MarineEVT: Advancing Event-Centric Marine Video Understanding via Visual Tool Reasoning

• URL: http://arxiv.org/abs/2607.24064v1
• Date: Mon, 27 Jul 2026 07:06:14 GMT
• Title: MarineEVT: Advancing Event-Centric Marine Video Understanding via Visual Tool Reasoning
• Abstract summary: We focus on marine video understanding, which requires substantial domain expertise and large-scale annotated video data.<n>To address these challenges, we carefully curate the first event-centric marine video understanding dataset called MarineEVT.<n>Based on MarineEVT, we decompose marine video understanding as an Event-centric Visual Tool-integrated Reasoning process EVT-R1.
• Score: 21.267648894621683
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent Vision-Language Models (VLMs) have achieved remarkable success in visual understanding, driven by the growing availability of high-quality image-text pairs. However, the performance of VLMs often degrades in the video domain due to the essential need for temporal understanding and the scarcity of large-scale annotated video data. In this work, we focus on marine video understanding, which brings further challenges: first, it requires substantial domain expertise; and video VLMs usually struggle with localizing and interpreting critical information from marine videos, as the informative events are typically sparse, unpredictable, and unevenly distributed. To address these challenges, we carefully curate the first event-centric marine video understanding dataset called MarineEVT, which features 20K multi-task, video-level visual question-answering pairs spanning multiple dimensions of marine understanding and analysis. Meanwhile, based on MarineEVT, we decompose marine video understanding as an Event-centric Visual Tool-integrated Reasoning process EVT-R1 for short, where we leverage powerful visual tools to drive the model to localize and interpret critical information aligned with visual questions and human intent. To demonstrate its effectiveness, we compare EVT-R1 against 11 SOTA VLMs in different settings. EVT-R1 outperforms the top open-source and top commercial models by 5.22 and 11.09, respectively. MarineEVT and EVT-R1 lay the foundation for ecological discovery and marine education, fostering the development of VLMs capable of interpreting marine dynamics, reasoning about ecological interactions, and supporting sustainable ocean video understanding and analysis.

Related papers

• TRANSPORTER: Transferring Visual Semantics from VLM Manifolds [56.749972238005604]
  This paper introduces a logits-to-video (L2V) task alongside a model-independent approach, TRANSPORTER, to generate videos.<n> TRANSPORTER learns an optimal transport coupling to VLM's high-semantic embedding spaces.<n>In turn, logit scores define embedding directions for conditional video generation.
  arXiv  Detail & Related papers  (2025-11-23T09:12:48Z)
• MVU-Eval: Towards Multi-Video Understanding Evaluation for Multimodal LLMs [61.70050081221131]
  MVU-Eval is the first comprehensive benchmark for evaluating Multi-Video Understanding for MLLMs.<n>Our MVU-Eval mainly assesses eight core competencies through 1,824 meticulously curated question-answer pairs spanning 4,959 videos.<n>These capabilities are rigorously aligned with real-world applications such as multi-sensor synthesis in autonomous systems and cross-angle sports analytics.
  arXiv  Detail & Related papers  (2025-11-10T16:02:33Z)
• Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models [78.32948112203228]
  Video understanding represents the most challenging frontier in computer vision.<n>Recent emergence of Video-Large Multitemporal Models has demonstrated remarkable capabilities in video understanding tasks.<n>Survey aims to provide researchers and practitioners with a unified framework for advancing Video-LMM capabilities.
  arXiv  Detail & Related papers  (2025-10-06T17:10:44Z)
• VLM-FO1: Bridging the Gap Between High-Level Reasoning and Fine-Grained Perception in VLMs [13.486495756813078]
  Vision-Language Models (VLMs) excel at high-level scene understanding but falter on fine-grained perception tasks requiring precise localization.<n>We introduce VLM-FO1, a novel framework that overcomes this limitation by reframing object-centric perception into a robust feature retrieval task.<n>Our method operates as a plug-and-play module that integrates with any pre-trained VLM.
  arXiv  Detail & Related papers  (2025-09-30T08:10:56Z)
• MSC: A Marine Wildlife Video Dataset with Grounded Segmentation and Clip-Level Captioning [16.858769096087297]
  Marine videos present significant challenges for video understanding.<n>Existing video captioning datasets often fail to generalize to the complexities of the marine environment.<n>We propose a two-stage marine object-oriented video captioning pipeline.
  arXiv  Detail & Related papers  (2025-08-06T15:34:24Z)
• Response Wide Shut? Surprising Observations in Basic Vision Language Model Capabilities [54.94982467313341]
  Vision-language Models (VLMs) have emerged as general-purpose tools for addressing a variety of complex computer vision problems.<n>We set out to understand the limitations of SoTA VLMs on fundamental visual tasks by constructing a series of tests that probe which components of design, specifically, may be lacking.
  arXiv  Detail & Related papers  (2025-07-10T15:26:41Z)
• UVLM: Benchmarking Video Language Model for Underwater World Understanding [11.475921633970977]
  We introduce UVLM, a benchmark for underwater video observation.<n> dataset includes 419 classes of marine animals, and various static plants and terrains.<n>Experiments on two representative VidLMs demonstrate that fine-tuning VidLMs on UVLM significantly improves underwater world understanding.
  arXiv  Detail & Related papers  (2025-07-03T07:08:38Z)
• Kwai Keye-VL Technical Report [80.53170317017147]
  We introduce textbfKwai Keye-VL, a multimodal foundation model for short-video understanding.<n>The development of Keye-VL rests on two core pillars: a massive, high-quality dataset with a strong emphasis on video, and an innovative training recipe.<n>To validate our approach, we conduct extensive evaluations, showing that Keye-VL achieves state-of-the-art results on public video benchmarks and remains highly competitive on general image-based tasks.
  arXiv  Detail & Related papers  (2025-07-02T17:57:28Z)
• SAMA: Towards Multi-Turn Referential Grounded Video Chat with Large Language Models [93.73583158211115]
  Achieving fine-grained-temporal understanding in videos remains a major challenge for current Video Large Multimodels (Video LMMs)<n>We contribute in three core aspects: dataset, model, and benchmark.<n>First, we introduce SAMA-239K, a large-scale dataset comprising 15K videos specifically to enable joint learning of video understanding, grounding, and multi-turn video chat.<n>Second, we propose the SAMA model, which incorporates a versatile-temporal context aggregator and a Segment Model to jointly enhance fine-grained video comprehension and precise grounding capabilities.
  arXiv  Detail & Related papers  (2025-05-24T18:13:16Z)
• AUTV: Creating Underwater Video Datasets with Pixel-wise Annotations [27.609227883183713]
  We propose AUTV, a framework for synthesizing marine video data with pixel-wise annotations.<n>We demonstrate the effectiveness of this framework by constructing two video datasets.
  arXiv  Detail & Related papers  (2025-03-17T05:18:20Z)
• MarineVRS: Marine Video Retrieval System with Explainability via Semantic Understanding [11.878077736295863]
  MarineVRS is a novel and flexible video retrieval system designed explicitly for the marine domain. MarineVRS integrates state-of-the-art methods for visual and linguistic object representation to enable efficient and accurate search and analysis of vast volumes of underwater video data. MarineVRS is a powerful tool for marine researchers and scientists to efficiently and accurately process vast amounts of data and gain deeper insights into the behavior and movements of marine species.
  arXiv  Detail & Related papers  (2023-06-07T16:46:44Z)

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.