Výsledky vyhledávání

Report

PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance

Autor: Liu, Ruyang, Tang, Haoran, Liu, Haibo, Ge, Yixiao, Shan, Ying, Li, Chen, Yang, Jiankun

The past year has witnessed the significant advancement of video-based large language models. However, the challenge of developing a unified model for both short and long video understanding remains unresolved. Most existing video LLMs cannot handle

Externí odkaz: http://arxiv.org/abs/2411.02327

Zobrazit plný text záznamu

Report

MUSE: Mamba is Efficient Multi-scale Learner for Text-video Retrieval

Autor: Tang, Haoran, Cao, Meng, Huang, Jinfa, Liu, Ruyang, Jin, Peng, Li, Ge, Liang, Xiaodan

Text-Video Retrieval (TVR) aims to align and associate relevant video content with corresponding natural language queries. Most existing TVR methods are based on large-scale pre-trained vision-language models (e.g., CLIP). However, due to the inheren

Externí odkaz: http://arxiv.org/abs/2408.10575

Zobrazit plný text záznamu

Report

RAP: Efficient Text-Video Retrieval with Sparse-and-Correlated Adapter

Autor: Cao, Meng, Tang, Haoran, Huang, Jinfa, Jin, Peng, Zhang, Can, Liu, Ruyang, Chen, Long, Liang, Xiaodan, Yuan, Li, Li, Ge

Text-Video Retrieval (TVR) aims to align relevant video content with natural language queries. To date, most state-of-the-art TVR methods learn image-to-video transfer learning based on large-scale pre-trained visionlanguage models (e.g., CLIP). Howe

Externí odkaz: http://arxiv.org/abs/2405.19465

Zobrazit plný text záznamu

Report

ST-LLM: Large Language Models Are Effective Temporal Learners

Autor: Liu, Ruyang, Li, Chen, Tang, Haoran, Ge, Yixiao, Shan, Ying, Li, Ge

Large Language Models (LLMs) have showcased impressive capabilities in text comprehension and generation, prompting research efforts towards video LLMs to facilitate human-AI interaction at the video level. However, how to effectively encode and unde

Externí odkaz: http://arxiv.org/abs/2404.00308

Zobrazit plný text záznamu

Report

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

Autor: Liu, Ruyang, Li, Chen, Ge, Yixiao, Shan, Ying, Li, Thomas H., Li, Ge

The recent progress in Large Language Models (LLM) has spurred various advancements in image-language conversation agents, while how to build a proficient video-based dialogue system is still under exploration. Considering the extensive scale of LLM

Externí odkaz: http://arxiv.org/abs/2309.15785

Zobrazit plný text záznamu

Report

Revisiting Temporal Modeling for CLIP-based Image-to-Video Knowledge Transferring

Autor: Liu, Ruyang, Huang, Jingjia, Li, Ge, Feng, Jiashi, Wu, Xinglong, Li, Thomas H.

Image-text pretrained models, e.g., CLIP, have shown impressive general multi-modal knowledge learned from large-scale image-text data pairs, thus attracting increasing attention for their potential to improve visual representation learning in the vi

Externí odkaz: http://arxiv.org/abs/2301.11116

Zobrazit plný text záznamu