Papers with Code 아카이브

Zero-Shot Video Question Answer

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

하위 태스크: 0
평가표: 17
보존된 평가 기록: 239

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

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/IVGSZ/Flash-VStream

공식 코드

Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams

https://github.com/LLaVA-VL/LLaVA-NeXT

공식 코드

LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models

https://github.com/MILVLG/activitynet-qa

공식 코드

ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering

https://github.com/OpenBMB/MiniCPM-o

공식 코드

MiniCPM-V: A GPT-4V Level MLLM on Your Phone

https://github.com/PKU-YuanGroup/Video-LLaVA

공식 코드

Video-LLaVA: Learning United Visual Representation by Alignment Before Projection

https://github.com/TencentARC/ST-LLM

공식 코드

ST-LLM: Large Language Models Are Effective Temporal Learners

https://github.com/Vision-CAIR/LongVU

공식 코드

LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding

https://github.com/Vision-CAIR/MiniGPT4-video

공식 코드

MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens

https://github.com/Ziyang412/VideoTree

공식 코드

VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos

https://github.com/antoyang/FrozenBiLM

공식 코드

Zero-Shot Video Question Answering via Frozen Bidirectional Language Models

https://github.com/apple/ml-slowfast-llava

공식 코드

SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models

https://github.com/brown-palm/Vamos

공식 코드

Vamos: Versatile Action Models for Video Understanding

https://github.com/bytedance/Shot2Story

공식 코드

Shot2Story20K: A New Benchmark for Comprehensive Understanding of Multi-shot Videos

https://github.com/bytedance/tarsier

공식 코드

https://arxiv.org/abs/2407.00634

https://github.com/ceezh/llovi

공식 코드

A Simple LLM Framework for Long-Range Video Question-Answering

https://github.com/cvlab-columbia/viper

공식 코드

ViperGPT: Visual Inference via Python Execution for Reasoning

https://github.com/damo-nlp-sg/video-llama

공식 코드

Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding

https://github.com/damo-nlp-sg/videollama2

공식 코드

VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs

https://github.com/daromog/q-vid

공식 코드

Question-Instructed Visual Descriptions for Zero-Shot Video Question Answering

https://github.com/dvlab-research/llama-vid

공식 코드

LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models

https://github.com/efficient-large-model/vila

공식 코드

VILA: On Pre-training for Visual Language Models

https://github.com/egoschema/egoschema

공식 코드

EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding

https://github.com/engindeniz/vitis

공식 코드

Zero-Shot and Few-Shot Video Question Answering with Multi-Modal Prompts

https://github.com/evolvinglmms-lab/lmms-eval

공식 코드

LLaVA-OneVision: Easy Visual Task Transfer

https://github.com/evolvinglmms-lab/longva

공식 코드

Long Context Transfer from Language to Vision

https://github.com/fansunqi/akeys

공식 코드

Agentic Keyframe Search for Video Question Answering

https://github.com/farewellthree/BT-Adapter

공식 코드

BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning

https://github.com/farewellthree/ppllava

공식 코드

PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance

https://github.com/gls0425/linvt

공식 코드

LinVT: Empower Your Image-level Large Language Model to Understand Videos

https://github.com/google-research/scenic/tree/main/scenic/projects/verbs_in_action

공식 코드

Verbs in Action: Improving verb understanding in video-language models

https://github.com/hon-wong/elysium

공식 코드

Elysium: Exploring Object-level Perception in Videos via MLLM

https://github.com/ictnlp/llava-mini

공식 코드

LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token

https://github.com/idt-iti/vidctx

공식 코드

VidCtx: Context-aware Video Question Answering with Image Models

https://github.com/imagegridworth/IG-VLM

공식 코드

An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM

https://github.com/joez17/videoniah

공식 코드

Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMs

https://github.com/jongwoopark7978/LVNet

공식 코드

Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.