Noa Garcia

Latest

• Model-agnostic gender debiased image captioning
• Not only generative art: Stable diffusion for content-style disentanglement in art analysis
• Uncurated image-text datasets: Shedding light on demographic bias
• CARE-MI: Chinese benchmark for misinformation evaluation in maternity and infant care
• Gender and Racial Bias in Visual Question Answering Datasets
• Quantifying Societal Bias Amplification in Image Captioning
• The semantic typology of visually grounded paraphrases
• GCNBoost: Artwork Classificationby Label Propagation Through a Knowledge Graph
• Transferring domain-agnostic knowledge in video question answering
• Explain me the painting: Multi-topic knowledgeable art description generation
• Attending self-attention: A case study of visually grounded supervision in vision-and-language transformers
• A comparative study of language Transformers for video question answering
• The laughing machine: Predicting humor in video
• Cross-lingual visual grounding
• Demographic influences on contemporary art with unsupervised style embeddings
• Knowledge-based video question answering with unsupervised scene descriptions
• KnowIT VQA: Answering knowledge-based questions about videos
• BERT representations for video question answering
• ContextNet: representation and exploration for painting classification and retrieval in context
• Context-aware embeddings for automatic art analysis
• Video meets knowledge in visual question answering