CoCoVideo: The High-Quality Commercial-Model-Based Contrastive Benchmark for AI-Generated Video Detection

• URL: http://arxiv.org/abs/2606.00101v1
• Date: Tue, 26 May 2026 03:18:44 GMT
• Title: CoCoVideo: The High-Quality Commercial-Model-Based Contrastive Benchmark for AI-Generated Video Detection
• Abstract summary: CoCoVideo-26K is a contrastive, commercial-model-based AIGC video dataset covering 13 mainstream commercial generators.<n>Building on this dataset, we propose CoDetect, a framework integrating contrastive learning with confidence-gated multimodal large language model (MLLM) inference.
• Score: 12.128022166557754
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: With the rapid advancement of artificial intelligence generated content (AIGC) technologies, video forgery has become increasingly prevalent, posing new challenges to public discourse and societal security. Despite remarkable progress in existing deepfake detection methods, AIGC forgery detection remains challenging, as existing datasets mainly rely on open-source video generation models with quality far below that of commercial AIGC systems. Even datasets containing a few commercial samples often retain visible watermarks, compromising authenticity and hindering model generalization to high-fidelity AIGC videos. To address these issues, we introduce CoCoVideo-26K, a contrastive, commercial-model-based AIGC video dataset covering 13 mainstream commercial generators and providing semantically aligned real-fake video pairs. This dataset enables deeper exploration of the differences between authentic and high-quality synthetic videos and establishes a new benchmark for highly realistic video forgery detection. Building on this dataset, we propose CoCoDetect, a detection framework integrating contrastive learning with confidence-gated multimodal large language model (MLLM) inference. An R3D-18 backbone extracts spatio-temporal representations, while a confidence gate routes uncertain cases to an MLLM for reasoning about physical plausibility and scene consistency. Extensive experiments on CoCoVideo-26K and public benchmarks demonstrate state-of-the-art performance, validating the framework's robustness and generalizability. Our code and dataset are available at https://github.com/DonoToT/CoCoVideo.

Related papers

• SphereVideo: Prototype-anchored Hyperspherical Boundary for Continual AI-generated Video Detection [61.05420454815012]
  AI-generated video (AIGV) detection aims to distinguish real videos from AI-generated ones.<n>In practice, detectors trained on existing data often fail to generalize to newly emerging generative models.<n>We propose SphereVideo, a novel framework for AIGV detection built on two key observations.
  arXiv  Detail & Related papers  (2026-08-02T15:54:54Z)
• Training-free Detection of Generated Videos via Spatial-Temporal Likelihoods [6.921364920053057]
  We introduce STALL, a training-free, theoretically justified detector that provides likelihood-based scoring for videos.<n>We evaluate STALL on two public benchmarks and introduce ComGenVid, a new benchmark with state-of-the-art generative models.
  arXiv  Detail & Related papers  (2026-03-16T09:26:56Z)
• AEGIS: Authenticity Evaluation Benchmark for AI-Generated Video Sequences [41.66718802220536]
  AEGIS comprises over 10,000 rigorously curated real and synthetic videos generated by diverse, state-of-the-art generative models.<n>We provide multimodal annotations spanning Semantic-Authenticity Descriptions, Motion Features, and Low-level Visual Features.<n>Experiments using advanced vision-language models demonstrate limited detection capabilities on the most challenging subsets of AEGIS.
  arXiv  Detail & Related papers  (2025-08-14T15:55:49Z)
• Generative Video Matting [57.186684844156595]
  Video matting has traditionally been limited by the lack of high-quality ground-truth data.<n>Most existing video matting datasets provide only human-annotated imperfect alpha and foreground annotations.<n>We introduce a novel video matting approach that can effectively leverage the rich priors from pre-trained video diffusion models.
  arXiv  Detail & Related papers  (2025-08-11T12:18:55Z)
• Leveraging Pre-Trained Visual Models for AI-Generated Video Detection [54.88903878778194]
  The field of video generation has advanced beyond DeepFakes, creating an urgent need for methods capable of detecting AI-generated videos with generic content.<n>We propose a novel approach that leverages pre-trained visual models to distinguish between real and generated videos.<n>Our method achieves high detection accuracy, above 90% on average, underscoring its effectiveness.
  arXiv  Detail & Related papers  (2025-07-17T15:36:39Z)
• BrokenVideos: A Benchmark Dataset for Fine-Grained Artifact Localization in AI-Generated Videos [63.03271511550633]
  BrokenVideos is a benchmark dataset of 3,254 AI-generated videos with meticulously annotated, pixel-level masks highlighting regions of visual corruption.<n>Our experiments show that training state of the art artifact detection models and multi modal large language models (MLLMs) on BrokenVideos significantly improves their ability to localize corrupted regions.
  arXiv  Detail & Related papers  (2025-06-25T03:30:04Z)
• DAVID-XR1: Detecting AI-Generated Videos with Explainable Reasoning [58.70446237944036]
  DAVID-X is the first dataset to pair AI-generated videos with detailed defect-level, temporal-spatial annotations and written rationales.<n>We present DAVID-XR1, a video-language model designed to deliver an interpretable chain of visual reasoning.<n>Our results highlight the promise of explainable detection methods for trustworthy identification of AI-generated video content.
  arXiv  Detail & Related papers  (2025-06-13T13:39:53Z)
• BusterX: MLLM-Powered AI-Generated Video Forgery Detection and Explanation [77.55074597806035]
  GenBuster-200K is a large-scale, high-quality AI-generated video dataset featuring 200K high-resolution video clips.<n>BusterX is a novel AI-generated video detection and explanation framework leveraging multimodal large language model (MLLM) and reinforcement learning.
  arXiv  Detail & Related papers  (2025-05-19T02:06:43Z)
• GenVidBench: A Challenging Benchmark for Detecting AI-Generated Video [35.05198100139731]
  We introduce GenVidBench, a challenging AI-generated video detection dataset with several key advantages.<n>The dataset includes videos from 8 state-of-the-art AI video generators.<n>It is analyzed from multiple dimensions and classified into various semantic categories based on their content.
  arXiv  Detail & Related papers  (2025-01-20T08:58:56Z)
• Detecting AI-Generated Video via Frame Consistency [25.290019967304616]
  We propose an open-source dataset and a detection method for generated video for the first time.<n>First, we propose a scalable dataset consisting of 964 prompts, covering various forgery targets, scenes, behaviors, and actions.<n>Second, we find via probing experiments that spatial artifact-based detectors lack generalizability.
  arXiv  Detail & Related papers  (2024-02-03T08:52:06Z)

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.