constants.py

# this is .py for store constants 
MODEL_INFO = ["Model Type", "Model", "Language Model"]

TASK_INFO_v2 = ["Avg. All", "Avg. Video-Exclusive", "Avg. Prior-Knowledge QA", "Avg. Decision-Making",
                "ActivityNet", "MSVD", "MSRVTT", "TGIF", "Youcook2", "Ucfcrime", "MOT",
                "TVQA", "MV", "NBA",
                "Driving-exam", "Driving-decision-making", "SQA3D"]

AVG_INFO = ["Avg. All", "Avg. Video-Exclusive", "Avg. Prior-Knowledge QA", "Avg. Decision-Making"]
DATA_TITILE_TYPE = ["markdown", "markdown", "markdown", "markdown",
                    "number", "number", "number", "number", "number", "number", "number",
                    "number", "number", "number",
                    "number", "number", "number"]
CSV_DIR = "./file/result.csv"

# COLUMN_NAMES = MODEL_INFO + TASK_INFO
COLUMN_NAMES = MODEL_INFO + TASK_INFO_v2


LEADERBORAD_INTRODUCTION = """# Video-Bench Leaderboard
    
    Welcome to the leaderboard of the Video-Bench! 🏆 
    Video-Bench consists of 15K questions with human-like video for evaluating Video-LLMs, covering three-level and 13 evaluation dimensions including both the spatial and temporal understanding.
    Please refer to [our paper](https://arxiv.org/abs/2311.16103) for more details.
    """

SUBMIT_INTRODUCTION = """# Submit Introduction
    1. Obtain JSON file from our [github repository](https://github.com/AILab-CVC/SEED-Bench#leaderboard-submit) after evaluation. For example, you can obtain InstructBLIP's JSON file as results/results.json after running 
    ```shell
    python eval.py --model instruct_blip --anno_path SEED-Bench.json --output-dir results
    ```
    2. If you want to update model performance by uploading new results, please ensure 'Model Name Revision' is the same as what's shown in the leaderboard. For example, if you want to modify InstructBLIP's performance, you need to fill in 'InstructBLIP' in 'Revision Model Name'.
    3. Please provide the correct link of your model's repository for each submission.  
    4. For the evaluation dimension, you can choose "All/Image/Video", and the results of dimensions that are not evaluated will be set to zero.
    5. After clicking 'Submit Eval', you can click 'Refresh' to obtain the latest result in the leaderboard.

    ## Submit Example
    For example, if you want to upload InstructBLIP's result in the leaderboard, you need to:
    1. Fill in 'InstructBLIP' in 'Model Name' if it is your first time to submit your result (You can leave 'Revision Model Name' blank).
    2. Fill in 'InstructBLIP' in 'Revision Model Name' if you want to update your result (You can leave 'Model Name' blank).
    2. Select 'ImageLLM' in 'Model Type'.
    3. Fill in 'https://github.com/salesforce/LAVIS' in 'Model Link'.
    4. Select 'Flan-T5-XL' in 'LLM Type'.
    5. Select 'All' in 'Evaluation Dimension'.
    6. Upload results.json.
    7. Click the 'Submit Eval' button.
    8. Click 'Refresh' to obtain the uploaded leaderboard.
"""

TABLE_INTRODUCTION = """In the table below, we summarize each task performance of all the models.
        We use accurancy(%) as the primary evaluation metric for each tasks. 
    """

LEADERBORAD_INFO = """
      Based on powerful Large Language Models (LLMs), recent generative Multimodal Large Language Models (MLLMs) have gained prominence as a pivotal research area, exhibiting remarkable capability for both comprehension and generation. 
      In this work, we address the evaluation of generative comprehension in MLLMs as a preliminary step towards a comprehensive assessment of generative models, by introducing a benchmark named SEED-Bench. 
      SEED-Bench consists of 19K multiple choice questions with accurate human annotations (x6 larger than existing benchmarks), which spans 12 evaluation dimensions including the comprehension of both the image and video modality. 
      We develop an advanced pipeline for generating multiple-choice questions that target specific evaluation dimensions, integrating both automatic filtering and manual verification processes. 
      Multiple-choice questions with groundtruth options derived from human annotation enables an objective and efficient assessment of model performance, eliminating the need for human or GPT intervention during evaluation. 
      We further evaluate the performance of 18 models across all 12 dimensions, covering both the spatial and temporal understanding. 
      By revealing the limitations of existing MLLMs through evaluation results, we aim for SEED-Bench to provide insights for motivating future research.
"""



CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
CITATION_BUTTON_TEXT = r"""@misc{ning2023videobench,
      title={Video-Bench: A Comprehensive Benchmark and Toolkit for Evaluating Video-based Large Language Models}, 
      author={Munan Ning and Bin Zhu and Yujia Xie and Bin Lin and Jiaxi Cui and Lu Yuan and Dongdong Chen and Li Yuan},
      year={2023},
      eprint={2311.16103},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}
}"""