HyperAIHyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAIHyperAI

Video Question Answering On Situated

Metrics

Average Accuracy

Results

Performance results of various models on this benchmark

Model Name
Average Accuracy
Paper TitleRepository
MIST51.13MIST: Multi-modal Iterative Spatial-Temporal Transformer for Long-form Video Question Answering-
TraveLER (0-shot)44.9TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answering-
SHG-VQA (trained from scratch)39.47Learning Situation Hyper-Graphs for Video Question Answering-
Flamingo-9B (4-shot)42.8Flamingo: a Visual Language Model for Few-Shot Learning-
SeViLA64.9Self-Chained Image-Language Model for Video Localization and Question Answering-
All-in-one47.5All in One: Exploring Unified Video-Language Pre-training-
GF(sup)53.94Glance and Focus: Memory Prompting for Multi-Event Video Question Answering-
VLAP (4 frames)67.1ViLA: Efficient Video-Language Alignment for Video Question Answering-
SeViLA (0-shot)44.6Self-Chained Image-Language Model for Video Localization and Question Answering-
Flamingo-80B (0-shot)39.7Flamingo: a Visual Language Model for Few-Shot Learning-
LLaMA-VQA65.4Large Language Models are Temporal and Causal Reasoners for Video Question Answering-
InternVideo58.7InternVideo: General Video Foundation Models via Generative and Discriminative Learning-
Flamingo-9B (0-shot)41.8Flamingo: a Visual Language Model for Few-Shot Learning-
Temp[ATP]48.37Revisiting the "Video" in Video-Language Understanding-
AnyMAL-70B (0-shot)48.2AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model-
Flamingo-80B (4-shot)42.4Flamingo: a Visual Language Model for Few-Shot Learning-
GF(uns)53.86Glance and Focus: Memory Prompting for Multi-Event Video Question Answering-
0 of 17 row(s) selected.
Video Question Answering On Situated | SOTA | HyperAI