Matches in SemOpenAlex for { <https://semopenalex.org/work/W4225517085> ?p ?o ?g. }
- W4225517085 abstract "Visual grounding, i.e., localizing objects in images ac-cording to natural language queries, is an important topic in visual language understanding. The most effective approaches for this task are based on deep learning, which generally require expensive manually labeled image-query or patch-query pairs. To eliminate the heavy depen-dence on human annotations, we present a novel method, named Pseudo-Q, to automatically generate pseudo language queries for supervised training. Our method lever-ages an off-the-shelf object detector to identify visual ob-jects from unlabeled images, and then language queries for these objects are obtained in an unsupervised fashion with a pseudo-query generation module. Then, we design a task-related query prompt module to specifically tailor generated pseudo language queries for visual grounding tasks. Further, in order to fully capture the contextual re-lationships between images and language queries, we de-velop a visual-language model equipped with multi-level cross-modality attention mechanism. Extensive experimen-tal results demonstrate that our method has two notable benefits: (1) it can reduce human annotation costs signifi-cantly, e.g., 31% on Ref Coco [65] without degrading orig-inal model's performance under the fully supervised set-ting, and (2) without bells and whistles, it achieves supe-rior or comparable performance compared to state-of-the-art weakly-supervised visual grounding methods on all the five datasets we have experimented. Code is available at https://github.com/LeapLabTHU/Pseudo-Q." @default.
- W4225517085 created "2022-05-05" @default.
- W4225517085 creator A5013240918 @default.
- W4225517085 creator A5021497868 @default.
- W4225517085 creator A5022391546 @default.
- W4225517085 creator A5034603953 @default.
- W4225517085 creator A5091028140 @default.
- W4225517085 date "2022-06-01" @default.
- W4225517085 modified "2023-10-01" @default.
- W4225517085 title "Pseudo-Q: Generating Pseudo Language Queries for Visual Grounding" @default.
- W4225517085 cites W1773149199 @default.
- W4225517085 cites W1933349210 @default.
- W4225517085 cites W2100771357 @default.
- W4225517085 cites W2108598243 @default.
- W4225517085 cites W2194775991 @default.
- W4225517085 cites W2277195237 @default.
- W4225517085 cites W2565639579 @default.
- W4225517085 cites W2745461083 @default.
- W4225517085 cites W2798990097 @default.
- W4225517085 cites W2962764817 @default.
- W4225517085 cites W2963042258 @default.
- W4225517085 cites W2963109634 @default.
- W4225517085 cites W2963115613 @default.
- W4225517085 cites W2963445828 @default.
- W4225517085 cites W2963446712 @default.
- W4225517085 cites W2963465381 @default.
- W4225517085 cites W2963614783 @default.
- W4225517085 cites W2963735856 @default.
- W4225517085 cites W2963743213 @default.
- W4225517085 cites W2964022527 @default.
- W4225517085 cites W2964345792 @default.
- W4225517085 cites W2970231061 @default.
- W4225517085 cites W2981663434 @default.
- W4225517085 cites W2984121207 @default.
- W4225517085 cites W2984194315 @default.
- W4225517085 cites W2986803748 @default.
- W4225517085 cites W2987401211 @default.
- W4225517085 cites W2987734933 @default.
- W4225517085 cites W2989176720 @default.
- W4225517085 cites W3035248626 @default.
- W4225517085 cites W3126391825 @default.
- W4225517085 cites W3175773336 @default.
- W4225517085 cites W3178418424 @default.
- W4225517085 cites W3179041377 @default.
- W4225517085 cites W3211681816 @default.
- W4225517085 cites W4214490042 @default.
- W4225517085 cites W4214661601 @default.
- W4225517085 cites W4214746887 @default.
- W4225517085 cites W4214773477 @default.
- W4225517085 cites W4214893857 @default.
- W4225517085 cites W4226146163 @default.
- W4225517085 cites W4290714341 @default.
- W4225517085 doi "https://doi.org/10.1109/cvpr52688.2022.01507" @default.
- W4225517085 hasPublicationYear "2022" @default.
- W4225517085 type Work @default.
- W4225517085 citedByCount "7" @default.
- W4225517085 countsByYear W42255170852023 @default.
- W4225517085 crossrefType "proceedings-article" @default.
- W4225517085 hasAuthorship W4225517085A5013240918 @default.
- W4225517085 hasAuthorship W4225517085A5021497868 @default.
- W4225517085 hasAuthorship W4225517085A5022391546 @default.
- W4225517085 hasAuthorship W4225517085A5034603953 @default.
- W4225517085 hasAuthorship W4225517085A5091028140 @default.
- W4225517085 hasBestOaLocation W42255170852 @default.
- W4225517085 hasConcept C137293760 @default.
- W4225517085 hasConcept C153180895 @default.
- W4225517085 hasConcept C154945302 @default.
- W4225517085 hasConcept C162324750 @default.
- W4225517085 hasConcept C177264268 @default.
- W4225517085 hasConcept C187736073 @default.
- W4225517085 hasConcept C195324797 @default.
- W4225517085 hasConcept C199360897 @default.
- W4225517085 hasConcept C204321447 @default.
- W4225517085 hasConcept C2776151529 @default.
- W4225517085 hasConcept C2776321320 @default.
- W4225517085 hasConcept C2776760102 @default.
- W4225517085 hasConcept C2780451532 @default.
- W4225517085 hasConcept C2781238097 @default.
- W4225517085 hasConcept C41008148 @default.
- W4225517085 hasConcept C76155785 @default.
- W4225517085 hasConcept C94915269 @default.
- W4225517085 hasConceptScore W4225517085C137293760 @default.
- W4225517085 hasConceptScore W4225517085C153180895 @default.
- W4225517085 hasConceptScore W4225517085C154945302 @default.
- W4225517085 hasConceptScore W4225517085C162324750 @default.
- W4225517085 hasConceptScore W4225517085C177264268 @default.
- W4225517085 hasConceptScore W4225517085C187736073 @default.
- W4225517085 hasConceptScore W4225517085C195324797 @default.
- W4225517085 hasConceptScore W4225517085C199360897 @default.
- W4225517085 hasConceptScore W4225517085C204321447 @default.
- W4225517085 hasConceptScore W4225517085C2776151529 @default.
- W4225517085 hasConceptScore W4225517085C2776321320 @default.
- W4225517085 hasConceptScore W4225517085C2776760102 @default.
- W4225517085 hasConceptScore W4225517085C2780451532 @default.
- W4225517085 hasConceptScore W4225517085C2781238097 @default.
- W4225517085 hasConceptScore W4225517085C41008148 @default.
- W4225517085 hasConceptScore W4225517085C76155785 @default.
- W4225517085 hasConceptScore W4225517085C94915269 @default.
- W4225517085 hasFunder F4320321001 @default.
- W4225517085 hasFunder F4320329860 @default.