Matches in SemOpenAlex for { <https://semopenalex.org/work/W4225531230> ?p ?o ?g. }
- W4225531230 endingPage "6323" @default.
- W4225531230 startingPage "6308" @default.
- W4225531230 abstract "How to explore the interaction between the RGB and thermal modalities is the key success of the RGB-T saliency object detection (SOD). Most of the existing methods integrate multi-modality information by designing various fusion strategies. However, the modality gap between the RGB and thermal features will lead to unsatisfactory performances by simple feature concatenation. To solve this problem, we innovatively propose a cross-guided modality difference reduction network (CGMDRNet) to achieve intrinsic consistency feature fusion via reducing the modality differences. Specifically, we design a modality difference reduction (MDR) module, which is embedded in each layer of the backbone network. The module uses a cross-guided strategy to reduce the modality difference between the RGB and thermal features. Then, a cross-attention fusion (CAF) module is designed to fuse cross-modality features with small modality differences. In addition, we use a transformer-based feature enhancement (TFE) module to enhance the high-level feature representation that contributes more to performance. Finally, the high-level features guide the fusion of low-level features to obtain a saliency map with clear boundaries. Extensive experiments on three public RGB-T datasets show that the proposed CGMDRNet achieves competitive performance compared with state-of-the-art (SOTA) RGB-T SOD models." @default.
- W4225531230 created "2022-05-05" @default.
- W4225531230 creator A5000581688 @default.
- W4225531230 creator A5018282808 @default.
- W4225531230 creator A5026080520 @default.
- W4225531230 creator A5030554236 @default.
- W4225531230 creator A5045067652 @default.
- W4225531230 creator A5049898953 @default.
- W4225531230 creator A5061745929 @default.
- W4225531230 date "2022-09-01" @default.
- W4225531230 modified "2023-10-14" @default.
- W4225531230 title "CGMDRNet: Cross-Guided Modality Difference Reduction Network for RGB-T Salient Object Detection" @default.
- W4225531230 cites W1976409045 @default.
- W4225531230 cites W1994273284 @default.
- W4225531230 cites W2039298799 @default.
- W4225531230 cites W20683899 @default.
- W4225531230 cites W2100470808 @default.
- W4225531230 cites W2337762808 @default.
- W4225531230 cites W2474876375 @default.
- W4225531230 cites W2560023338 @default.
- W4225531230 cites W2620958690 @default.
- W4225531230 cites W2725229849 @default.
- W4225531230 cites W2757028014 @default.
- W4225531230 cites W2765838470 @default.
- W4225531230 cites W2767623212 @default.
- W4225531230 cites W2793668851 @default.
- W4225531230 cites W2798807298 @default.
- W4225531230 cites W2798857366 @default.
- W4225531230 cites W2799074129 @default.
- W4225531230 cites W2883780447 @default.
- W4225531230 cites W2887486131 @default.
- W4225531230 cites W2887522866 @default.
- W4225531230 cites W2907643346 @default.
- W4225531230 cites W2909381593 @default.
- W4225531230 cites W2928165649 @default.
- W4225531230 cites W2942049721 @default.
- W4225531230 cites W2945809413 @default.
- W4225531230 cites W2948300571 @default.
- W4225531230 cites W2948500402 @default.
- W4225531230 cites W2951006004 @default.
- W4225531230 cites W2954773727 @default.
- W4225531230 cites W2957414648 @default.
- W4225531230 cites W2963112696 @default.
- W4225531230 cites W2963163009 @default.
- W4225531230 cites W2963529609 @default.
- W4225531230 cites W2963572583 @default.
- W4225531230 cites W2963706010 @default.
- W4225531230 cites W2963868681 @default.
- W4225531230 cites W2965638232 @default.
- W4225531230 cites W2969377765 @default.
- W4225531230 cites W2984144959 @default.
- W4225531230 cites W2985033611 @default.
- W4225531230 cites W2990984982 @default.
- W4225531230 cites W2995936506 @default.
- W4225531230 cites W2996878574 @default.
- W4225531230 cites W2996884277 @default.
- W4225531230 cites W2998449272 @default.
- W4225531230 cites W3002301267 @default.
- W4225531230 cites W3006465601 @default.
- W4225531230 cites W3010616503 @default.
- W4225531230 cites W3025800305 @default.
- W4225531230 cites W3047800102 @default.
- W4225531230 cites W3083388823 @default.
- W4225531230 cites W3097336090 @default.
- W4225531230 cites W3105291825 @default.
- W4225531230 cites W3106587394 @default.
- W4225531230 cites W3108421143 @default.
- W4225531230 cites W3108608656 @default.
- W4225531230 cites W3121523901 @default.
- W4225531230 cites W3134912427 @default.
- W4225531230 cites W3135874576 @default.
- W4225531230 cites W3151956566 @default.
- W4225531230 cites W3152765238 @default.
- W4225531230 cites W3159018159 @default.
- W4225531230 cites W3164802490 @default.
- W4225531230 cites W3166016280 @default.
- W4225531230 cites W3171757599 @default.
- W4225531230 cites W3177040887 @default.
- W4225531230 cites W3177795924 @default.
- W4225531230 cites W3187910480 @default.
- W4225531230 cites W3203040502 @default.
- W4225531230 cites W3203718853 @default.
- W4225531230 cites W3207668590 @default.
- W4225531230 cites W3211246039 @default.
- W4225531230 cites W4205971281 @default.
- W4225531230 cites W4214561053 @default.
- W4225531230 cites W4214696292 @default.
- W4225531230 cites W4256578957 @default.
- W4225531230 doi "https://doi.org/10.1109/tcsvt.2022.3166914" @default.
- W4225531230 hasPublicationYear "2022" @default.
- W4225531230 type Work @default.
- W4225531230 citedByCount "13" @default.
- W4225531230 countsByYear W42255312302023 @default.
- W4225531230 crossrefType "journal-article" @default.
- W4225531230 hasAuthorship W4225531230A5000581688 @default.
- W4225531230 hasAuthorship W4225531230A5018282808 @default.
- W4225531230 hasAuthorship W4225531230A5026080520 @default.
- W4225531230 hasAuthorship W4225531230A5030554236 @default.