FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4322731026> ?p ?o ?g. }

• W4322731026 endingPage "5199" @default.
• W4322731026 startingPage "5186" @default.
• W4322731026 abstract "Since video data contains temporal information, video crowd counting demonstrates more potential than single-frame crowd counting for scenarios requiring high accuracy. However, learning robust relationships among frames efficiently and cheaply is very challenging. Existing methods for video crowd counting lack explicit temporal correlation modeling and robustness, and they are complex. In this paper, we propose the Frame-Recurrent Video Crowd Counting (FRVCC) framework to solve these issues. Specifically, we design a frame-recurrent manner to recursively relate the density maps in the temporal dimension, which efficiently explores long-term inter-frame knowledge and ensures the continuity of feature map responses. FRVCC consists of three plug-in modules: an optical flow estimation module, a single-frame counting module, and a density map fusion module. For the fusion module, we propose the ResTrans network to robustly learn complementary features between visual-based and correlation-based feature maps through residual strategy and vision transformer. To constrain the output distribution to be consistent with the ground truth distribution, we introduce an adversarial loss to rectify the training process. Additionally, we release a large-scale synthetic video crowd-counting dataset, CrowdXV, to evaluate the proposed method and further improve its performance. We have conducted extensive experiments on several video-counting datasets. The results demonstrate that FRVCC achieves state-of-the-art performance and, concurrently, high generalization, high flexibility, and less complexity." @default.
• W4322731026 created "2023-03-03" @default.
• W4322731026 creator A5013030532 @default.
• W4322731026 creator A5027946490 @default.
• W4322731026 creator A5038617003 @default.
• W4322731026 creator A5048509281 @default.
• W4322731026 creator A5065926499 @default.
• W4322731026 date "2023-09-01" @default.
• W4322731026 modified "2023-09-27" @default.
• W4322731026 title "Frame-Recurrent Video Crowd Counting" @default.
• W4322731026 cites W1755205674 @default.
• W4322731026 cites W1910776219 @default.
• W4322731026 cites W1947481528 @default.
• W4322731026 cites W1976959044 @default.
• W4322731026 cites W2031454541 @default.
• W4322731026 cites W2064675550 @default.
• W4322731026 cites W2072232009 @default.
• W4322731026 cites W2123175289 @default.
• W4322731026 cites W2164990725 @default.
• W4322731026 cites W2194775991 @default.
• W4322731026 cites W2316109659 @default.
• W4322731026 cites W2321408197 @default.
• W4322731026 cites W2463631526 @default.
• W4322731026 cites W2520826941 @default.
• W4322731026 cites W2552900565 @default.
• W4322731026 cites W2560474170 @default.
• W4322731026 cites W2583147637 @default.
• W4322731026 cites W2745597836 @default.
• W4322731026 cites W2795889831 @default.
• W4322731026 cites W2798490576 @default.
• W4322731026 cites W2799108379 @default.
• W4322731026 cites W2810968807 @default.
• W4322731026 cites W2886443245 @default.
• W4322731026 cites W2889054948 @default.
• W4322731026 cites W2895051362 @default.
• W4322731026 cites W2922282711 @default.
• W4322731026 cites W2922295717 @default.
• W4322731026 cites W2937076142 @default.
• W4322731026 cites W2945574898 @default.
• W4322731026 cites W2953684117 @default.
• W4322731026 cites W2962921175 @default.
• W4322731026 cites W2963426457 @default.
• W4322731026 cites W2963653352 @default.
• W4322731026 cites W2963693541 @default.
• W4322731026 cites W2963782415 @default.
• W4322731026 cites W2963893037 @default.
• W4322731026 cites W2964018834 @default.
• W4322731026 cites W2964094092 @default.
• W4322731026 cites W2964203052 @default.
• W4322731026 cites W2964209782 @default.
• W4322731026 cites W2964260687 @default.
• W4322731026 cites W2964286567 @default.
• W4322731026 cites W2964721919 @default.
• W4322731026 cites W2965778995 @default.
• W4322731026 cites W2967069910 @default.
• W4322731026 cites W2967776630 @default.
• W4322731026 cites W2968848584 @default.
• W4322731026 cites W2969620138 @default.
• W4322731026 cites W2977057439 @default.
• W4322731026 cites W2978859332 @default.
• W4322731026 cites W2982021328 @default.
• W4322731026 cites W2991203386 @default.
• W4322731026 cites W3004672782 @default.
• W4322731026 cites W3015084401 @default.
• W4322731026 cites W3015801606 @default.
• W4322731026 cites W3018001946 @default.
• W4322731026 cites W3027606690 @default.
• W4322731026 cites W3035307763 @default.
• W4322731026 cites W3035925134 @default.
• W4322731026 cites W3049248796 @default.
• W4322731026 cites W3089443962 @default.
• W4322731026 cites W3098866279 @default.
• W4322731026 cites W3109157205 @default.
• W4322731026 cites W3113251869 @default.
• W4322731026 cites W3120524222 @default.
• W4322731026 cites W3126329292 @default.
• W4322731026 cites W3163284529 @default.
• W4322731026 cites W3170841864 @default.
• W4322731026 cites W3188394685 @default.
• W4322731026 cites W3203845557 @default.
• W4322731026 cites W4214828374 @default.
• W4322731026 cites W4221147659 @default.
• W4322731026 cites W4226360223 @default.
• W4322731026 cites W4312613051 @default.
• W4322731026 cites W4312644483 @default.
• W4322731026 cites W764651262 @default.
• W4322731026 doi "https://doi.org/10.1109/tcsvt.2023.3250946" @default.
• W4322731026 hasPublicationYear "2023" @default.
• W4322731026 type Work @default.
• W4322731026 citedByCount "0" @default.
• W4322731026 crossrefType "journal-article" @default.
• W4322731026 hasAuthorship W4322731026A5013030532 @default.
• W4322731026 hasAuthorship W4322731026A5027946490 @default.
• W4322731026 hasAuthorship W4322731026A5038617003 @default.
• W4322731026 hasAuthorship W4322731026A5048509281 @default.
• W4322731026 hasAuthorship W4322731026A5065926499 @default.
• W4322731026 hasConcept C104317684 @default.
• W4322731026 hasConcept C115961682 @default.

• next