├── .gitignore ├── .gitmodules ├── LICENSE ├── README.md ├── TextCentric ├── README.md ├── eval │ ├── config │ │ └── api_config.yaml │ └── src │ │ ├── config │ │ ├── __init__.py │ │ └── config_loader.py │ │ ├── evaluate_videos.py │ │ ├── evaluator │ │ ├── __init__.py │ │ ├── judges.py │ │ ├── metrics.py │ │ └── video_evaluator.py │ │ └── utils │ │ ├── __init__.py │ │ ├── audio_utils.py │ │ └── video_utils.py ├── infer │ └── request_videos.py └── scripts │ ├── eval.sh │ └── run.sh ├── assets ├── huggingface_paper_blue_aligned.svg ├── huggingface_paper_gold_week.svg └── main_picture.png ├── requirements.txt └── visual_puzzles ├── README.md ├── eval └── find_best_frame.py ├── example_data ├── color_grid │ ├── data.json │ ├── puzzles │ │ └── 00.png │ └── solutions │ │ └── 00.png ├── color_hexagon │ ├── data.json │ ├── puzzles │ │ └── 00.png │ └── solutions │ │ └── 00.png ├── color_overlap_squares │ ├── data.json │ ├── puzzles │ │ └── 00.png │ └── solutions │ │ └── 00.png ├── color_size │ ├── data.json │ ├── puzzles │ │ └── 00.png │ └── solutions │ │ └── 00.png ├── polygon_sides_color │ ├── data.json │ ├── puzzles │ │ └── 00.png │ └── solutions │ │ └── 00.png ├── rectangle_height_color │ ├── data.json │ ├── puzzles │ │ └── 00.png │ └── solutions │ │ └── 00.png ├── shape_reflect │ ├── data.json │ ├── puzzles │ │ └── 00.png │ └── solutions │ │ └── 00.png ├── shape_size_grid │ ├── data.json │ ├── puzzles │ │ └── 00.png │ └── solutions │ │ └── 00.png ├── size_cycle │ ├── data.json │ ├── puzzles │ │ └── 00.png │ └── solutions │ │ └── 00.png └── size_grid │ ├── data.json │ ├── puzzles │ └── 00.png │ └── solutions │ └── 00.png ├── fonts ├── OpenSans-Light.ttf ├── OpenSans-Medium.ttf └── OpenSans-Regular.ttf ├── gen_data └── data_generation.py ├── infer └── request_videos.py └── scripts ├── extract_best_frame.sh ├── generate_data.sh └── run.sh /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/.gitignore -------------------------------------------------------------------------------- /.gitmodules: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/.gitmodules -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/README.md -------------------------------------------------------------------------------- /TextCentric/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/TextCentric/README.md -------------------------------------------------------------------------------- /TextCentric/eval/config/api_config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/TextCentric/eval/config/api_config.yaml -------------------------------------------------------------------------------- /TextCentric/eval/src/config/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/TextCentric/eval/src/config/__init__.py -------------------------------------------------------------------------------- /TextCentric/eval/src/config/config_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/TextCentric/eval/src/config/config_loader.py -------------------------------------------------------------------------------- /TextCentric/eval/src/evaluate_videos.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/TextCentric/eval/src/evaluate_videos.py -------------------------------------------------------------------------------- /TextCentric/eval/src/evaluator/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/TextCentric/eval/src/evaluator/__init__.py -------------------------------------------------------------------------------- /TextCentric/eval/src/evaluator/judges.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/TextCentric/eval/src/evaluator/judges.py -------------------------------------------------------------------------------- /TextCentric/eval/src/evaluator/metrics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/TextCentric/eval/src/evaluator/metrics.py -------------------------------------------------------------------------------- /TextCentric/eval/src/evaluator/video_evaluator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/TextCentric/eval/src/evaluator/video_evaluator.py -------------------------------------------------------------------------------- /TextCentric/eval/src/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/TextCentric/eval/src/utils/__init__.py -------------------------------------------------------------------------------- /TextCentric/eval/src/utils/audio_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/TextCentric/eval/src/utils/audio_utils.py -------------------------------------------------------------------------------- /TextCentric/eval/src/utils/video_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/TextCentric/eval/src/utils/video_utils.py -------------------------------------------------------------------------------- /TextCentric/infer/request_videos.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/TextCentric/infer/request_videos.py -------------------------------------------------------------------------------- /TextCentric/scripts/eval.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/TextCentric/scripts/eval.sh -------------------------------------------------------------------------------- /TextCentric/scripts/run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/TextCentric/scripts/run.sh -------------------------------------------------------------------------------- /assets/huggingface_paper_blue_aligned.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/assets/huggingface_paper_blue_aligned.svg -------------------------------------------------------------------------------- /assets/huggingface_paper_gold_week.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/assets/huggingface_paper_gold_week.svg -------------------------------------------------------------------------------- /assets/main_picture.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/assets/main_picture.png -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/requirements.txt -------------------------------------------------------------------------------- /visual_puzzles/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/README.md -------------------------------------------------------------------------------- /visual_puzzles/eval/find_best_frame.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/eval/find_best_frame.py -------------------------------------------------------------------------------- /visual_puzzles/example_data/color_grid/data.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/example_data/color_grid/data.json -------------------------------------------------------------------------------- /visual_puzzles/example_data/color_grid/puzzles/00.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/example_data/color_grid/puzzles/00.png -------------------------------------------------------------------------------- /visual_puzzles/example_data/color_grid/solutions/00.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/example_data/color_grid/solutions/00.png -------------------------------------------------------------------------------- /visual_puzzles/example_data/color_hexagon/data.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/example_data/color_hexagon/data.json -------------------------------------------------------------------------------- /visual_puzzles/example_data/color_hexagon/puzzles/00.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/example_data/color_hexagon/puzzles/00.png -------------------------------------------------------------------------------- /visual_puzzles/example_data/color_hexagon/solutions/00.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/example_data/color_hexagon/solutions/00.png -------------------------------------------------------------------------------- /visual_puzzles/example_data/color_overlap_squares/data.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/example_data/color_overlap_squares/data.json -------------------------------------------------------------------------------- /visual_puzzles/example_data/color_overlap_squares/puzzles/00.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/example_data/color_overlap_squares/puzzles/00.png -------------------------------------------------------------------------------- /visual_puzzles/example_data/color_overlap_squares/solutions/00.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/example_data/color_overlap_squares/solutions/00.png -------------------------------------------------------------------------------- /visual_puzzles/example_data/color_size/data.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/example_data/color_size/data.json -------------------------------------------------------------------------------- /visual_puzzles/example_data/color_size/puzzles/00.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/example_data/color_size/puzzles/00.png -------------------------------------------------------------------------------- /visual_puzzles/example_data/color_size/solutions/00.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/example_data/color_size/solutions/00.png -------------------------------------------------------------------------------- /visual_puzzles/example_data/polygon_sides_color/data.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/example_data/polygon_sides_color/data.json -------------------------------------------------------------------------------- /visual_puzzles/example_data/polygon_sides_color/puzzles/00.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/example_data/polygon_sides_color/puzzles/00.png -------------------------------------------------------------------------------- /visual_puzzles/example_data/polygon_sides_color/solutions/00.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/example_data/polygon_sides_color/solutions/00.png -------------------------------------------------------------------------------- /visual_puzzles/example_data/rectangle_height_color/data.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/example_data/rectangle_height_color/data.json -------------------------------------------------------------------------------- /visual_puzzles/example_data/rectangle_height_color/puzzles/00.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/example_data/rectangle_height_color/puzzles/00.png -------------------------------------------------------------------------------- /visual_puzzles/example_data/rectangle_height_color/solutions/00.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/example_data/rectangle_height_color/solutions/00.png -------------------------------------------------------------------------------- /visual_puzzles/example_data/shape_reflect/data.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/example_data/shape_reflect/data.json -------------------------------------------------------------------------------- /visual_puzzles/example_data/shape_reflect/puzzles/00.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/example_data/shape_reflect/puzzles/00.png -------------------------------------------------------------------------------- /visual_puzzles/example_data/shape_reflect/solutions/00.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/example_data/shape_reflect/solutions/00.png -------------------------------------------------------------------------------- /visual_puzzles/example_data/shape_size_grid/data.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/example_data/shape_size_grid/data.json -------------------------------------------------------------------------------- /visual_puzzles/example_data/shape_size_grid/puzzles/00.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/example_data/shape_size_grid/puzzles/00.png -------------------------------------------------------------------------------- /visual_puzzles/example_data/shape_size_grid/solutions/00.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/example_data/shape_size_grid/solutions/00.png -------------------------------------------------------------------------------- /visual_puzzles/example_data/size_cycle/data.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/example_data/size_cycle/data.json -------------------------------------------------------------------------------- /visual_puzzles/example_data/size_cycle/puzzles/00.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/example_data/size_cycle/puzzles/00.png -------------------------------------------------------------------------------- /visual_puzzles/example_data/size_cycle/solutions/00.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/example_data/size_cycle/solutions/00.png -------------------------------------------------------------------------------- /visual_puzzles/example_data/size_grid/data.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/example_data/size_grid/data.json -------------------------------------------------------------------------------- /visual_puzzles/example_data/size_grid/puzzles/00.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/example_data/size_grid/puzzles/00.png -------------------------------------------------------------------------------- /visual_puzzles/example_data/size_grid/solutions/00.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/example_data/size_grid/solutions/00.png -------------------------------------------------------------------------------- /visual_puzzles/fonts/OpenSans-Light.ttf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/fonts/OpenSans-Light.ttf -------------------------------------------------------------------------------- /visual_puzzles/fonts/OpenSans-Medium.ttf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/fonts/OpenSans-Medium.ttf -------------------------------------------------------------------------------- /visual_puzzles/fonts/OpenSans-Regular.ttf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/fonts/OpenSans-Regular.ttf -------------------------------------------------------------------------------- /visual_puzzles/gen_data/data_generation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/gen_data/data_generation.py -------------------------------------------------------------------------------- /visual_puzzles/infer/request_videos.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/infer/request_videos.py -------------------------------------------------------------------------------- /visual_puzzles/scripts/extract_best_frame.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/scripts/extract_best_frame.sh -------------------------------------------------------------------------------- /visual_puzzles/scripts/generate_data.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/scripts/generate_data.sh -------------------------------------------------------------------------------- /visual_puzzles/scripts/run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tongjingqi/Thinking-with-Video/HEAD/visual_puzzles/scripts/run.sh --------------------------------------------------------------------------------