MOT-17

MOT17 is a benchmark dataset for evaluating multiple people tracking algorithms in monocular videos, containing challenging scenarios such as occlusions and crowded scenes.

Papers using MOT-17 (20)

Probabilistic Tracklet Scoring And Inpainting For Multiple Object Tracking2020 · 85 citesOcclusion-robust Online Multi-object Visual Tracking Using A GM-PHD Filter With Cnn-based Re-identification2019 · 33 citesLITE: A Paradigm Shift In Multi-object Tracking With Efficient Reid Feature Integration2024 · 1 citesOcclusion-aware SORT: Observing Occlusion For Robust Multi-object Tracking2026Tracking Objects As Points2020 · 1,228 citesMemotr: Long-term Memory-augmented Transformer For Multi-object Tracking2023 · 100 citesSimple Cues Lead To A Strong Multi-object Tracker2022 · 6 citesMesh-sort: Simple And Effective Location-wise Tracker With Lost Management Strategies2023 · 1 citesWhen To Extract Reid Features: A Selective Approach For Improved Multiple Object Tracking2024Is Multiple Object Tracking A Matter Of Specialization?2024An Approximate Dynamic Programming Framework For Occlusion-robust Multi-object Tracking2024Temporally Propagated Masks And Bounding Boxes: Combining The Best Of Both Worlds For Multi-object Tracking2024TransTrack: Multiple Object Tracking with Transformer2020 · 359 citesMultiple People Tracking Using Hierarchical Deep Tracklet Re-identification2018 · 21 citesDeep OC-SORT: Multi-Pedestrian Tracking by Adaptive Re-Identification2023 · 10 citesContrastive Learning for Multi-Object Tracking with Transformers2023 · 4 citesTracking Objects as Pixel-wise Distributions2022 · 1 citesEnd-to-End Multi-Object Tracking with Global Response Map2020DeNoising-MOT: Towards Multiple Object Tracking with Severe Occlusions2023Learning Data Association for Multi-Object Tracking using Only Coordinates2024