EventGPT: Event Stream Understanding with Multimodal Large Language Models

• URL: http://arxiv.org/abs/2412.00832v1
• Date: Sun, 01 Dec 2024 14:38:40 GMT
• Title: EventGPT: Event Stream Understanding with Multimodal Large Language Models
• Authors: Shaoyu Liu, Jianing Li, Guanghui Zhao, Yunjian Zhang, Xin Meng, Fei Richard Yu, Xiangyang Ji, Ming Li,
• Abstract summary: Event cameras record visual information as asynchronous pixel change streams, excelling at scene perception under unsatisfactory lighting or high-dynamic conditions. Existing multimodal large language models (MLLMs) concentrate on natural RGB images, failing in scenarios where event data fits better. We introduce EventGPT, the first MLLM for event stream understanding.
• Score: 59.65010502000344
• License:
• Abstract: Event cameras record visual information as asynchronous pixel change streams, excelling at scene perception under unsatisfactory lighting or high-dynamic conditions. Existing multimodal large language models (MLLMs) concentrate on natural RGB images, failing in scenarios where event data fits better. In this paper, we introduce EventGPT, the first MLLM for event stream understanding, to the best of our knowledge, marking a pioneering attempt to integrate large language models (LLMs) with event stream comprehension. To mitigate the huge domain gaps, we develop a three-stage optimization paradigm to gradually equip a pre-trained LLM with the capability of understanding event-based scenes. Our EventGPT comprises an event encoder, followed by a spatio-temporal aggregator, a linear projector, an event-language adapter, and an LLM. Firstly, RGB image-text pairs generated by GPT are leveraged to warm up the linear projector, referring to LLaVA, as the gap between natural image and language modalities is relatively smaller. Secondly, we construct a synthetic yet large dataset, N-ImageNet-Chat, consisting of event frames and corresponding texts to enable the use of the spatio-temporal aggregator and to train the event-language adapter, thereby aligning event features more closely with the language space. Finally, we gather an instruction dataset, Event-Chat, which contains extensive real-world data to fine-tune the entire model, further enhancing its generalization ability. We construct a comprehensive benchmark, and experiments show that EventGPT surpasses previous state-of-the-art MLLMs in generation quality, descriptive accuracy, and reasoning capability.

Related papers

• EventVL: Understand Event Streams via Multimodal Large Language Model [18.57504605615107]
  We propose EventVL, the first generative event-based MLLM framework for explicit semantic understanding. Specifically, to bridge the data gap for connecting different modalities semantics, we first annotate a large event-image/video-text dataset. To further promote a compact semantic space, Dynamic Semantic Alignment is introduced to improve and complete sparse semantic spaces of events.
  arXiv  Detail & Related papers  (2025-01-23T14:37:21Z)
• Grounding Partially-Defined Events in Multimodal Data [61.0063273919745]
  We introduce a multimodal formulation for partially-defined events and cast the extraction of these events as a three-stage span retrieval task. We propose a benchmark for this task, MultiVENT-G, that consists of 14.5 hours of densely annotated current event videos and 1,168 text documents, containing 22.8K labeled event-centric entities. Results illustrate the challenges that abstract event understanding poses and demonstrates promise in event-centric video-language systems.
  arXiv  Detail & Related papers  (2024-10-07T17:59:48Z)
• Generating Event-oriented Attribution for Movies via Two-Stage Prefix-Enhanced Multimodal LLM [47.786978666537436]
  We propose a Two-Stage Prefix-Enhanced MLLM (TSPE) approach for event attribution in movie videos. In the local stage, we introduce an interaction-aware prefix that guides the model to focus on the relevant multimodal information within a single clip. In the global stage, we strengthen the connections between associated events using an inferential knowledge graph.
  arXiv  Detail & Related papers  (2024-09-14T08:30:59Z)
• EvSign: Sign Language Recognition and Translation with Streaming Events [59.51655336911345]
  Event camera could naturally perceive dynamic hand movements, providing rich manual clues for sign language tasks. We propose efficient transformer-based framework for event-based SLR and SLT tasks. Our method performs favorably against existing state-of-the-art approaches with only 0.34% computational cost.
  arXiv  Detail & Related papers  (2024-07-17T14:16:35Z)
• GenEARL: A Training-Free Generative Framework for Multimodal Event Argument Role Labeling [89.07386210297373]
  GenEARL is a training-free generative framework that harnesses the power of modern generative models to understand event task descriptions. We show that GenEARL outperforms the contrastive pretraining (CLIP) baseline by 9.4% and 14.2% accuracy for zero-shot EARL on the M2E2 and SwiG datasets.
  arXiv  Detail & Related papers  (2024-04-07T00:28:13Z)
• EventBind: Learning a Unified Representation to Bind Them All for Event-based Open-world Understanding [7.797154022794006]
  EventBind is a novel framework that unleashes the potential of vision-language models (VLMs) for event-based recognition. We first introduce a novel event encoder that subtly models the temporal information from events. We then design a text encoder that generates content prompts and utilizes hybrid text prompts to enhance EventBind's generalization ability.
  arXiv  Detail & Related papers  (2023-08-06T15:05:42Z)
• CLIP-Event: Connecting Text and Images with Event Structures [123.31452120399827]
  We propose a contrastive learning framework to enforce vision-language pretraining models. We take advantage of text information extraction technologies to obtain event structural knowledge. Experiments show that our zero-shot CLIP-Event outperforms the state-of-the-art supervised model in argument extraction.
  arXiv  Detail & Related papers  (2022-01-13T17:03:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.