Matches in SemOpenAlex for { <https://semopenalex.org/work/W3048252364> ?p ?o ?g. }
- W3048252364 abstract "Fully convolutional networks have shown outstanding performance in the salient object detection (SOD) field. The state-of-the-art (SOTA) methods have a tendency to become deeper and more complex, which easily homogenize their learned deep features, resulting in a clear performance bottleneck. In sharp contrast to the conventional ``deeper'' schemes, this paper proposes a ``wider'' network architecture which consists of parallel sub networks with totally different network architectures. In this way, those deep features obtained via these two sub networks will exhibit large diversity, which will have large potential to be able to complement with each other. However, a large diversity may easily lead to the feature conflictions, thus we use the dense short-connections to enable a recursively interaction between the parallel sub networks, pursuing an optimal complementary status between multi-model deep features. Finally, all these complementary multi-model deep features will be selectively fused to make high-performance salient object detections. Extensive experiments on several famous benchmarks clearly demonstrate the superior performance, good generalization, and powerful learning ability of the proposed wider framework." @default.
- W3048252364 created "2020-08-13" @default.
- W3048252364 creator A5030724247 @default.
- W3048252364 creator A5035153076 @default.
- W3048252364 creator A5063211322 @default.
- W3048252364 creator A5065912071 @default.
- W3048252364 creator A5085393190 @default.
- W3048252364 date "2020-08-07" @default.
- W3048252364 modified "2023-09-27" @default.
- W3048252364 title "Depth Quality-aware Selective Saliency Fusion for RGB-D Image Salient Object Detection" @default.
- W3048252364 cites W1849277567 @default.
- W3048252364 cites W1895577753 @default.
- W3048252364 cites W1931639407 @default.
- W3048252364 cites W1942214758 @default.
- W3048252364 cites W1947031653 @default.
- W3048252364 cites W2002574940 @default.
- W3048252364 cites W2002781701 @default.
- W3048252364 cites W2037954058 @default.
- W3048252364 cites W2039313011 @default.
- W3048252364 cites W2068078373 @default.
- W3048252364 cites W2068723588 @default.
- W3048252364 cites W2086791339 @default.
- W3048252364 cites W2091840685 @default.
- W3048252364 cites W2097462803 @default.
- W3048252364 cites W21025885 @default.
- W3048252364 cites W2128272608 @default.
- W3048252364 cites W2128340050 @default.
- W3048252364 cites W2461475918 @default.
- W3048252364 cites W2519528544 @default.
- W3048252364 cites W2589728353 @default.
- W3048252364 cites W2765082222 @default.
- W3048252364 cites W2766915143 @default.
- W3048252364 cites W2788154928 @default.
- W3048252364 cites W2798791651 @default.
- W3048252364 cites W2808442315 @default.
- W3048252364 cites W2894878591 @default.
- W3048252364 cites W2896535068 @default.
- W3048252364 cites W2901084634 @default.
- W3048252364 cites W2934630415 @default.
- W3048252364 cites W2937549930 @default.
- W3048252364 cites W2939217524 @default.
- W3048252364 cites W2941590339 @default.
- W3048252364 cites W2944195984 @default.
- W3048252364 cites W2948510860 @default.
- W3048252364 cites W2950178297 @default.
- W3048252364 cites W2950622378 @default.
- W3048252364 cites W2951157758 @default.
- W3048252364 cites W2963032190 @default.
- W3048252364 cites W2963136160 @default.
- W3048252364 cites W2963299740 @default.
- W3048252364 cites W2963906836 @default.
- W3048252364 cites W2964023275 @default.
- W3048252364 cites W2969626490 @default.
- W3048252364 hasPublicationYear "2020" @default.
- W3048252364 type Work @default.
- W3048252364 sameAs 3048252364 @default.
- W3048252364 citedByCount "0" @default.
- W3048252364 crossrefType "posted-content" @default.
- W3048252364 hasAuthorship W3048252364A5030724247 @default.
- W3048252364 hasAuthorship W3048252364A5035153076 @default.
- W3048252364 hasAuthorship W3048252364A5063211322 @default.
- W3048252364 hasAuthorship W3048252364A5065912071 @default.
- W3048252364 hasAuthorship W3048252364A5085393190 @default.
- W3048252364 hasConcept C104317684 @default.
- W3048252364 hasConcept C108583219 @default.
- W3048252364 hasConcept C112313634 @default.
- W3048252364 hasConcept C115961682 @default.
- W3048252364 hasConcept C127716648 @default.
- W3048252364 hasConcept C134306372 @default.
- W3048252364 hasConcept C138885662 @default.
- W3048252364 hasConcept C149635348 @default.
- W3048252364 hasConcept C153180895 @default.
- W3048252364 hasConcept C154945302 @default.
- W3048252364 hasConcept C177148314 @default.
- W3048252364 hasConcept C185592680 @default.
- W3048252364 hasConcept C188082640 @default.
- W3048252364 hasConcept C193415008 @default.
- W3048252364 hasConcept C202444582 @default.
- W3048252364 hasConcept C26517878 @default.
- W3048252364 hasConcept C2776151529 @default.
- W3048252364 hasConcept C2776401178 @default.
- W3048252364 hasConcept C2776502983 @default.
- W3048252364 hasConcept C2780513914 @default.
- W3048252364 hasConcept C2780719617 @default.
- W3048252364 hasConcept C33923547 @default.
- W3048252364 hasConcept C38652104 @default.
- W3048252364 hasConcept C41008148 @default.
- W3048252364 hasConcept C41895202 @default.
- W3048252364 hasConcept C55493867 @default.
- W3048252364 hasConcept C81363708 @default.
- W3048252364 hasConcept C82990744 @default.
- W3048252364 hasConcept C9652623 @default.
- W3048252364 hasConceptScore W3048252364C104317684 @default.
- W3048252364 hasConceptScore W3048252364C108583219 @default.
- W3048252364 hasConceptScore W3048252364C112313634 @default.
- W3048252364 hasConceptScore W3048252364C115961682 @default.
- W3048252364 hasConceptScore W3048252364C127716648 @default.
- W3048252364 hasConceptScore W3048252364C134306372 @default.
- W3048252364 hasConceptScore W3048252364C138885662 @default.
- W3048252364 hasConceptScore W3048252364C149635348 @default.