Papers Object Tracking
“Object Tracking” 태그가 달린 논문 2,087편 · 필터 해제
Lattice Boltzmann Model for Learning Real-World Pixel Dynamicity
This work proposes the Lattice Boltzmann Model (LBM) to learn real-world pixel dynamicity for visual tracking. LBM decomposes visual representations into dynamic pixel lattices and solves pixel motion states through coll…
Object TrackingVisual TrackingPoint TrackingStableTracker: Learning to Stably Track Target via Differentiable Simulation
Existing FPV object tracking methods heavily rely on handcrafted modular pipelines, which incur high onboard computation and cumulative errors. While learning-based approaches have mitigated computational delays, most st…
Object TrackingT-SiamTPN: Temporal Siamese Transformer Pyramid Networks for Robust and Efficient UAV Tracking
Aerial object tracking remains a challenging task due to scale variations, dynamic backgrounds, clutter, and frequent occlusions. While most existing trackers emphasize spatial cues, they often overlook temporal dependen…
Computational EfficiencyObject TrackingMATTER: Multiscale Attention for Registration Error Regression
Point cloud registration (PCR) is crucial for many downstream tasks, such as simultaneous localization and mapping (SLAM) and object tracking. This makes detecting and quantifying registration misalignment, i.e., PCR qua…
Point Cloud RegistrationObject TrackingPoint CloudsBeyond Frame-wise Tracking: A Trajectory-based Paradigm for Efficient Point Cloud Tracking
LiDAR-based 3D single object tracking (3D SOT) is a critical task in robotics and autonomous systems. Existing methods typically follow frame-wise motion estimation or a sequence-based paradigm. However, the two-frame me…
Object TrackingPoint CloudsClassification of Driver Behaviour Using External Observation Techniques for Autonomous Vehicles
Road traffic accidents remain a significant global concern, with human error, particularly distracted and impaired driving, among the leading causes. This study introduces a novel driver behaviour classification system t…
Autonomous VehiclesObject DetectionObject TrackingHyperspectral Mamba for Hyperspectral Object Tracking
Hyperspectral object tracking holds great promise due to the rich spectral information and fine-grained material distinctions in hyperspectral images, which are beneficial in challenging scenarios. While existing hypersp…
Object TrackingBenchmarking EfficientTAM on FMO datasets
Fast and tiny object tracking remains a challenge in computer vision and in this paper we first introduce a JSON metadata file associated with four open source datasets of Fast Moving Objects (FMOs) image sequences. In a…
Object Tracking6-DoF Object Tracking with Event-based Optical Flow and Frames
Tracking the position and orientation of objects in space (i.e., in 6-DoF) in real time is a fundamental problem in robotics for environment interaction. It becomes more challenging when objects move at high-speed due to…
Event-based Optical FlowPose EstimationObject TrackingPose TrackingMulti-State Tracker: Enhancing Efficient Object Tracking via Multi-State Specialization and Interaction
Efficient trackers achieve faster runtime by reducing computational complexity and model parameters. However, this efficiency often compromises the expense of weakened feature representation capacity, thus limiting their…
Object TrackingSOI is the Root of All Evil: Quantifying and Breaking Similar Object Interference in Single Object Tracking
In this paper, we present the first systematic investigation and quantification of Similar Object Interference (SOI), a long-overlooked yet critical bottleneck in Single Object Tracking (SOT). Through controlled Online I…
Object TrackingOffline Auto Labeling: BAAS
This paper introduces BAAS, a new Extended Object Tracking (EOT) and fusion-based label annotation framework for radar detections in autonomous driving. Our framework utilizes Bayesian-based tracking, smoothing and event…
Autonomous DrivingObject TrackingSUIT: Spatial-Spectral Union-Intersection Interaction Network for Hyperspectral Object Tracking
Hyperspectral videos (HSVs), with their inherent spatial-spectral-temporal structure, offer distinct advantages in challenging tracking scenarios such as cluttered backgrounds and small objects. However, existing methods…
Object TrackingYOLOv1 to YOLOv11: A Comprehensive Survey of Real-Time Object Detection Innovations and Challenges
Over the past decade, object detection has advanced significantly, with the YOLO (You Only Look Once) family of models transforming the landscape of real-time vision applications through unified, end-to-end detection fra…
Real-Time Object DetectionInstance SegmentationPose EstimationObject TrackingTowards Robust Semantic Correspondence: A Benchmark and Insights
Semantic correspondence aims to identify semantically meaningful relationships between different images and is a fundamental challenge in computer vision. It forms the foundation for numerous tasks such as 3D reconstruct…
Semantic correspondence3D ReconstructionObject TrackingImage EditingA Deep Dive into Generic Object Tracking: A Survey
Generic object tracking remains an important yet challenging task in computer vision due to complex spatio-temporal dynamics, especially in the presence of occlusions, similar distractors, and appearance variations. Over…
Object TrackingCST Anti-UAV: A Thermal Infrared Benchmark for Tiny UAV Tracking in Complex Scenes
The widespread application of Unmanned Aerial Vehicles (UAVs) has raised serious public safety and privacy concerns, making UAV perception crucial for anti-UAV tasks. However, existing UAV tracking datasets predominantly…
Object TrackingEfficient Spatial-Temporal Modeling for Real-Time Video Analysis: A Unified Framework for Action Recognition and Object Tracking
Real-time video analysis remains a challenging problem in computer vision, requiring efficient processing of both spatial and temporal information while maintaining computational efficiency. Existing approaches often str…
Computational EfficiencyTemporal SequencesAction RecognitionObject TrackingTrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking
3D LiDAR-based single object tracking (SOT) relies on sparse and irregular point clouds, posing challenges from geometric variations in scale, motion patterns, and structural complexity across object categories. Current …
Object TrackingPoint CloudsMVA 2025 Small Multi-Object Tracking for Spotting Birds Challenge: Dataset, Methods, and Results
Small Multi-Object Tracking (SMOT) is particularly challenging when targets occupy only a few dozen pixels, rendering detection and appearance-based association unreliable. Building on the success of the MVA2023 SOD4SB c…
Multi-Object TrackingObject Tracking