https://github.com/TencentARC/ST-LLM
공식 코드ST-LLM: Large Language Models Are Effective Temporal Learners
Papers with Code 아카이브
Video-based Generative Performance Benchmarking (Temporal Understanding)
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 1
- 보존된 평가 기록
- 18
The benchmark evaluates a generative Video Conversational Model with respect to Temporal Understanding.
We curate a test set based on the ActivityNet-200 dataset, featuring videos with rich, dense descriptive captions and associated question-answer pairs from human annotations. We develop an evaluation pipeline using the GPT-3.5 model that assigns a relative score to the generated predictions on a scale of 1-5.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/Vision-CAIR/MiniGPT4-video
공식 코드https://github.com/apple/ml-slowfast-llava
공식 코드SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models
https://github.com/damo-nlp-sg/video-llama
공식 코드Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding
https://github.com/farewellthree/BT-Adapter
공식 코드BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning
https://github.com/farewellthree/ppllava
공식 코드PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance
https://github.com/huangb23/vtimellm
공식 코드https://github.com/magic-research/PLLaVA
공식 코드PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning
https://github.com/mbzuai-oryx/video-chatgpt
공식 코드Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models
https://github.com/mbzuai-oryx/videogpt-plus
공식 코드VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding
https://github.com/opengvlab/ask-anything
공식 코드https://github.com/pku-yuangroup/chat-univi
공식 코드https://github.com/rese1f/MovieChat
공식 코드MovieChat: From Dense Token to Sparse Memory for Long Video Understanding
https://github.com/tingyu215/ts-llava
공식 코드https://github.com/zrrskywalker/llama-adapter
공식 코드LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model
https://github.com/Mind23-2/MindCode-140
LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model
https://github.com/bytedance/tarsier
MVBench: A Comprehensive Multi-modal Video Understanding Benchmark
https://github.com/damo-nlp-sg/videollama2
Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding
https://github.com/damo-nlp-sg/videollama3
Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding
https://github.com/opengvlab/llama-adapter
LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model
https://github.com/pku-yuangroup/video-bench
https://github.com/pwc-1/Paper-9/tree/main/2/minigpt4
https://github.com/qiujihao19/artemis
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models
https://github.com/skyworkai/moe-plus-plus
https://github.com/skyworkai/moh
https://github.com/xinding-sys/StreamMind
Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.