{ "denseCaptionsResult": { "values": [ { "text": "a man pointing at a screen", "confidence": 0.7767596244812012, "boundingBox": { "x": 0, "y": 0, "w": 1038, "h": 692 } }, { "text": "a screen shot of a computer", "confidence": 0.7601339221000671, "boundingBox": { "x": 62, "y": 51, "w": 673, "h": 437 } }, { "text": "a man pointing at a screen", "confidence": 0.7736578583717346, "boundingBox": { "x": 646, "y": 63, "w": 269, "h": 605 } }, { "text": "a close up of a table", "confidence": 0.7479931712150574, "boundingBox": { "x": 0, "y": 536, "w": 1021, "h": 146 } }, { "text": "a close up of a man's head", "confidence": 0.8116378784179688, "boundingBox": { "x": 782, "y": 77, "w": 116, "h": 103 } }, { "text": "a person's back pocket", "confidence": 0.7274041771888733, "boundingBox": { "x": 753, "y": 538, "w": 140, "h": 135 } }, { "text": "a close up of a plant", "confidence": 0.7625939846038818, "boundingBox": { "x": 0, "y": 10, "w": 86, "h": 507 } }, { "text": "a man pointing at a screen", "confidence": 0.7956112623214722, "boundingBox": { "x": 9, "y": 15, "w": 973, "h": 651 } }, { "text": "a person in a yellow coat", "confidence": 0.6707674860954285, "boundingBox": { "x": 687, "y": 199, "w": 225, "h": 356 } }, { "text": "a screenshot of a phone", "confidence": 0.7743726372718811, "boundingBox": { "x": 0, "y": 0, "w": 214, "h": 541 } } ] }, "modelVersion": "2023-02-01-preview", "metadata": { "width": 1038, "height": 692 } }