Matches in SemOpenAlex for { <https://semopenalex.org/work/W3110856766> ?p ?o ?g. }
- W3110856766 abstract "Crowd counting is a fundamental yet challenging task, which desires rich information to generate pixel-wise crowd density maps. However, most previous methods only used the limited information of RGB images and cannot well discover potential pedestrians in unconstrained scenarios. In this work, we find that incorporating optical and thermal information can greatly help to recognize pedestrians. To promote future researches in this field, we introduce a large-scale RGBT Crowd Counting (RGBT-CC) benchmark, which contains 2,030 pairs of RGB-thermal images with 138,389 annotated people. Furthermore, to facilitate the multimodal crowd counting, we propose a cross-modal collaborative representation learning framework, which consists of multiple modality-specific branches, a modality-shared branch, and an Information Aggregation-Distribution Module (IADM) to capture the complementary information of different modalities fully. Specifically, our IADM incorporates two collaborative information transfers to dynamically enhance the modality-shared and modality-specific representations with a dual information propagation mechanism. Extensive experiments conducted on the RGBT-CC benchmark demonstrate the effectiveness of our framework for RGBT crowd counting. Moreover, the proposed approach is universal for multimodal crowd counting and is also capable to achieve superior performance on the ShanghaiTechRGBD dataset. Finally, our source code and benchmark are released at {url{http://lingboliu.com/RGBT_Crowd_Counting.html}}." @default.
- W3110856766 created "2020-12-21" @default.
- W3110856766 creator A5042117275 @default.
- W3110856766 creator A5042965510 @default.
- W3110856766 creator A5050590989 @default.
- W3110856766 creator A5058965019 @default.
- W3110856766 creator A5061828638 @default.
- W3110856766 creator A5071844040 @default.
- W3110856766 date "2020-12-08" @default.
- W3110856766 modified "2023-10-16" @default.
- W3110856766 title "Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting" @default.
- W3110856766 cites W1203557841 @default.
- W3110856766 cites W1522301498 @default.
- W3110856766 cites W1686810756 @default.
- W3110856766 cites W1910776219 @default.
- W3110856766 cites W1976959044 @default.
- W3110856766 cites W1978232622 @default.
- W3110856766 cites W2058907003 @default.
- W3110856766 cites W2072232009 @default.
- W3110856766 cites W2123175289 @default.
- W3110856766 cites W2145056192 @default.
- W3110856766 cites W2463631526 @default.
- W3110856766 cites W2497039038 @default.
- W3110856766 cites W2520826941 @default.
- W3110856766 cites W2541389513 @default.
- W3110856766 cites W2741077351 @default.
- W3110856766 cites W2798618325 @default.
- W3110856766 cites W2886443245 @default.
- W3110856766 cites W2895051362 @default.
- W3110856766 cites W2943898693 @default.
- W3110856766 cites W2947690922 @default.
- W3110856766 cites W2948300571 @default.
- W3110856766 cites W2949333977 @default.
- W3110856766 cites W2955171701 @default.
- W3110856766 cites W2962832028 @default.
- W3110856766 cites W2962891704 @default.
- W3110856766 cites W2963893037 @default.
- W3110856766 cites W2964018834 @default.
- W3110856766 cites W2964203052 @default.
- W3110856766 cites W2964209782 @default.
- W3110856766 cites W2965247173 @default.
- W3110856766 cites W2970971581 @default.
- W3110856766 cites W2981521755 @default.
- W3110856766 cites W2982007926 @default.
- W3110856766 cites W2982014038 @default.
- W3110856766 cites W2990128502 @default.
- W3110856766 cites W2995582330 @default.
- W3110856766 cites W2998048830 @default.
- W3110856766 cites W3002301267 @default.
- W3110856766 cites W3004672782 @default.
- W3110856766 cites W3006419170 @default.
- W3110856766 cites W3010021361 @default.
- W3110856766 cites W3013987429 @default.
- W3110856766 cites W3031402860 @default.
- W3110856766 cites W3032910121 @default.
- W3110856766 cites W3034519219 @default.
- W3110856766 cites W3035193053 @default.
- W3110856766 cites W3035284915 @default.
- W3110856766 cites W3035357085 @default.
- W3110856766 cites W3035633116 @default.
- W3110856766 cites W3040479127 @default.
- W3110856766 cites W3040607188 @default.
- W3110856766 cites W3042272129 @default.
- W3110856766 cites W3049248796 @default.
- W3110856766 cites W3082004586 @default.
- W3110856766 cites W3095336680 @default.
- W3110856766 cites W3097053213 @default.
- W3110856766 cites W3097305524 @default.
- W3110856766 cites W3108822985 @default.
- W3110856766 cites W3109242411 @default.
- W3110856766 cites W3203040502 @default.
- W3110856766 doi "https://doi.org/10.48550/arxiv.2012.04529" @default.
- W3110856766 hasPublicationYear "2020" @default.
- W3110856766 type Work @default.
- W3110856766 sameAs 3110856766 @default.
- W3110856766 citedByCount "1" @default.
- W3110856766 countsByYear W31108567662021 @default.
- W3110856766 crossrefType "posted-content" @default.
- W3110856766 hasAuthorship W3110856766A5042117275 @default.
- W3110856766 hasAuthorship W3110856766A5042965510 @default.
- W3110856766 hasAuthorship W3110856766A5050590989 @default.
- W3110856766 hasAuthorship W3110856766A5058965019 @default.
- W3110856766 hasAuthorship W3110856766A5061828638 @default.
- W3110856766 hasAuthorship W3110856766A5071844040 @default.
- W3110856766 hasBestOaLocation W31108567661 @default.
- W3110856766 hasConcept C119857082 @default.
- W3110856766 hasConcept C121332964 @default.
- W3110856766 hasConcept C13280743 @default.
- W3110856766 hasConcept C144024400 @default.
- W3110856766 hasConcept C154945302 @default.
- W3110856766 hasConcept C162324750 @default.
- W3110856766 hasConcept C177264268 @default.
- W3110856766 hasConcept C17744445 @default.
- W3110856766 hasConcept C185592680 @default.
- W3110856766 hasConcept C185798385 @default.
- W3110856766 hasConcept C187736073 @default.
- W3110856766 hasConcept C188027245 @default.
- W3110856766 hasConcept C199360897 @default.
- W3110856766 hasConcept C199539241 @default.
- W3110856766 hasConcept C202444582 @default.