Matches in SemOpenAlex for { <https://semopenalex.org/work/W3016101116> ?p ?o ?g. }
- W3016101116 abstract "Datasets drive vision progress, yet existing driving datasets are impoverished in terms of visual content and supported tasks to study multitask learning for autonomous driving. Researchers are usually constrained to study a small set of problems on one dataset, while real-world computer vision applications require performing tasks of various complexities. We construct BDD100K, the largest driving video dataset with 100K videos and 10 tasks to evaluate the exciting progress of image recognition algorithms on autonomous driving. The dataset possesses geographic, environmental, and weather diversity, which is useful for training models that are less likely to be surprised by new conditions. Based on this diverse dataset, we build a benchmark for heterogeneous multitask learning and study how to solve the tasks together. Our experiments show that special training strategies are needed for existing models to perform such heterogeneous tasks. BDD100K opens the door for future studies in this important venue." @default.
- W3016101116 created "2020-04-17" @default.
- W3016101116 creator A5006822602 @default.
- W3016101116 creator A5029105520 @default.
- W3016101116 creator A5048295434 @default.
- W3016101116 creator A5048617484 @default.
- W3016101116 creator A5050844365 @default.
- W3016101116 creator A5067487326 @default.
- W3016101116 creator A5075643825 @default.
- W3016101116 creator A5083103259 @default.
- W3016101116 date "2018-05-12" @default.
- W3016101116 modified "2023-09-27" @default.
- W3016101116 title "BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning" @default.
- W3016101116 cites W1861492603 @default.
- W3016101116 cites W1927052826 @default.
- W3016101116 cites W2031489346 @default.
- W3016101116 cites W2069248067 @default.
- W3016101116 cites W2107775979 @default.
- W3016101116 cites W2108598243 @default.
- W3016101116 cites W2115579991 @default.
- W3016101116 cites W2129587342 @default.
- W3016101116 cites W2134670479 @default.
- W3016101116 cites W2143104527 @default.
- W3016101116 cites W2167222293 @default.
- W3016101116 cites W2194775991 @default.
- W3016101116 cites W2291627510 @default.
- W3016101116 cites W2340897893 @default.
- W3016101116 cites W24089286 @default.
- W3016101116 cites W2524365899 @default.
- W3016101116 cites W2559767995 @default.
- W3016101116 cites W2594507094 @default.
- W3016101116 cites W2613718673 @default.
- W3016101116 cites W2781228439 @default.
- W3016101116 cites W2809324505 @default.
- W3016101116 cites W2890447039 @default.
- W3016101116 cites W2913340405 @default.
- W3016101116 cites W2916743882 @default.
- W3016101116 cites W2953920664 @default.
- W3016101116 cites W2962850830 @default.
- W3016101116 cites W2962855257 @default.
- W3016101116 cites W2963150697 @default.
- W3016101116 cites W2963211188 @default.
- W3016101116 cites W2963323244 @default.
- W3016101116 cites W2964185501 @default.
- W3016101116 cites W2964332990 @default.
- W3016101116 cites W2995681297 @default.
- W3016101116 cites W36434594 @default.
- W3016101116 cites W967544008 @default.
- W3016101116 doi "https://doi.org/10.48550/arxiv.1805.04687" @default.
- W3016101116 hasPublicationYear "2018" @default.
- W3016101116 type Work @default.
- W3016101116 sameAs 3016101116 @default.
- W3016101116 citedByCount "9" @default.
- W3016101116 countsByYear W30161011162021 @default.
- W3016101116 countsByYear W30161011162022 @default.
- W3016101116 countsByYear W30161011162023 @default.
- W3016101116 crossrefType "posted-content" @default.
- W3016101116 hasAuthorship W3016101116A5006822602 @default.
- W3016101116 hasAuthorship W3016101116A5029105520 @default.
- W3016101116 hasAuthorship W3016101116A5048295434 @default.
- W3016101116 hasAuthorship W3016101116A5048617484 @default.
- W3016101116 hasAuthorship W3016101116A5050844365 @default.
- W3016101116 hasAuthorship W3016101116A5067487326 @default.
- W3016101116 hasAuthorship W3016101116A5075643825 @default.
- W3016101116 hasAuthorship W3016101116A5083103259 @default.
- W3016101116 hasBestOaLocation W30161011161 @default.
- W3016101116 hasConcept C119857082 @default.
- W3016101116 hasConcept C13280743 @default.
- W3016101116 hasConcept C154945302 @default.
- W3016101116 hasConcept C162324750 @default.
- W3016101116 hasConcept C177264268 @default.
- W3016101116 hasConcept C185798385 @default.
- W3016101116 hasConcept C187736073 @default.
- W3016101116 hasConcept C199360897 @default.
- W3016101116 hasConcept C205649164 @default.
- W3016101116 hasConcept C2780451532 @default.
- W3016101116 hasConcept C2780801425 @default.
- W3016101116 hasConcept C28006648 @default.
- W3016101116 hasConcept C41008148 @default.
- W3016101116 hasConcept C51632099 @default.
- W3016101116 hasConceptScore W3016101116C119857082 @default.
- W3016101116 hasConceptScore W3016101116C13280743 @default.
- W3016101116 hasConceptScore W3016101116C154945302 @default.
- W3016101116 hasConceptScore W3016101116C162324750 @default.
- W3016101116 hasConceptScore W3016101116C177264268 @default.
- W3016101116 hasConceptScore W3016101116C185798385 @default.
- W3016101116 hasConceptScore W3016101116C187736073 @default.
- W3016101116 hasConceptScore W3016101116C199360897 @default.
- W3016101116 hasConceptScore W3016101116C205649164 @default.
- W3016101116 hasConceptScore W3016101116C2780451532 @default.
- W3016101116 hasConceptScore W3016101116C2780801425 @default.
- W3016101116 hasConceptScore W3016101116C28006648 @default.
- W3016101116 hasConceptScore W3016101116C41008148 @default.
- W3016101116 hasConceptScore W3016101116C51632099 @default.
- W3016101116 hasLocation W30161011161 @default.
- W3016101116 hasOpenAccess W3016101116 @default.
- W3016101116 hasPrimaryLocation W30161011161 @default.
- W3016101116 hasRelatedWork W1509467138 @default.
- W3016101116 hasRelatedWork W2655871005 @default.
- W3016101116 hasRelatedWork W2961085424 @default.