FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4292433237> ?p ?o ?g. }

• W4292433237 abstract "Grounded Situation Recognition (GSR) aims to generate structured semantic summaries of images for human-like'' event understanding. Specifically, GSR task not only detects the salient activity verb (e.g. buying), but also predicts all corresponding semantic roles (e.g. agent and goods). Inspired by object detection and image captioning tasks, existing methods typically employ a two-stage framework: 1) detect the activity verb, and then 2) predict semantic roles based on the detected verb. Obviously, this illogical framework constitutes a huge obstacle to semantic understanding. First, pre-detecting verbs solely without semantic roles inevitably fails to distinguish many similar daily activities (e.g., offering and giving, buying and selling). Second, predicting semantic roles in a closed auto-regressive manner can hardly exploit the semantic relations among the verb and roles. To this end, in this paper we propose a novel two-stage framework that focuses on utilizing such bidirectional relations within verbs and roles. In the first stage, instead of pre-detecting the verb, we postpone the detection step and assume a pseudo label, where an intermediate representation for each corresponding semantic role is learned from images. In the second stage, we exploit transformer layers to unearth the potential semantic relations within both verbs and semantic roles. With the help of a set of support images, an alternate learning scheme is designed to simultaneously optimize the results: update the verb using nouns corresponding to the image, and update nouns using verbs from support images. Extensive experimental results on challenging SWiG benchmarks show that our renovated framework outperforms other state-of-the-art methods under various metrics." @default.
• W4292433237 created "2022-08-20" @default.
• W4292433237 creator A5008754580 @default.
• W4292433237 creator A5030378762 @default.
• W4292433237 creator A5052956256 @default.
• W4292433237 creator A5058898461 @default.
• W4292433237 creator A5062546146 @default.
• W4292433237 date "2022-10-10" @default.
• W4292433237 modified "2023-10-11" @default.
• W4292433237 title "GSRFormer: Grounded Situation Recognition Transformer with Alternate Semantic Attention Refinement" @default.
• W4292433237 cites W2017875634 @default.
• W4292433237 cites W2105101328 @default.
• W4292433237 cites W2302086703 @default.
• W4292433237 cites W2423576022 @default.
• W4292433237 cites W2526377930 @default.
• W4292433237 cites W2527464456 @default.
• W4292433237 cites W2550553598 @default.
• W4292433237 cites W2560747010 @default.
• W4292433237 cites W2565639579 @default.
• W4292433237 cites W2579549467 @default.
• W4292433237 cites W2583194072 @default.
• W4292433237 cites W2604673901 @default.
• W4292433237 cites W2617576589 @default.
• W4292433237 cites W2745461083 @default.
• W4292433237 cites W2764273117 @default.
• W4292433237 cites W2886970679 @default.
• W4292433237 cites W2897169468 @default.
• W4292433237 cites W2916723116 @default.
• W4292433237 cites W2962766617 @default.
• W4292433237 cites W2962974137 @default.
• W4292433237 cites W2963037989 @default.
• W4292433237 cites W2963084599 @default.
• W4292433237 cites W2963155035 @default.
• W4292433237 cites W2963346996 @default.
• W4292433237 cites W2963524571 @default.
• W4292433237 cites W2963536419 @default.
• W4292433237 cites W2963542293 @default.
• W4292433237 cites W2963560594 @default.
• W4292433237 cites W2963649796 @default.
• W4292433237 cites W2963936326 @default.
• W4292433237 cites W2964157791 @default.
• W4292433237 cites W2980088508 @default.
• W4292433237 cites W2987123286 @default.
• W4292433237 cites W3003365594 @default.
• W4292433237 cites W3004349648 @default.
• W4292433237 cites W3034655362 @default.
• W4292433237 cites W3034971973 @default.
• W4292433237 cites W3035399403 @default.
• W4292433237 cites W3035413240 @default.
• W4292433237 cites W3035517717 @default.
• W4292433237 cites W3035598501 @default.
• W4292433237 cites W3095624694 @default.
• W4292433237 cites W3096609285 @default.
• W4292433237 cites W3096682293 @default.
• W4292433237 cites W3107320732 @default.
• W4292433237 cites W3138516171 @default.
• W4292433237 cites W3166304536 @default.
• W4292433237 cites W3170956458 @default.
• W4292433237 cites W3171660447 @default.
• W4292433237 cites W3172872502 @default.
• W4292433237 cites W3174012740 @default.
• W4292433237 cites W3175824375 @default.
• W4292433237 cites W3175958943 @default.
• W4292433237 cites W3181951703 @default.
• W4292433237 cites W4200630531 @default.
• W4292433237 cites W4211156271 @default.
• W4292433237 cites W4312900708 @default.
• W4292433237 cites W4313118515 @default.
• W4292433237 doi "https://doi.org/10.1145/3503161.3547943" @default.
• W4292433237 hasPublicationYear "2022" @default.
• W4292433237 type Work @default.
• W4292433237 citedByCount "2" @default.
• W4292433237 countsByYear W42924332372023 @default.
• W4292433237 crossrefType "proceedings-article" @default.
• W4292433237 hasAuthorship W4292433237A5008754580 @default.
• W4292433237 hasAuthorship W4292433237A5030378762 @default.
• W4292433237 hasAuthorship W4292433237A5052956256 @default.
• W4292433237 hasAuthorship W4292433237A5058898461 @default.
• W4292433237 hasAuthorship W4292433237A5062546146 @default.
• W4292433237 hasBestOaLocation W42924332371 @default.
• W4292433237 hasConcept C121332964 @default.
• W4292433237 hasConcept C121934690 @default.
• W4292433237 hasConcept C154945302 @default.
• W4292433237 hasConcept C165696696 @default.
• W4292433237 hasConcept C165801399 @default.
• W4292433237 hasConcept C19768560 @default.
• W4292433237 hasConcept C198942812 @default.
• W4292433237 hasConcept C204321447 @default.
• W4292433237 hasConcept C2776397901 @default.
• W4292433237 hasConcept C2777530160 @default.
• W4292433237 hasConcept C38652104 @default.
• W4292433237 hasConcept C41008148 @default.
• W4292433237 hasConcept C62520636 @default.
• W4292433237 hasConcept C66322947 @default.
• W4292433237 hasConcept C67277372 @default.
• W4292433237 hasConceptScore W4292433237C121332964 @default.
• W4292433237 hasConceptScore W4292433237C121934690 @default.
• W4292433237 hasConceptScore W4292433237C154945302 @default.
• W4292433237 hasConceptScore W4292433237C165696696 @default.
• W4292433237 hasConceptScore W4292433237C165801399 @default.

• next