MST-MIXER/raw_data/test_set4DSTC10-AVSD.json

1 line
1.8 MiB
JSON
Raw Normal View History

2024-07-08 11:41:28 +02:00
{"type": "scene_aware_dialog", "version": "0.1", "dialogs": [{"image_id": "CGRUM", "dialog": [{"question": "it is a man or a woman ?", "answer": "it is a man on the bed"}, {"question": "is he the only one in the video ?", "answer": "yes , he is the only one in the video"}, {"question": "where is he ?", "answer": "laying in his bedroom , on the bed , eating chips and watching tv he does this the whole time"}, {"question": "does he make any noise ?", "answer": "i hear no audio , but munching and the bag crunching"}, {"question": "is he smiling or laughing ?", "answer": "only i can see is him filling his mouth ."}, {"question": "does he do anything else besides lay in bed , eating chips and watching tv ?", "answer": "no all he does is lay there"}, {"question": "can you tell what time of day it is ?", "answer": "no , it is very dark in there"}, {"question": "can you see what he is watching ?", "answer": "__UNDISCLOSED__", "reason": [{"timestamp": [0.0, 23.744], "sentence": "he is in is house"}]}]}, {"image_id": "M8TPH", "dialog": [{"question": "please describe for me in detail what actions occur in the first half of the video ?", "answer": "a guy is sitting in front of the computer , eating on something ."}, {"question": "please describe for me in detail what actions occur in the last half of the video ?", "answer": "he sits in front of the comouter bites a peice of his food"}, {"question": "can you tell what the man is doing on the computer ?", "answer": "he is only looking at the computer screen"}, {"question": "can you tell what the man is eating ?", "answer": "it looks like a peice of bread or a sandwich too dark to tell"}, {"question": "does the man show any emotion in what he is doing ( happy , angry , ect ) ?", "answer": "no he shows no emotions at all just eating and loooking at the screen"}, {"question": "is there anyone else present besides the man ?", "answer": "no no one else , he is alone"}, {"question": "does it appear to be daytime or nighttime ?", "answer": "it appears to be daylight outside , the blinds are closed ."}, {"question": "what color is the walls in the room ?", "answer": "looks either beige or off white room is a little dark"}, {"question": "is the fan turned on or off ?", "answer": "__UNDISCLOSED__", "reason": [{"timestamp": [1.526347, 3.101843], "sentence": "the fan is turned off ."}]}]}, {"image_id": "XGF95", "dialog": [{"question": "how many people in the video ?", "answer": "there are two people in the video ."}, {"question": "what happens first ?", "answer": "the woman holds a book , opens it and looks at it , and begins talking to the man beside her ."}, {"question": "what does the man do ?", "answer": "the man is holding a remote control and is talking to the woman who is holding the book ."}, {"question": "what else is happening ?", "answer": "they 're both sitting in chairs next to each other and are laughing ."}, {"question": "is there anything else i need to know ?", "answer": "there is not anything else you should need to know ."}, {"question": "are there any pets in the video ?", "answer": "there are no pets in the video ."}, {"question": "so does this sounds right : a woman holds a book as she sits next to a man . she talks to a man that is holding a remote and sitting next to her ?", "answer": "__UNDISCLOSED__", "reason": [{"timestamp": [2.171, 27.04047], "sentence": "the man and women are talking ."}, {"timestamp": [27.468497, 32.024], "sentence": "the man and women are laughing ."}]}]}, {"image_id": "N6VAV", "dialog": [{"question": "what does the man do in the video ?", "answer": "he opens the tap and gets the towel"}, {"question": "what objects does he interact with ?", "answer": "he interacts with a towel and tap"}, {"question": "what does he do with the towel ?", "answer": "he wipes his hands with it"}, {"question": "what does he do with it after that ?", "answer": "he hangs it back up"}, {"question": "he only opens the tap right ?", "answer": "he opens , and then closes it"}, {"question": "what else does he do in the video ?", "answer": "he does only that and goes away"}, {"