https://github.com/cogsys-tuebingen/CBMOT
공식 코드Score refinement for confidence-based 3D multi-object tracking
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Multi-Object Tracking is a task in computer vision that involves detecting and tracking multiple objects within a video sequence. The goal is to identify and locate objects of interest in each frame and then associate them across frames to keep track of their movements over time. This task is challenging due to factors such as occlusion, motion blur, and changes in object appearance, and is typically solved using algorithms that integrate object detection and data association techniques.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Score refinement for confidence-based 3D multi-object tracking
OVT-B: A New Large-Scale Benchmark for Open-Vocabulary Multi-Object Tracking
UCMCTrack: Multi-Object Tracking with Uniform Camera Motion Compensation
Multi-view Tracking Using Weakly Supervised Human Motion Prediction
Quo Vadis: Is Trajectory Forecasting the Key Towards Long-Term Multi-Object Tracking?
Large-Scale Pre-training for Person Re-identification with Noisy Labels
Tracklet-Switch Adversarial Attack against Pedestrian Multi-Object Tracking Trackers
Segment as Points for Efficient Online Multi-Object Tracking and Segmentation
SRT3D: A Sparse Region-Based 3D Object Tracking Approach for the Real World
3DMOTFormer: Graph Transformer for Online 3D Multi-Object Tracking
VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking
Benchmarking Unsupervised Object Representations for Video Sequences
Probabilistic 3D Multi-Object Tracking for Autonomous Driving
When to Extract ReID Features: A Selective Approach for Improved Multiple Object Tracking
When to Extract ReID Features: A Selective Approach for Improved Multiple Object Tracking
Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection
Using Panoramic Videos for Multi-person Localization and Tracking in a 3D Panoramic Coordinate
Self-Supervised Multi-Object Tracking with Cross-Input Consistency
1st Place Solution to ECCV-TAO-2020: Detect and Represent Any Object for Tracking
CityFlow-NL: Tracking and Retrieval of Vehicles at City Scale by Natural Language Descriptions
Spatial-Temporal Multi-Cuts for Online Multiple-Camera Vehicle Tracking
Synthehicle: Multi-Vehicle Multi-Camera Tracking in Virtual Cities
FishMOT: A Simple and Effective Method for Fish Tracking Based on IoU Matching
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.