FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3190647944> ?p ?o ?g. }

• W3190647944 endingPage "3087" @default.
• W3190647944 startingPage "3069" @default.
• W3190647944 abstract "Multi-object tracking (MOT) is an important problem in computer vision which has a wide range of applications. Formulating MOT as multi-task learning of object detection and re-ID in a single network is appealing since it allows joint optimization of the two tasks and enjoys high computation efficiency. However, we find that the two tasks tend to compete with each other which need to be carefully addressed. In particular, previous works usually treat re-ID as a secondary task whose accuracy is heavily affected by the primary detection task. As a result, the network is biased to the primary detection task which is not fair to the re-ID task. To solve the problem, we present a simple yet effective approach termed as FairMOT based on the anchor-free object detection architecture CenterNet. Note that it is not a naive combination of CenterNet and re-ID. Instead, we present a bunch of detailed designs which are critical to achieve good tracking results by thorough empirical studies. The resulting approach achieves high accuracy for both detection and tracking. The approach outperforms the state-of-the-art methods by a large margin on several public datasets. The source code and pre-trained models are released at https://github.com/ifzhang/FairMOT ." @default.
• W3190647944 created "2021-08-16" @default.
• W3190647944 creator A5032279676 @default.
• W3190647944 creator A5037191476 @default.
• W3190647944 creator A5049963367 @default.
• W3190647944 creator A5050818559 @default.
• W3190647944 creator A5062755510 @default.
• W3190647944 date "2021-09-03" @default.
• W3190647944 modified "2023-10-18" @default.
• W3190647944 title "FairMOT: On the Fairness of Detection and Re-identification in Multiple Object Tracking" @default.
• W3190647944 cites W1528063097 @default.
• W3190647944 cites W1531192956 @default.
• W3190647944 cites W1861492603 @default.
• W3190647944 cites W1964846093 @default.
• W3190647944 cites W2055022211 @default.
• W3190647944 cites W2083049794 @default.
• W3190647944 cites W2111644456 @default.
• W3190647944 cites W2117539524 @default.
• W3190647944 cites W2120419212 @default.
• W3190647944 cites W2124781496 @default.
• W3190647944 cites W2150298366 @default.
• W3190647944 cites W2154889144 @default.
• W3190647944 cites W2163937424 @default.
• W3190647944 cites W2171243491 @default.
• W3190647944 cites W2194775991 @default.
• W3190647944 cites W2222512263 @default.
• W3190647944 cites W2225887246 @default.
• W3190647944 cites W2252355370 @default.
• W3190647944 cites W2474389331 @default.
• W3190647944 cites W2511791013 @default.
• W3190647944 cites W2534578893 @default.
• W3190647944 cites W2547098537 @default.
• W3190647944 cites W2565639579 @default.
• W3190647944 cites W2579024533 @default.
• W3190647944 cites W2594507094 @default.
• W3190647944 cites W2603203130 @default.
• W3190647944 cites W2604679602 @default.
• W3190647944 cites W2739491435 @default.
• W3190647944 cites W2766984662 @default.
• W3190647944 cites W2791873344 @default.
• W3190647944 cites W2806224701 @default.
• W3190647944 cites W2886581236 @default.
• W3190647944 cites W2890773826 @default.
• W3190647944 cites W2895150009 @default.
• W3190647944 cites W2895387432 @default.
• W3190647944 cites W2901155229 @default.
• W3190647944 cites W2902137659 @default.
• W3190647944 cites W2921601546 @default.
• W3190647944 cites W2953920664 @default.
• W3190647944 cites W2962855257 @default.
• W3190647944 cites W2963150697 @default.
• W3190647944 cites W2963323244 @default.
• W3190647944 cites W2963351448 @default.
• W3190647944 cites W2963377935 @default.
• W3190647944 cites W2963430933 @default.
• W3190647944 cites W2963498646 @default.
• W3190647944 cites W2963574614 @default.
• W3190647944 cites W2963901085 @default.
• W3190647944 cites W2963927307 @default.
• W3190647944 cites W2964019074 @default.
• W3190647944 cites W2964241181 @default.
• W3190647944 cites W2967515867 @default.
• W3190647944 cites W2967533163 @default.
• W3190647944 cites W2981393651 @default.
• W3190647944 cites W2983208726 @default.
• W3190647944 cites W2986357608 @default.
• W3190647944 cites W2986732333 @default.
• W3190647944 cites W2987175876 @default.
• W3190647944 cites W2989604896 @default.
• W3190647944 cites W3012573144 @default.
• W3190647944 cites W3014641072 @default.
• W3190647944 cites W3028052296 @default.
• W3190647944 cites W3034399482 @default.
• W3190647944 cites W3034427487 @default.
• W3190647944 cites W3034429256 @default.
• W3190647944 cites W3035410385 @default.
• W3190647944 cites W3035442500 @default.
• W3190647944 cites W3035727180 @default.
• W3190647944 cites W3085046840 @default.
• W3190647944 cites W3095753995 @default.
• W3190647944 cites W3096068180 @default.
• W3190647944 cites W3098711604 @default.
• W3190647944 cites W3099887740 @default.
• W3190647944 cites W3100591638 @default.
• W3190647944 cites W3100935401 @default.
• W3190647944 cites W3106763294 @default.
• W3190647944 cites W3165926952 @default.
• W3190647944 cites W4230498685 @default.
• W3190647944 doi "https://doi.org/10.1007/s11263-021-01513-4" @default.
• W3190647944 hasPublicationYear "2021" @default.
• W3190647944 type Work @default.
• W3190647944 sameAs 3190647944 @default.
• W3190647944 citedByCount "412" @default.
• W3190647944 countsByYear W31906479442020 @default.
• W3190647944 countsByYear W31906479442021 @default.
• W3190647944 countsByYear W31906479442022 @default.
• W3190647944 countsByYear W31906479442023 @default.
• W3190647944 crossrefType "journal-article" @default.

• next