Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288043238> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W4288043238 abstract "We introduce a zero-shot video captioning method that employs two frozen networks: the GPT-2 language model and the CLIP image-text matching model. The matching score is used to steer the language model toward generating a sentence that has a high average matching score to a subset of the video frames. Unlike zero-shot image captioning methods, our work considers the entire sentence at once. This is achieved by optimizing, during the generation process, part of the prompt from scratch, by modifying the representation of all other tokens in the prompt, and by repeating the process iteratively, gradually improving the specificity and comprehensiveness of the generated sentence. Our experiments show that the generated captions are coherent and display a broad range of real-world knowledge. Our code is available at: https://github.com/YoadTew/zero-shot-video-to-text" @default.
- W4288043238 created "2022-07-27" @default.
- W4288043238 creator A5020220135 @default.
- W4288043238 creator A5039215377 @default.
- W4288043238 creator A5074649648 @default.
- W4288043238 creator A5078102229 @default.
- W4288043238 creator A5082617813 @default.
- W4288043238 date "2022-07-22" @default.
- W4288043238 modified "2023-09-24" @default.
- W4288043238 title "Zero-Shot Video Captioning with Evolving Pseudo-Tokens" @default.
- W4288043238 doi "https://doi.org/10.48550/arxiv.2207.11100" @default.
- W4288043238 hasPublicationYear "2022" @default.
- W4288043238 type Work @default.
- W4288043238 citedByCount "0" @default.
- W4288043238 crossrefType "posted-content" @default.
- W4288043238 hasAuthorship W4288043238A5020220135 @default.
- W4288043238 hasAuthorship W4288043238A5039215377 @default.
- W4288043238 hasAuthorship W4288043238A5074649648 @default.
- W4288043238 hasAuthorship W4288043238A5078102229 @default.
- W4288043238 hasAuthorship W4288043238A5082617813 @default.
- W4288043238 hasBestOaLocation W42880432381 @default.
- W4288043238 hasConcept C105795698 @default.
- W4288043238 hasConcept C115961682 @default.
- W4288043238 hasConcept C138885662 @default.
- W4288043238 hasConcept C154945302 @default.
- W4288043238 hasConcept C157657479 @default.
- W4288043238 hasConcept C159985019 @default.
- W4288043238 hasConcept C165064840 @default.
- W4288043238 hasConcept C177264268 @default.
- W4288043238 hasConcept C17744445 @default.
- W4288043238 hasConcept C178790620 @default.
- W4288043238 hasConcept C185592680 @default.
- W4288043238 hasConcept C192562407 @default.
- W4288043238 hasConcept C199360897 @default.
- W4288043238 hasConcept C199539241 @default.
- W4288043238 hasConcept C204321447 @default.
- W4288043238 hasConcept C204323151 @default.
- W4288043238 hasConcept C2776359362 @default.
- W4288043238 hasConcept C2776760102 @default.
- W4288043238 hasConcept C2777530160 @default.
- W4288043238 hasConcept C2778344882 @default.
- W4288043238 hasConcept C2780813799 @default.
- W4288043238 hasConcept C2781235140 @default.
- W4288043238 hasConcept C28490314 @default.
- W4288043238 hasConcept C33923547 @default.
- W4288043238 hasConcept C41008148 @default.
- W4288043238 hasConcept C41895202 @default.
- W4288043238 hasConcept C94625758 @default.
- W4288043238 hasConcept C98045186 @default.
- W4288043238 hasConceptScore W4288043238C105795698 @default.
- W4288043238 hasConceptScore W4288043238C115961682 @default.
- W4288043238 hasConceptScore W4288043238C138885662 @default.
- W4288043238 hasConceptScore W4288043238C154945302 @default.
- W4288043238 hasConceptScore W4288043238C157657479 @default.
- W4288043238 hasConceptScore W4288043238C159985019 @default.
- W4288043238 hasConceptScore W4288043238C165064840 @default.
- W4288043238 hasConceptScore W4288043238C177264268 @default.
- W4288043238 hasConceptScore W4288043238C17744445 @default.
- W4288043238 hasConceptScore W4288043238C178790620 @default.
- W4288043238 hasConceptScore W4288043238C185592680 @default.
- W4288043238 hasConceptScore W4288043238C192562407 @default.
- W4288043238 hasConceptScore W4288043238C199360897 @default.
- W4288043238 hasConceptScore W4288043238C199539241 @default.
- W4288043238 hasConceptScore W4288043238C204321447 @default.
- W4288043238 hasConceptScore W4288043238C204323151 @default.
- W4288043238 hasConceptScore W4288043238C2776359362 @default.
- W4288043238 hasConceptScore W4288043238C2776760102 @default.
- W4288043238 hasConceptScore W4288043238C2777530160 @default.
- W4288043238 hasConceptScore W4288043238C2778344882 @default.
- W4288043238 hasConceptScore W4288043238C2780813799 @default.
- W4288043238 hasConceptScore W4288043238C2781235140 @default.
- W4288043238 hasConceptScore W4288043238C28490314 @default.
- W4288043238 hasConceptScore W4288043238C33923547 @default.
- W4288043238 hasConceptScore W4288043238C41008148 @default.
- W4288043238 hasConceptScore W4288043238C41895202 @default.
- W4288043238 hasConceptScore W4288043238C94625758 @default.
- W4288043238 hasConceptScore W4288043238C98045186 @default.
- W4288043238 hasLocation W42880432381 @default.
- W4288043238 hasOpenAccess W4288043238 @default.
- W4288043238 hasPrimaryLocation W42880432381 @default.
- W4288043238 hasRelatedWork W10582454 @default.
- W4288043238 hasRelatedWork W10934236 @default.
- W4288043238 hasRelatedWork W1266808 @default.
- W4288043238 hasRelatedWork W12873135 @default.
- W4288043238 hasRelatedWork W1453065 @default.
- W4288043238 hasRelatedWork W2061806 @default.
- W4288043238 hasRelatedWork W3115526 @default.
- W4288043238 hasRelatedWork W4325123 @default.
- W4288043238 hasRelatedWork W4867410 @default.
- W4288043238 hasRelatedWork W878239 @default.
- W4288043238 isParatext "false" @default.
- W4288043238 isRetracted "false" @default.
- W4288043238 workType "article" @default.