https://github.com/HumanMLLM/LLaVA-Scissor
공식 코드LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs
Papers with Code 아카이브
Video Question Answering
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 28
- 보존된 평가 기록
- 254
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/IVGSZ/Flash-VStream
공식 코드Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams
https://github.com/InterDigitalInc/DialogSummary-VideoQA
공식 코드On the hidden treasure of dialog in video question answering
https://github.com/JiwanChung/long-story-short
공식 코드Long Story Short: a Summarize-then-Search Method for Long Video Question Answering
https://github.com/Jumperkables/tvqa_modality_bias
공식 코드https://github.com/JunweiLiang/FVTA_MemexQA
공식 코드https://github.com/Koukyosyumei/secure_ml
공식 코드Video in 10 Bits: Few-Bit VideoQA for Efficiency and Privacy
https://github.com/LLaVA-VL/LLaVA-NeXT
공식 코드LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models
https://github.com/MILVLG/activitynet-qa
공식 코드ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering
https://github.com/MILVLG/anetqa-code
공식 코드ANetQA: A Large-scale Benchmark for Fine-grained Compositional Reasoning over Untrimmed Videos
https://github.com/MM-IR/DualVGR-VideoQA
공식 코드DualVGR: A Dual-Visual Graph Reasoning Unit for Video Question Answering
https://github.com/MichiganNLP/video-fill-in-the-blank
공식 코드FIBER: Fill-in-the-Blanks as a Challenging Video Understanding Evaluation Framework
https://github.com/Mvrjustid/MHN-IJCAI22
공식 코드Multilevel Hierarchical Network with Multiscale Sampling for Video Question Answering
https://github.com/NVIDIA-AI-IOT/remembr
공식 코드ReMEmbR: Building and Reasoning Over Long-Horizon Spatio-Temporal Memory for Robot Navigation
https://github.com/OpenBMB/MiniCPM-o
공식 코드https://github.com/PKU-YuanGroup/Video-LLaVA
공식 코드Video-LLaVA: Learning United Visual Representation by Alignment Before Projection
https://github.com/PaddlePaddle/PaddleVideo/blob/develop/docs/en/model_zoo/multimodal/actbert.md
공식 코드https://github.com/SCZwangxiao/RTQ-MM2023
공식 코드RTQ: Rethinking Video-language Understanding Based on Image-text Model
https://github.com/SUTDCV/SUTD-TrafficQA
공식 코드https://github.com/SunDoge/L-GCN
공식 코드Location-aware Graph Convolutional Networks for Video Question Answering
https://github.com/TXH-mercury/VALOR
공식 코드VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset
https://github.com/TencentARC/ST-LLM
공식 코드ST-LLM: Large Language Models Are Effective Temporal Learners
https://github.com/VALUE-Leaderboard/StarterCode
공식 코드VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation
https://github.com/Vision-CAIR/LongVU
공식 코드LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
https://github.com/Vision-CAIR/MiniGPT4-video
공식 코드https://github.com/XingruiWang/SuperCLEVR-Physics
공식 코드Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question Answering
https://github.com/Yui010206/CREMA
공식 코드CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion
https://github.com/Yxxxb/VoCo-LLaMA
공식 코드VoCo-LLaMA: Towards Vision Compression with Large Language Models
https://github.com/ZJULearning/TreeAttention
공식 코드A Better Way to Attend: Attention with Trees for Video Question Answering
https://github.com/Ziyang412/VideoTree
공식 코드VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos
https://github.com/acolas1/TutorialVQAData
공식 코드https://github.com/adityavavre/videgovlm
공식 코드EgoVLM: Policy Optimization for Egocentric Video Understanding
https://github.com/ahjeongseo/MASN-pytorch
공식 코드Attend What You Need: Motion-Appearance Synergistic Networks for Video Question Answering
https://github.com/alanaai/evud
공식 코드AlanaVLM: A Multimodal Embodied AI Foundation Model for Egocentric Video Understanding
https://github.com/alibaba/AliceMind
공식 코드mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video
https://github.com/alpha-vllm/llama2-accessory
공식 코드SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.