VLM

VideoPrism: A Foundational Visual Encoder for Video Understanding

jinuklee 2024. 9. 30. 15:35

https://arxiv.org/pdf/2402.13217

'VLM' 카테고리의 다른 글

VideoLLaMA 2Advancing Spatial-Temporal Modeling and AudioUnderstanding in Video-LLM  (0) 2024.09.30
INTERNVIDEO2: SCALING FOUNDATION MODELS FORMULTIMODAL VIDEO UNDERSTANDING 논문리뷰  (0) 2024.09.30
Qwen2-VL: Enhancing Vision-Language Model’s Perceptionof the World at Any Resolution  (0) 2024.09.21
An interactive agent foundation model 논문리뷰  (0) 2024.09.14

'VLM'의 다른글

  • 현재글VideoPrism: A Foundational Visual Encoder for Video Understanding

관련글

티스토리툴바