paper-with-me

Papers

Learning Video Context as Interleaved Multimodal Sequences

2024-07-31 · Kevin Qinghong Lin, Pengchuan Zhang, Difei Gao, Xide Xia, Joya Chen, Ziteng Gao, Jinheng Xie, Xuhong Xiao, Mike Zheng Shou

Narrative videos, such as movies, pose significant challenges in video understanding due to their rich contexts (characters, dialogues, storylines) and diverse demands (identify who, relationship, and reason). In this paper, we introduce MovieSeq, a multimodal language model developed to address the wide range of challenges in understanding video contexts. Our core idea is to represent videos as interleaved multimodal sequences (including images, plots, videos, and subtitles), either by linking external knowledge databases or using offline models (such as whisper for subtitles). Through instruction-tuning, this approach empowers the language model to interact with videos using interleaved multimodal instructions. For example, instead of solely relying on video as input, we jointly provide character photos alongside their names and dialogues, allowing the model to associate these elements and generate more comprehensive responses. To demonstrate its effectiveness, we validate MovieSeq's performance on six datasets (LVU, MAD, Movienet, CMD, TVC, MovieQA) across five settings (video classification, audio description, video-text retrieval, video captioning, and video question-answering). The code will be public at https://github.com/showlab/MovieSeq.

📄 PDF Abstract BibTeX arXiv:2407.21757

Code (1)

showlab/movieseq 공식 구현 pytorch

Tasks

Language ModelingLanguage ModellingQuestion AnsweringText RetrievalVideo CaptioningVideo ClassificationVideo Question AnsweringVideo-Text RetrievalVideo Understanding

Similar Papers 제목 키워드 기반

Emu: Generative Pretraining in Multimodality

2023-07-11 · Quan Sun, Qiying Yu, Yufeng Cui, Fan Zhang 외

We present Emu, a Transformer-based multimodal foundation model, which can seamlessly generate images and texts in multimodal context. This omnivore model can take in any single-modality or multimodal data input indiscri…

Image CaptioningImage GenerationImage to textQuestion Answering+7

DuoGen: Towards General Purpose Interleaved Multimodal Generation

2026-01-31 · Min Shi, Xiaohui Zeng, Jiannan Huang, Yin Cui 외 arxiv

Interleaved multimodal generation enables capabilities beyond unimodal generation models, such as step-by-step instructional guides, visual planning, and generating visual drafts for reasoning. However, the quality of ex…

multimodal generationVideo GenerationImage Editing

CoMM: A Coherent Interleaved Image-Text Dataset for Multimodal Understanding and Generation

2024-06-15 · CVPR 2025 1 · Wei Chen, Lin Li, Yongqi Yang, Bin Wen 외

Interleaved image-text generation has emerged as a crucial multimodal task, aiming at creating sequences of interleaved visual and textual content given a query. Despite notable advancements in recent multimodal large la…

In-Context LearningText GenerationVisual Storytelling

Illuminating Unified Multimodal Model for Free-form Interleaved Text-Image Generation

2026-06-29 · Chonghuinan Wang, Zhikai Chen, Chunwei Wang, Yecong Wan 외 arxiv

The advancement of generative AI models capable of producing text and image marks a critical step forward in the realm of multimodal intelligence, particularly for tasks involving the interleaving of both modalities. To …

Image GenerationStyle Transfer

Towards Text-Image Interleaved Retrieval

2025-02-18 · Xin Zhang, Ziqi Dai, Yongqi Li, Yanzhao Zhang 외

Current multimodal information retrieval studies mainly focus on single-image inputs, which limits real-world applications involving multiple images and text-image interleaved content. In this work, we introduce the text…

Information RetrievalLanguage ModelingLanguage ModellingLarge Language Model+3