Litcius/Paper detail

UnMA-CapSumT: Unified and Multi-Head attention-driven caption summarization transformer

Dhruv Sharma, Chhavi Dhiman, Dinesh Kumar

2025Journal of Visual Communication and Image Representation8 citationsDOI

Topics & Concepts

Computer scienceTransformerAutomatic summarizationStylized factEmbeddingWord embeddingNatural language processingArtificial intelligenceLanguage modelNatural languageRobustness (evolution)Natural language understandingRepetition (rhetorical device)Question answeringSpeech recognitionWord (group theory)Source codeCode (set theory)Multimodal Machine Learning ApplicationsNatural Language Processing TechniquesVideo Analysis and Summarization
UnMA-CapSumT: Unified and Multi-Head attention-driven caption summarization transformer | Litcius