V2Dial : Unification of Video and Visual Dialog via Multimodal Experts

Adnen Abdessaied,   Anna Rohrbach,   Marcus Rohrbach,   Andreas Bulling

CVPR 2025, Nashville, TN, USA
[Paper]

---

Citation

If you find our code useful or use it in your own projects, please cite our paper:

@InProceedings{v2dial_abdessaied,
    author    = {Abdessaied, Adnen and Rohrbach, Anna and Rohrbach, Marcus and Bulling, Andreas},
    title     = {{V2Dial: Unification of Video and Visual Dialog via Multimodal Experts}},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    year      = {2025}
    }

Table of Contents

• Setup and Dependencies
• Download Data
• Training
• Response Generation
• Results
• Acknowledgements

Setup and Dependencies

Create a conda environment and install dependencies

   conda create -n v2dial python=3.9
   conda activate v2dial
   conda install pytorch==2.2.0 torchvision==0.17.0 torchaudio==2.2.0 pytorch-cuda=11.8 -c pytorch -c nvidia
   conda install -c huggingface transformers
   pip install evaluate wandb glog pyhocon

Download Data

❗ We do NOT own any of the data used in this projects. For legal reasons, we only provide links to where they could be downloaded.

Champagne

• Textual data can be accessed here
• The video url can be used to download the raw videos if needed. This can done using the folowing code

WebVid-2M

• Please follow the instructions/hints from this repo the download the dataset

CC3M

• Please follow these instructions to download the dataset

AVSD

• The textual data of the three versions can be downloaded from AVSD-DSTC7, AVSD-DSTC8 and AVSD-DSTC10, respectively
• The videos can be obtained from here

VisDial v1.0

• Both textual and image data can be obtained from here

After the data is downloaded, you need to set up their paths correctly in the config-files in \config

Training

We trained our model on 8 Nvidia A100 GPUs on all different stages.

Stage 1

Run

CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python main_stage_1.py \
   --mode train \
   --tag stage_1 \

Stage 2

Run

CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python main_stage_2.py \
   --mode train \
   --tag stage_2 \

Stage 3

Run

CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python main_stage_3.py \
   --mode train \
   --tag stage_3 \

Response Generation

AVSD-DSTC7

1. Set dstc=7 in the .conf file of your trained networks. in The default setting, can find this under logs/exeriment_tag/code/config/v2_dial_stage_x.conf
2. Generate the responses

./generate_parallel_avsd.sh v2dial/stage_x results_avsd_dstc7_v2dial_stage_x generate logs/stage_x/tag_to_be_used 7

3. All responses will be saved in output/dstc7/

AVSD-DSTC8

1. Set dstc=8 in the .conf file of your trained networks. in The default setting, can find this under logs/exeriment_tag/code/config/v2_dial_stage_x.conf
2. Generate the responses

./generate_parallel_avsd.sh v2dial/stage_x results_avsd_dstc8_v2dial_stage_x generate logs/stage_x/tag_to_be_used 8

3. All responses will be saved in output/dstc8/

AVSD-DSTC10

1. Set dstc=10 in the .conf file of your trained networks. in The default setting, can find this under logs/exeriment_tag/code/config/v2_dial_stage_x.conf
2. Generate the responses

./generate_parallel_avsd.sh v2dial/stage_x results_avsd_dstc10_v2dial_stage_x generate logs/stage_x/tag_to_be_used 10

3. All responses will be saved in output/dstc10/

VisDial

1. Generate the responses

./generate_parallel_visdial.sh v2dial/stage_x results_visdial_v2dial_stage_x generate logs/stage_x/tag_to_be_used

2. All responses will be saved in output/visdial/

Results

AVSD

To evaluate the results of AVSD, please use the tool Executing the eval_tool_dstc7 of AVSD-DSTC7 eval_tool_dstc and eval_tool_dstc10 on the generated reponses from the previous stage.

VisDial

Use the script eval_visdial.py for evaluation.

Acknowledgements

We thank the authors of miniGPT4-Video, VindLU, BLIP-2 for providing their codebases that greatly influenced this work.