FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2956268511> ?p ?o ?g. }

• W2956268511 endingPage "393" @default.
• W2956268511 startingPage "380" @default.
• W2956268511 abstract "Pedestrian detection has achieved significant progress with the availability of existing benchmark datasets. However, there is a gap in the diversity and density between real world requirements and current pedestrian detection benchmarks: 1) most of existing datasets are taken from a vehicle driving through the regular traffic scenario, usually leading to insufficient diversity; 2) crowd scenarios with highly occluded pedestrians are still under represented, resulting in low density. To narrow this gap and facilitate future pedestrian detection research, we introduce a large and diverse dataset named WiderPerson for dense pedestrian detection in the wild. This dataset involves five types of annotations in a wide range of scenarios, no longer limited to the traffic scenario. There are a total of $13,382$ images with $399,786$ annotations, i.e., $29.87$ annotations per image, which means this dataset contains dense pedestrians with various kinds of occlusions. Hence, pedestrians in the proposed dataset are extremely challenging due to large variations in the scenario and occlusion, which is suitable to evaluate pedestrian detectors in the wild. We introduce an improved Faster R-CNN and the vanilla RetinaNet to serve as baselines for the new pedestrian detection benchmark. Several experiments are conducted on previous datasets including Caltech-USA and CityPersons to analyze the generalization capabilities of the proposed dataset and we achieve state-of-the-art performances on these previous datasets without bells and whistles. Finally, we analyze common failure cases and find the classification ability of pedestrian detector needs to be improved to reduce false alarm and miss detection rates. The proposed dataset is available at http://www.cbsr.ia.ac.cn/users/sfzhang/WiderPerson" @default.
• W2956268511 created "2019-07-23" @default.
• W2956268511 creator A5042265409 @default.
• W2956268511 creator A5042988051 @default.
• W2956268511 creator A5063979916 @default.
• W2956268511 creator A5069079313 @default.
• W2956268511 creator A5082786719 @default.
• W2956268511 creator A5085022758 @default.
• W2956268511 date "2020-02-01" @default.
• W2956268511 modified "2023-10-16" @default.
• W2956268511 title "WiderPerson: A Diverse Dataset for Dense Pedestrian Detection in the Wild" @default.
• W2956268511 cites W1475617732 @default.
• W2956268511 cites W1903029394 @default.
• W2956268511 cites W1903127635 @default.
• W2956268511 cites W1910108985 @default.
• W2956268511 cites W1915068405 @default.
• W2956268511 cites W1962468782 @default.
• W2956268511 cites W1976818984 @default.
• W2956268511 cites W2031454541 @default.
• W2956268511 cites W2072232009 @default.
• W2956268511 cites W2074777933 @default.
• W2956268511 cites W2081021369 @default.
• W2956268511 cites W2096349671 @default.
• W2956268511 cites W2098699644 @default.
• W2956268511 cites W2100375262 @default.
• W2956268511 cites W2115991091 @default.
• W2956268511 cites W2117203466 @default.
• W2956268511 cites W2124285714 @default.
• W2956268511 cites W2125556102 @default.
• W2956268511 cites W2127420331 @default.
• W2956268511 cites W2133755669 @default.
• W2956268511 cites W2139479830 @default.
• W2956268511 cites W2150066425 @default.
• W2956268511 cites W2152945944 @default.
• W2956268511 cites W2159386181 @default.
• W2956268511 cites W2161969291 @default.
• W2956268511 cites W2162741153 @default.
• W2956268511 cites W2194775991 @default.
• W2956268511 cites W2200528286 @default.
• W2956268511 cites W2474389331 @default.
• W2956268511 cites W2548197316 @default.
• W2956268511 cites W2594507094 @default.
• W2956268511 cites W2610165754 @default.
• W2956268511 cites W2613599172 @default.
• W2956268511 cites W2752782242 @default.
• W2956268511 cites W2768166594 @default.
• W2956268511 cites W2775890136 @default.
• W2956268511 cites W2792824754 @default.
• W2956268511 cites W2801227907 @default.
• W2956268511 cites W2803740064 @default.
• W2956268511 cites W2962843773 @default.
• W2956268511 cites W2962850098 @default.
• W2956268511 cites W2963093690 @default.
• W2956268511 cites W2963315052 @default.
• W2956268511 cites W2963351448 @default.
• W2956268511 cites W2963566548 @default.
• W2956268511 cites W2963681621 @default.
• W2956268511 cites W2963786238 @default.
• W2956268511 cites W2963998989 @default.
• W2956268511 cites W639708223 @default.
• W2956268511 doi "https://doi.org/10.1109/tmm.2019.2929005" @default.
• W2956268511 hasPublicationYear "2020" @default.
• W2956268511 type Work @default.
• W2956268511 sameAs 2956268511 @default.
• W2956268511 citedByCount "57" @default.
• W2956268511 countsByYear W29562685112020 @default.
• W2956268511 countsByYear W29562685112021 @default.
• W2956268511 countsByYear W29562685112022 @default.
• W2956268511 countsByYear W29562685112023 @default.
• W2956268511 crossrefType "journal-article" @default.
• W2956268511 hasAuthorship W2956268511A5042265409 @default.
• W2956268511 hasAuthorship W2956268511A5042988051 @default.
• W2956268511 hasAuthorship W2956268511A5063979916 @default.
• W2956268511 hasAuthorship W2956268511A5069079313 @default.
• W2956268511 hasAuthorship W2956268511A5082786719 @default.
• W2956268511 hasAuthorship W2956268511A5085022758 @default.
• W2956268511 hasBestOaLocation W29562685112 @default.
• W2956268511 hasConcept C119857082 @default.
• W2956268511 hasConcept C124101348 @default.
• W2956268511 hasConcept C127413603 @default.
• W2956268511 hasConcept C134306372 @default.
• W2956268511 hasConcept C153180895 @default.
• W2956268511 hasConcept C154945302 @default.
• W2956268511 hasConcept C159985019 @default.
• W2956268511 hasConcept C177148314 @default.
• W2956268511 hasConcept C185798385 @default.
• W2956268511 hasConcept C192562407 @default.
• W2956268511 hasConcept C204323151 @default.
• W2956268511 hasConcept C205649164 @default.
• W2956268511 hasConcept C22212356 @default.
• W2956268511 hasConcept C2776151529 @default.
• W2956268511 hasConcept C2776836416 @default.
• W2956268511 hasConcept C2777113093 @default.
• W2956268511 hasConcept C2780156472 @default.
• W2956268511 hasConcept C33923547 @default.
• W2956268511 hasConcept C41008148 @default.
• W2956268511 hasConcept C58640448 @default.
• W2956268511 hasConcept C76155785 @default.

• next