Official code for "V2Dial: Unification of Video and Visual Dialog via Multimodal Experts" published at CVPR'25
Find a file
2025-06-24 08:38:09 +02:00
data initial commit 2025-06-24 08:38:09 +02:00
datasets initial commit 2025-06-24 08:38:09 +02:00
emergency initial commit 2025-06-24 08:38:09 +02:00
models initial commit 2025-06-24 08:38:09 +02:00
processors initial commit 2025-06-24 08:38:09 +02:00
tasks initial commit 2025-06-24 08:38:09 +02:00
tokenizers initial commit 2025-06-24 08:38:09 +02:00
utils initial commit 2025-06-24 08:38:09 +02:00
eval_visdial.py initial commit 2025-06-24 08:38:09 +02:00
eval_visdial_sentence_embeddings.py initial commit 2025-06-24 08:38:09 +02:00
generate_parallel_avsd.sh initial commit 2025-06-24 08:38:09 +02:00
generate_parallel_nextqa.sh initial commit 2025-06-24 08:38:09 +02:00
generate_parallel_visdial.sh initial commit 2025-06-24 08:38:09 +02:00
main_stage_1.py initial commit 2025-06-24 08:38:09 +02:00
main_stage_2.py initial commit 2025-06-24 08:38:09 +02:00
main_stage_3.py initial commit 2025-06-24 08:38:09 +02:00
merge_pred_avsd.py initial commit 2025-06-24 08:38:09 +02:00
merge_pred_nextqa.py initial commit 2025-06-24 08:38:09 +02:00