HyperAI
الرئيسيةالأخبارأحدث الأوراق البحثيةالدروسمجموعات البياناتالموسوعةSOTAنماذج LLMلوحة الأداء GPUالفعاليات
البحث
حول
HyperAI

Zeroshot Video Question Answer On Tgif Qa

المقاييس

Accuracy
Confidence Score

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

اسم النموذج
Accuracy
Confidence Score
Paper TitleRepository
Elysium66.63.6Elysium: Exploring Object-level Perception in Videos via MLLM
MiniGPT4-video-7B72.22-MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens
TS-LLaVA-34B81.04.2TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models
Video Chat-7B34.42.3VideoChat: Chat-Centric Video Understanding
SlowFast-LLaVA-34B80.64.3SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models
Video-LLaVA-7B70.04.0Video-LLaVA: Learning United Visual Representation by Alignment Before Projection
VideoGPT+74.64.1VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding
LinVT-Qwen2-VL (7B)81.34.3LinVT: Empower Your Image-level Large Language Model to Understand Videos
IG-VLM79.14.2An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM
Video-ChatGPT-7B51.43.0Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models
PLLaVA80.64.3PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning
Chat-UniVi-7B69.03.8Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding
FrozenBiLM41.9-Zero-Shot Video Question Answering via Frozen Bidirectional Language Models
Tarsier (34B)82.54.4Tarsier: Recipes for Training and Evaluating Large Video Description Models
0 of 14 row(s) selected.