Multiobject tracking as maximum weight independent set

By William Brendel, Mohamed R. Amer, Sinisa Todorovic. Computer Vision and Pattern Recognition, 2011

302 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/38079a7f127ee9279ac99c4e18f87e80777cc895

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Features for Multi-target Multi-camera Tracking and Re-identification (2018, background): “Formulations with polynomial time solutions consider evidence along paths of time-consecutive edges [8, 16, 31, 37, 38, 39, 55, 75, 78] and some build on bipartite matching [12, 14, 20, 26, 42, 62, 71].”
Online Multi-object Tracking Using CNN-Based Single Object Tracker with Spatial-Temporal Attention Mechanism (2017, methodology): “These off-line methods consider MOT as a global optimization problem and focus on designing various optimization algorithm such as network flow [39, 58], continuous energy minimization [33], max weight independent set [6], k-partite graph [56, 10], subgraph multi-cut [43, 44] and so on.”
Joint Probabilistic Data Association Revisited (2015, background): “Further examples that belong to that second class include quadratic boolean programming [24], generalized clique problems [45], maximum weight-independent set [9] and many more.”
Multi-target tracking by learning local-to-global trajectory models (2015, methodology): “In each temporal window, the trajectory models are initialized by the local information to link those easy-to-connect detections into a set of tracklets.”
Part-based multiple-person tracking with partial occlusion handling (2012, methodology): “[5] apply a maximum-weight independent set algorithm to merge small tracklets into long tracks.”
The Way They Move: Tracking Multiple Targets with Similar Appearance (2013, methodology): “[12] used a maximum weighted set formulation but they only consider two-frames relations.”
Opening up Open World Tracking (2021, background): “Early effort focused on developing strong data association techniques [11,39,41,50,63,65] and hand-crafting appearance [23, 49, 52] and motion cues [15, 38].”
UA-DETRAC: A new benchmark and protocol for multi-object detection and tracking (2015, methodology): “…of detection / tracklet pairs as an optimization task based on the K-shortest path (Berclaz et al., 2011), maximum weight independent sets (Brendel et al., 2011), maximum multi-clique optimization (Dehghan et al., 2015), tensor power iterations (Shi et al., 2014), network ﬂows (Zhang et…”
Robust Online Multi-object Tracking Based on Tracklet Confidence and Online Discriminative Appearance Learning (2014, background): “Thus, the global association is very crucial in this approach, and many methods [2, 6, 21] for global association have been proposed.”
Spatial-Temporal Relation Networks for Multi-Object Tracking (2019, background): “According to what kind of information is used to establishing the association between objects in different frames, the existing methods can be categorized into online methods [2, 12, 19, 27, 33, 35, 38, 47, 50, 58, 59, 9], and offline methods [7, 14, 36, 39, 40, 44, 51, 52, 53, 62].”
On pairwise costs for network flow multi-object tracking (2014, methodology): “[20, 19] formulate the problem in a framework that first selects tracklets and then connects them using a learned distance measure [7] or a CRF [20, 19].”
Fast action proposals for human action detection and search (2015, background): “In [41], maximum weight independent set is presented to solve the data association in multiple object tracking.”
Joint Graph Decomposition & Node Labeling: Problem, Algorithms, Applications (2016, background): “ns deﬁne both a decomposition and a node labeling of a givengraph(Fig. 1). This problem offers a common mathematical abstraction of seemingly unrelated computer vision tasks: Multiple object tracking [2, 3, 4, 7, 13, 17, 19, 29, 30] can be seen as the task of deciding, for every point in an image, w”
Memory Based Online Learning of Deep Representations from Video Streams (2017, methodology): “iple Object Tracking algorithms typically adopt appearance and motion cues into an afﬁnity model to estimate and link detections to form tracklets which are afterwards combined into ﬁnal trajectories [27,28,29,30,31,32]. Most existing MOT methods are applied to pedestrian tracking and either use sim”