{"task":"Object Localization","dataset":"IllusionVQA","metric_names":["Accuracy"],"rows":[{"id":38546,"task":"Object Localization","parent_task":null,"dataset":"IllusionVQA","model_name":"GPT4-Vision 4-shot+CoT","metrics":{"Accuracy":"49.7"},"paper_url":"https://arxiv.org/abs/2403.15952v3","paper_title":"IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language Models","paper_date":"2024-03-23","code_links":[{"title":"csebuetnlp/illusionvqa","url":"https://github.com/csebuetnlp/illusionvqa"}],"metrics_order":"[\"Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":38547,"task":"Object Localization","parent_task":null,"dataset":"IllusionVQA","model_name":"GPT4-Vision 4-shot","metrics":{"Accuracy":"46"},"paper_url":"https://arxiv.org/abs/2403.15952v3","paper_title":"IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language Models","paper_date":"2024-03-23","code_links":[{"title":"csebuetnlp/illusionvqa","url":"https://github.com/csebuetnlp/illusionvqa"}],"metrics_order":"[\"Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":38548,"task":"Object Localization","parent_task":null,"dataset":"IllusionVQA","model_name":"Gemini-Pro","metrics":{"Accuracy":"43.5"},"paper_url":"https://arxiv.org/abs/2403.15952v3","paper_title":"IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language Models","paper_date":"2024-03-23","code_links":[{"title":"csebuetnlp/illusionvqa","url":"https://github.com/csebuetnlp/illusionvqa"}],"metrics_order":"[\"Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":38549,"task":"Object Localization","parent_task":null,"dataset":"IllusionVQA","model_name":"Gemini-Pro 4-shot","metrics":{"Accuracy":"41.8"},"paper_url":"https://arxiv.org/abs/2403.15952v3","paper_title":"IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language Models","paper_date":"2024-03-23","code_links":[{"title":"csebuetnlp/illusionvqa","url":"https://github.com/csebuetnlp/illusionvqa"}],"metrics_order":"[\"Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":38550,"task":"Object Localization","parent_task":null,"dataset":"IllusionVQA","model_name":"GPT4-Vision","metrics":{"Accuracy":"40"},"paper_url":"https://arxiv.org/abs/2403.15952v3","paper_title":"IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language Models","paper_date":"2024-03-23","code_links":[{"title":"csebuetnlp/illusionvqa","url":"https://github.com/csebuetnlp/illusionvqa"}],"metrics_order":"[\"Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":38551,"task":"Object Localization","parent_task":null,"dataset":"IllusionVQA","model_name":"Gemini-Pro 4-shot+CoT","metrics":{"Accuracy":"33.9"},"paper_url":"https://arxiv.org/abs/2403.15952v3","paper_title":"IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language Models","paper_date":"2024-03-23","code_links":[{"title":"csebuetnlp/illusionvqa","url":"https://github.com/csebuetnlp/illusionvqa"}],"metrics_order":"[\"Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":38552,"task":"Object Localization","parent_task":null,"dataset":"IllusionVQA","model_name":"CogVLM","metrics":{"Accuracy":"28"},"paper_url":"https://arxiv.org/abs/2403.15952v3","paper_title":"IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language Models","paper_date":"2024-03-23","code_links":[{"title":"csebuetnlp/illusionvqa","url":"https://github.com/csebuetnlp/illusionvqa"}],"metrics_order":"[\"Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":38553,"task":"Object Localization","parent_task":null,"dataset":"IllusionVQA","model_name":"LLaVA-1.5-13B","metrics":{"Accuracy":"24.8"},"paper_url":"https://arxiv.org/abs/2403.15952v3","paper_title":"IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language Models","paper_date":"2024-03-23","code_links":[{"title":"csebuetnlp/illusionvqa","url":"https://github.com/csebuetnlp/illusionvqa"}],"metrics_order":"[\"Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":38554,"task":"Object Localization","parent_task":null,"dataset":"IllusionVQA","model_name":"InstructBLIP-13B","metrics":{"Accuracy":"24.3"},"paper_url":"https://arxiv.org/abs/2403.15952v3","paper_title":"IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language Models","paper_date":"2024-03-23","code_links":[{"title":"csebuetnlp/illusionvqa","url":"https://github.com/csebuetnlp/illusionvqa"}],"metrics_order":"[\"Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}