SOTAVerified

Zero-Shot Video Question Answer

This task present the results of Zeroshot Question Answer results on TGIF-QA dataset for LLM powered Video Conversational Models.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 26–50 of 85 papers

TitleStatusHype
LongVU: Spatiotemporal Adaptive Compression for Long Video-Language UnderstandingCode3
ViperGPT: Visual Inference via Python Execution for ReasoningCode3
SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language ModelsCode3
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language ModelsCode3
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextCode3
Video ReCap: Recursive Captioning of Hour-Long VideosCode3
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video UnderstandingCode2
VideoAgent: Long-form Video Understanding with Large Language Model as AgentCode2
Elysium: Exploring Object-level Perception in Videos via MLLMCode2
vid-TLDR: Training Free Token merging for Light-weight Video TransformerCode2
LinVT: Empower Your Image-level Large Language Model to Understand VideosCode2
LLaMA-VID: An Image is Worth 2 Tokens in Large Language ModelsCode2
VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long VideosCode2
MovieChat: From Dense Token to Sparse Memory for Long Video UnderstandingCode2
MVBench: A Comprehensive Multi-modal Video Understanding BenchmarkCode2
Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMsCode2
PPLLaVA: Varied Video Sequence Understanding With Prompt GuidanceCode2
An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLMCode2
TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video UnderstandingCode2
TimeSuite: Improving MLLMs for Long Video Understanding via Grounded TuningCode2
Understanding Long Videos with Multimodal Language ModelsCode2
Valley: Video Assistant with Large Language model Enhanced abilitYCode2
CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual ScenariosCode2
Language Repository for Long Video UnderstandingCode1
Shot2Story20K: A New Benchmark for Comprehensive Understanding of Multi-shot VideosCode1
Show:102550
← PrevPage 2 of 4Next →

No leaderboard results yet.