Matches in SemOpenAlex for { <https://semopenalex.org/work/W4281725540> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4281725540 abstract "Unpaired Image Captioning (UIC) has been developed to learn image descriptions from unaligned vision-language sample pairs. Existing works usually tackle this task using adversarial learning and visual concept reward based on reinforcement learning. However, these existing works were only able to learn limited cross-domain information in vision and language domains, which restrains the captioning performance of UIC. Inspired by the success of Vision-Language Pre-Trained Models (VL-PTMs) in this research, we attempt to infer the cross-domain cue information about a given image from the large VL-PTMs for the UIC task. This research is also motivated by recent successes of prompt learning in many downstream multi-modal tasks, including image-text retrieval and vision question answering. In this work, a semantic prompt is introduced and aggregated with visual features for more accurate caption prediction under the adversarial learning framework. In addition, a metric prompt is designed to select high-quality pseudo image-caption samples obtained from the basic captioning model and refine the model in an iterative manner. Extensive experiments on the COCO and Flickr30K datasets validate the promising captioning ability of the proposed model. We expect that the proposed prompt-based UIC model will stimulate a new line of research for the VL-PTMs based captioning." @default.
- W4281725540 created "2022-06-13" @default.
- W4281725540 creator A5002277899 @default.
- W4281725540 creator A5015744133 @default.
- W4281725540 creator A5018629269 @default.
- W4281725540 creator A5032061966 @default.
- W4281725540 creator A5058010200 @default.
- W4281725540 creator A5082605318 @default.
- W4281725540 creator A5087628708 @default.
- W4281725540 date "2022-05-25" @default.
- W4281725540 modified "2023-09-28" @default.
- W4281725540 title "Prompt-based Learning for Unpaired Image Captioning" @default.
- W4281725540 doi "https://doi.org/10.48550/arxiv.2205.13125" @default.
- W4281725540 hasPublicationYear "2022" @default.
- W4281725540 type Work @default.
- W4281725540 citedByCount "0" @default.
- W4281725540 crossrefType "posted-content" @default.
- W4281725540 hasAuthorship W4281725540A5002277899 @default.
- W4281725540 hasAuthorship W4281725540A5015744133 @default.
- W4281725540 hasAuthorship W4281725540A5018629269 @default.
- W4281725540 hasAuthorship W4281725540A5032061966 @default.
- W4281725540 hasAuthorship W4281725540A5058010200 @default.
- W4281725540 hasAuthorship W4281725540A5082605318 @default.
- W4281725540 hasAuthorship W4281725540A5087628708 @default.
- W4281725540 hasBestOaLocation W42817255401 @default.
- W4281725540 hasConcept C115961682 @default.
- W4281725540 hasConcept C119857082 @default.
- W4281725540 hasConcept C134306372 @default.
- W4281725540 hasConcept C154945302 @default.
- W4281725540 hasConcept C157657479 @default.
- W4281725540 hasConcept C162324750 @default.
- W4281725540 hasConcept C176217482 @default.
- W4281725540 hasConcept C187736073 @default.
- W4281725540 hasConcept C204321447 @default.
- W4281725540 hasConcept C21547014 @default.
- W4281725540 hasConcept C23123220 @default.
- W4281725540 hasConcept C2780451532 @default.
- W4281725540 hasConcept C33923547 @default.
- W4281725540 hasConcept C36503486 @default.
- W4281725540 hasConcept C41008148 @default.
- W4281725540 hasConcept C44291984 @default.
- W4281725540 hasConcept C97541855 @default.
- W4281725540 hasConceptScore W4281725540C115961682 @default.
- W4281725540 hasConceptScore W4281725540C119857082 @default.
- W4281725540 hasConceptScore W4281725540C134306372 @default.
- W4281725540 hasConceptScore W4281725540C154945302 @default.
- W4281725540 hasConceptScore W4281725540C157657479 @default.
- W4281725540 hasConceptScore W4281725540C162324750 @default.
- W4281725540 hasConceptScore W4281725540C176217482 @default.
- W4281725540 hasConceptScore W4281725540C187736073 @default.
- W4281725540 hasConceptScore W4281725540C204321447 @default.
- W4281725540 hasConceptScore W4281725540C21547014 @default.
- W4281725540 hasConceptScore W4281725540C23123220 @default.
- W4281725540 hasConceptScore W4281725540C2780451532 @default.
- W4281725540 hasConceptScore W4281725540C33923547 @default.
- W4281725540 hasConceptScore W4281725540C36503486 @default.
- W4281725540 hasConceptScore W4281725540C41008148 @default.
- W4281725540 hasConceptScore W4281725540C44291984 @default.
- W4281725540 hasConceptScore W4281725540C97541855 @default.
- W4281725540 hasLocation W42817255401 @default.
- W4281725540 hasOpenAccess W4281725540 @default.
- W4281725540 hasPrimaryLocation W42817255401 @default.
- W4281725540 hasRelatedWork W2051167396 @default.
- W4281725540 hasRelatedWork W207304934 @default.
- W4281725540 hasRelatedWork W219090214 @default.
- W4281725540 hasRelatedWork W2295744208 @default.
- W4281725540 hasRelatedWork W2745461083 @default.
- W4281725540 hasRelatedWork W2767577934 @default.
- W4281725540 hasRelatedWork W2890653670 @default.
- W4281725540 hasRelatedWork W2951590222 @default.
- W4281725540 hasRelatedWork W2952322859 @default.
- W4281725540 hasRelatedWork W3209355071 @default.
- W4281725540 isParatext "false" @default.
- W4281725540 isRetracted "false" @default.
- W4281725540 workType "article" @default.