paper-with-me

Papers

VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding

2024-03-18 · Yue Fan, Xiaojian Ma, Rujie Wu, Yuntao Du, Jiaqi Li, Zhi Gao, Qing Li

We explore how reconciling several foundation models (large language models and vision-language models) with a novel unified memory mechanism could tackle the challenging video understanding problem, especially capturing the long-term temporal relations in lengthy videos. In particular, the proposed multimodal agent VideoAgent: 1) constructs a structured memory to store both the generic temporal event descriptions and object-centric tracking states of the video; 2) given an input task query, it employs tools including video segment localization and object memory querying along with other visual foundation models to interactively solve the task, utilizing the zero-shot tool-use ability of LLMs. VideoAgent demonstrates impressive performances on several long-horizon video understanding benchmarks, an average increase of 6.6% on NExT-QA and 26.0% on EgoSchema over baselines, closing the gap between open-sourced models and private counterparts including Gemini 1.5 Pro.

📄 PDF Abstract BibTeX arXiv:2403.11481

Code (0)

등록된 구현이 없습니다.

Tasks

EgoSchemaVideo Understanding

Similar Papers 제목 키워드 기반

VideoAgent: Personalized Synthesis of Scientific Videos

2025-09-14 · Xiao Liang, Bangxin Li, Zixuan Chen, Hanyue Zheng 외 arxiv

The technical complexity of research papers often limits their reach, necessitating more accessible formats like scientific videos to disseminate key insights through engaging narration. However, existing automated metho…

VideoAgent: All-in-One Framework for Video Understanding and Editing

2026-06-22 · Hengji Zhou, Lingxuan Huang, Jian Wang, Bing Zhou 외 arxiv

Video editing has become essential in digital media creation, yet existing automated systems are restricted to short segment processing and domain-specific tasks. They face two critical limitations: i) inability to handl…

Cross-Modal Retrieval

Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding

2024-12-31 · Yue Fan, Xiaojian Ma, Rongpeng Su, Jun Guo 외

This paper investigates the problem of understanding dynamic 3D scenes from egocentric observations, a key challenge in robotics and embodied AI. Unlike prior studies that explored this as long-form video understanding a…

Robot ManipulationScene UnderstandingVideo Understanding

VideoAgent: Self-Improving Video Generation

2024-10-14 · Achint Soni, Sreyas Venkataraman, Abhranil Chandra, Sebastian Fischmeister 외

Video generation has been used to generate visual plans for controlling robotic systems. Given an image observation and a language instruction, previous work has generated video plans which are then converted to robot co…

HallucinationVideo Generation

LongVideoAgent: Multi-Agent Reasoning with Long Videos

2025-12-23 · Runtao Liu, Ziyi Liu, Jiaqi Tang, Yue Ma 외 arxiv

Recent advances in multimodal LLMs and systems that use tools for long-video QA point to the promise of reasoning over hour-long episodes. However, many methods still compress content into lossy summaries or rely on limi…

Reinforcement Learning