Matches in SemOpenAlex for { <https://semopenalex.org/work/W2996752649> ?p ?o ?g. }
- W2996752649 abstract "Pedestrian detection is an initial step to perform outdoor scene analysis, which plays an essential role in many real-world applications. Although having enjoyed the merits of deep learning frameworks from the generic object detectors, pedestrian detection is still a very challenging task due to heavy occlusion and highly crowded group. Generally, the conventional detectors are unable to differentiate individuals from each other effectively under such a dense environment. To tackle this critical problem, we propose an attribute-aware pedestrian detector to explicitly model people's semantic attributes in a high-level feature detection fashion. Besides the typical semantic features, center position, target's scale and offset, we introduce a pedestrian-oriented attribute feature to encode the high-level semantic differences among the crowd. Moreover, a novel attribute-feature-based Non-Maximum Suppression~(NMS) is proposed to distinguish the person from a highly overlapped group by adaptively rejecting the false-positive results in a very crowd settings. Furthermore, a novel ground truth target is designed to alleviate the difficulties caused by the attribute configuration and extremely class imbalance issues during training. Finally, we evaluate our proposed attribute-aware pedestrian detector on two benchmark datasets including CityPersons and CrowdHuman. The experimental results show that our approach outperforms state-of-the-art methods at a large margin on pedestrian detection." @default.
- W2996752649 created "2019-12-26" @default.
- W2996752649 creator A5019114599 @default.
- W2996752649 creator A5023372484 @default.
- W2996752649 creator A5032752009 @default.
- W2996752649 creator A5054030926 @default.
- W2996752649 creator A5062252650 @default.
- W2996752649 creator A5063519364 @default.
- W2996752649 creator A5074834854 @default.
- W2996752649 date "2019-10-21" @default.
- W2996752649 modified "2023-10-14" @default.
- W2996752649 title "Attribute-aware Pedestrian Detection in a Crowd" @default.
- W2996752649 cites W1536680647 @default.
- W2996752649 cites W1608462934 @default.
- W2996752649 cites W1903127635 @default.
- W2996752649 cites W1986905809 @default.
- W2996752649 cites W2046871815 @default.
- W2996752649 cites W2074777933 @default.
- W2996752649 cites W2117539524 @default.
- W2996752649 cites W2125556102 @default.
- W2996752649 cites W2140090057 @default.
- W2996752649 cites W2168356304 @default.
- W2996752649 cites W2170101770 @default.
- W2996752649 cites W2194775991 @default.
- W2996752649 cites W2200528286 @default.
- W2996752649 cites W2340897893 @default.
- W2996752649 cites W2490270993 @default.
- W2996752649 cites W2497039038 @default.
- W2996752649 cites W2519057214 @default.
- W2996752649 cites W2565639579 @default.
- W2996752649 cites W2570343428 @default.
- W2996752649 cites W2592691248 @default.
- W2996752649 cites W2594507094 @default.
- W2996752649 cites W2612624696 @default.
- W2996752649 cites W2613599172 @default.
- W2996752649 cites W2613718673 @default.
- W2996752649 cites W2775890136 @default.
- W2996752649 cites W2798542761 @default.
- W2996752649 cites W2801227907 @default.
- W2996752649 cites W2884960332 @default.
- W2996752649 cites W2886335102 @default.
- W2996752649 cites W2886904239 @default.
- W2996752649 cites W2894820835 @default.
- W2996752649 cites W2895451584 @default.
- W2996752649 cites W2896540732 @default.
- W2996752649 cites W2899771611 @default.
- W2996752649 cites W2935837427 @default.
- W2996752649 cites W2949560194 @default.
- W2996752649 cites W2952888378 @default.
- W2996752649 cites W2963093690 @default.
- W2996752649 cites W2963315052 @default.
- W2996752649 cites W2963323244 @default.
- W2996752649 cites W2963351448 @default.
- W2996752649 cites W2963402592 @default.
- W2996752649 cites W2963404857 @default.
- W2996752649 cites W2963681621 @default.
- W2996752649 cites W2963769056 @default.
- W2996752649 cites W2964080601 @default.
- W2996752649 cites W2964121718 @default.
- W2996752649 cites W2964121744 @default.
- W2996752649 cites W3106250896 @default.
- W2996752649 doi "https://doi.org/10.48550/arxiv.1910.09188" @default.
- W2996752649 hasPublicationYear "2019" @default.
- W2996752649 type Work @default.
- W2996752649 sameAs 2996752649 @default.
- W2996752649 citedByCount "2" @default.
- W2996752649 countsByYear W29967526492020 @default.
- W2996752649 countsByYear W29967526492021 @default.
- W2996752649 crossrefType "posted-content" @default.
- W2996752649 hasAuthorship W2996752649A5019114599 @default.
- W2996752649 hasAuthorship W2996752649A5023372484 @default.
- W2996752649 hasAuthorship W2996752649A5032752009 @default.
- W2996752649 hasAuthorship W2996752649A5054030926 @default.
- W2996752649 hasAuthorship W2996752649A5062252650 @default.
- W2996752649 hasAuthorship W2996752649A5063519364 @default.
- W2996752649 hasAuthorship W2996752649A5074834854 @default.
- W2996752649 hasBestOaLocation W29967526491 @default.
- W2996752649 hasConcept C104317684 @default.
- W2996752649 hasConcept C119857082 @default.
- W2996752649 hasConcept C124101348 @default.
- W2996752649 hasConcept C127413603 @default.
- W2996752649 hasConcept C13280743 @default.
- W2996752649 hasConcept C138885662 @default.
- W2996752649 hasConcept C153180895 @default.
- W2996752649 hasConcept C154945302 @default.
- W2996752649 hasConcept C175291020 @default.
- W2996752649 hasConcept C185592680 @default.
- W2996752649 hasConcept C185798385 @default.
- W2996752649 hasConcept C199360897 @default.
- W2996752649 hasConcept C205649164 @default.
- W2996752649 hasConcept C22212356 @default.
- W2996752649 hasConcept C2776151529 @default.
- W2996752649 hasConcept C2776401178 @default.
- W2996752649 hasConcept C2777113093 @default.
- W2996752649 hasConcept C2780156472 @default.
- W2996752649 hasConcept C31972630 @default.
- W2996752649 hasConcept C41008148 @default.
- W2996752649 hasConcept C41895202 @default.
- W2996752649 hasConcept C55493867 @default.
- W2996752649 hasConcept C66746571 @default.