benchmark for Night-time Visual Object Tracking
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.