Multiple Object Tracking
112 papers with code • 8 benchmarks • 16 datasets
Multiple Object Tracking is the problem of automatically identifying multiple objects in a video and representing them as a set of trajectories with high accuracy.
Source: SOT for MOT
Libraries
Use these libraries to find Multiple Object Tracking models and implementationsDatasets
Latest papers with no code
FOLT: Fast Multiple Object Tracking from UAV-captured Videos Based on Optical Flow
Given the extracted flow, the flow-guided feature augmentation is designed to augment the object detection feature based on its optical flow, which improves the detection of small objects.
MotionTrack: End-to-End Transformer-based Multi-Object Tracing with LiDAR-Camera Fusion
Multiple Object Tracking (MOT) is crucial to autonomous vehicle perception.
UTOPIA: Unconstrained Tracking Objects without Preliminary Examination via Cross-Domain Adaptation
Then, a new cross-domain MOT adaptation from existing datasets is proposed without any pre-defined human knowledge in understanding and modeling objects.
Tracking Objects with 3D Representation from Videos
In this paper, we rethink the data association in 2D MOT and utilize the 3D object representation to separate each object in the feature space.
MotionTrack: Learning Motion Predictor for Multiple Object Tracking
This challenge arises from two main factors: the insufficient discriminability of ReID features and the predominant utilization of linear motion models in MOT.
Z-GMOT: Zero-shot Generic Multiple Object Tracking
In this paper, we introduce a novel approach to address the limitations of existing MOT and GMOT methods.
Linear Object Detection in Document Images using Multiple Object Tracking
Linear objects convey substantial information about document structure, but are challenging to detect accurately because of degradation (curved, erased) or decoration (doubled, dashed).
Type-to-Track: Retrieve Any Object via Prompt-based Tracking
This paper introduces a novel paradigm for Multiple Object Tracking called Type-to-Track, which allows users to track objects in videos by typing natural language descriptions.
S$^3$Track: Self-supervised Tracking with Soft Assignment Flow
With this training approach in hand, we develop an appearance-based model for learning instance-aware object features used to construct a cost matrix based on the pairwise distances between the object features.
OVTrack: Open-Vocabulary Multiple Object Tracking
This leaves contemporary MOT methods limited to a small set of pre-defined object categories.