Impossible Videos

• URL: http://arxiv.org/abs/2503.14378v1
• Date: Tue, 18 Mar 2025 16:10:24 GMT
• Title: Impossible Videos
• Authors: Zechen Bai, Hai Ci, Mike Zheng Shou,
• Abstract summary: IPV-Bench is a benchmark designed to evaluate progress in video understanding and generation.<n>It features diverse scenes that defy physical, biological, geographical, or social laws.<n>A benchmark is curated to assess Video-LLMs on their ability of understanding impossible videos.
• Score: 21.16715759223276
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Synthetic videos nowadays is widely used to complement data scarcity and diversity of real-world videos. Current synthetic datasets primarily replicate real-world scenarios, leaving impossible, counterfactual and anti-reality video concepts underexplored. This work aims to answer two questions: 1) Can today's video generation models effectively follow prompts to create impossible video content? 2) Are today's video understanding models good enough for understanding impossible videos? To this end, we introduce IPV-Bench, a novel benchmark designed to evaluate and foster progress in video understanding and generation. IPV-Bench is underpinned by a comprehensive taxonomy, encompassing 4 domains, 14 categories. It features diverse scenes that defy physical, biological, geographical, or social laws. Based on the taxonomy, a prompt suite is constructed to evaluate video generation models, challenging their prompt following and creativity capabilities. In addition, a video benchmark is curated to assess Video-LLMs on their ability of understanding impossible videos, which particularly requires reasoning on temporal dynamics and world knowledge. Comprehensive evaluations reveal limitations and insights for future directions of video models, paving the way for next-generation video models.

Related papers

• VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness [76.16523963623537]
  We introduce VBench-2.0, a benchmark designed to evaluate video generative models for intrinsic faithfulness. VBench-2.0 assesses five key dimensions: Human Fidelity, Controllability, Creativity, Physics, and Commonsense. By pushing beyond superficial faithfulness toward intrinsic faithfulness, VBench-2.0 aims to set a new standard for the next generation of video generative models.
  arXiv  Detail & Related papers  (2025-03-27T17:57:01Z)
• VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation [66.58048825989239]
  VideoPhy-2 is an action-centric dataset for evaluating physical commonsense in generated videos.<n>We perform human evaluation that assesses semantic adherence, physical commonsense, and grounding of physical rules in the generated videos.<n>Our findings reveal major shortcomings, with even the best model achieving only 22% joint performance.
  arXiv  Detail & Related papers  (2025-03-09T22:49:12Z)
• GRADEO: Towards Human-Like Evaluation for Text-to-Video Generation via Multi-Step Reasoning [62.775721264492994]
  GRADEO is one of the first specifically designed video evaluation models.<n>It grades AI-generated videos for explainable scores and assessments through multi-step reasoning.<n> Experiments show that our method aligns better with human evaluations than existing methods.
  arXiv  Detail & Related papers  (2025-03-04T07:04:55Z)
• Generative Ghost: Investigating Ranking Bias Hidden in AI-Generated Videos [106.5804660736763]
  Video information retrieval remains a fundamental approach for accessing video content.<n>We build on the observation that retrieval models often favor AI-generated content in ad-hoc and image retrieval tasks.<n>We investigate whether similar biases emerge in the context of challenging video retrieval.
  arXiv  Detail & Related papers  (2025-02-11T07:43:47Z)
• What Matters in Detecting AI-Generated Videos like Sora? [51.05034165599385]
  Gap between synthetic and real-world videos remains under-explored. In this study, we compare real-world videos with those generated by a state-of-the-art AI model, Stable Video Diffusion. Our model is capable of detecting videos generated by Sora with high accuracy, even without exposure to any Sora videos during training.
  arXiv  Detail & Related papers  (2024-06-27T23:03:58Z)
• VideoPhy: Evaluating Physical Commonsense for Video Generation [93.28748850301949]
  We present VideoPhy, a benchmark designed to assess whether the generated videos follow physical commonsense for real-world activities. We then generate videos conditioned on captions from diverse state-of-the-art text-to-video generative models. Our human evaluation reveals that the existing models severely lack the ability to generate videos adhering to the given text prompts.
  arXiv  Detail & Related papers  (2024-06-05T17:53:55Z)
• Let's Think Frame by Frame with VIP: A Video Infilling and Prediction Dataset for Evaluating Video Chain-of-Thought [62.619076257298204]
  We motivate framing video reasoning as the sequential understanding of a small number of video reasonings. We introduce VIP, an inference-time challenge dataset designed to explore models' reasoning capabilities through video chain-of-thought. We benchmark GPT-4, GPT-3, and VICUNA on VIP, demonstrate the performance gap in complex video reasoning tasks, and encourage future work.
  arXiv  Detail & Related papers  (2023-05-23T10:26:42Z)
• Highlight Timestamp Detection Model for Comedy Videos via Multimodal Sentiment Analysis [1.6181085766811525]
  We propose a multimodal structure to obtain state-of-the-art performance in this field. We select several benchmarks for multimodal video understanding and apply the most suitable model to find the best performance.
  arXiv  Detail & Related papers  (2021-05-28T08:39:19Z)

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.