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 1–10 of 85 papers

TitleStatusHype
VideoMultiAgents: A Multi-Agent Framework for Video Question AnsweringCode1
Qwen2.5-Omni Technical ReportCode7
Agentic Keyframe Search for Video Question AnsweringCode1
VideoMind: A Chain-of-LoRA Agent for Long Video ReasoningCode3
BIMBA: Selective-Scan Compression for Long-Range Video Question AnsweringCode1
ENTER: Event Based Interpretable Reasoning for VideoQA—0
LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision TokenCode4
VidCtx: Context-aware Video Question Answering with Image ModelsCode0
LinVT: Empower Your Image-level Large Language Model to Understand VideosCode2
Video-RAG: Visually-aligned Retrieval-Augmented Long Video ComprehensionCode3
Show:102550
← PrevPage 1 of 9Next →

No leaderboard results yet.