MINERVA: Evaluating Complex Video Reasoning

• URL: http://arxiv.org/abs/2505.00681v1
• Date: Thu, 01 May 2025 17:41:49 GMT
• Title: MINERVA: Evaluating Complex Video Reasoning
• Authors: Arsha Nagrani, Sachit Menon, Ahmet Iscen, Shyamal Buch, Ramin Mehran, Nilpa Jha, Anja Hauth, Yukun Zhu, Carl Vondrick, Mikhail Sirotenko, Cordelia Schmid, Tobias Weyand,
• Abstract summary: We provide a new video reasoning dataset called MINERVA for modern multimodal models.<n>Our dataset is multimodal, diverse in terms of video domain and length, and consists of complex multi-step questions.<n>We perform fine-grained error analysis to identify common failure modes across various models, and create a taxonomy of reasoning errors.
• Score: 72.12644008002566
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal LLMs are turning their focus to video benchmarks, however most video benchmarks only provide outcome supervision, with no intermediate or interpretable reasoning steps. This makes it challenging to assess if models are truly able to combine perceptual and temporal information to reason about videos, or simply get the correct answer by chance or by exploiting linguistic biases. To remedy this, we provide a new video reasoning dataset called MINERVA for modern multimodal models. Each question in the dataset comes with 5 answer choices, as well as detailed, hand-crafted reasoning traces. Our dataset is multimodal, diverse in terms of video domain and length, and consists of complex multi-step questions. Extensive benchmarking shows that our dataset provides a challenge for frontier open-source and proprietary models. We perform fine-grained error analysis to identify common failure modes across various models, and create a taxonomy of reasoning errors. We use this to explore both human and LLM-as-a-judge methods for scoring video reasoning traces, and find that failure modes are primarily related to temporal localization, followed by visual perception errors, as opposed to logical or completeness errors. The dataset, along with questions, answer candidates and reasoning traces will be publicly available under https://github.com/google-deepmind/neptune?tab=readme-ov-file\#minerva.

Related papers

• TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models [75.42002690128486]
  TemporalBench is a new benchmark dedicated to evaluating fine-grained temporal understanding in videos. It consists of 10K video question-answer pairs, derived from 2K high-quality human annotations detailing the temporal dynamics in video clips. Results show that state-of-the-art models like GPT-4o achieve only 38.5% question answering accuracy on TemporalBench.
  arXiv  Detail & Related papers  (2024-10-14T17:59:58Z)
• Lost in Time: A New Temporal Benchmark for VideoLLMs [48.71203934876828]
  We show that the currently most used video-language benchmarks can be solved without requiring much temporal reasoning.<n>We propose TVBench, a novel open-source video multiple-choice question-answering benchmark.
  arXiv  Detail & Related papers  (2024-10-10T09:28:36Z)
• VANE-Bench: Video Anomaly Evaluation Benchmark for Conversational LMMs [64.60035916955837]
  VANE-Bench is a benchmark designed to assess the proficiency of Video-LMMs in detecting anomalies and inconsistencies in videos. Our dataset comprises an array of videos synthetically generated using existing state-of-the-art text-to-video generation models. We evaluate nine existing Video-LMMs, both open and closed sources, on this benchmarking task and find that most of the models encounter difficulties in effectively identifying the subtle anomalies.
  arXiv  Detail & Related papers  (2024-06-14T17:59:01Z)
• Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMs [20.168429351519055]
  Video understanding is a crucial next step for multimodal large language models (LMLMs) We propose VideoNIAH (Video Needle In A Haystack), a benchmark construction framework through synthetic video generation. We conduct a comprehensive evaluation of both proprietary and open-source models, uncovering significant differences in their video understanding capabilities.
  arXiv  Detail & Related papers  (2024-06-13T17:50:05Z)
• CinePile: A Long Video Question Answering Dataset and Benchmark [55.30860239555001]
  We present a novel dataset and benchmark, CinePile, specifically designed for authentic long-form video understanding. Our comprehensive dataset comprises 305,000 multiple-choice questions (MCQs), covering various visual and multimodal aspects. We fine-tuned open-source Video-LLMs on the training split and evaluated both open-source and proprietary video-centric LLMs on the test split of our dataset.
  arXiv  Detail & Related papers  (2024-05-14T17:59:02Z)
• Deconfounded Video Moment Retrieval with Causal Intervention [80.90604360072831]
  We tackle the task of video moment retrieval (VMR), which aims to localize a specific moment in a video according to a textual query. Existing methods primarily model the matching relationship between query and moment by complex cross-modal interactions. We propose a causality-inspired VMR framework that builds structural causal model to capture the true effect of query and video content on the prediction.
  arXiv  Detail & Related papers  (2021-06-03T01:33:26Z)
• Fill-in-the-blank as a Challenging Video Understanding Evaluation Framework [19.031957183047048]
  We introduce a novel dataset consisting of 28,000 videos and fill-in-the-blank tests. We show that both a multimodal model and a strong language model have a large gap with human performance.
  arXiv  Detail & Related papers  (2021-04-09T04:00:10Z)

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.