arXiv:2604.11082v2 Announce Type: replace Abstract: Visual glitches in video games degrade player experience and perceived quality, yet manual quality assurance cannot keep pace with the growing test...
The paper examines four leading motion‑based AI‑generated video detectors and finds that three of them suffer from preprocessing and sampling biases that inflate their reported performance. These detectors rely heavily on motion patterns—specifically, the lower inter‑frame movement typical of synthetic videos—so their accuracy drops to near random when tested on datasets lacking this bias or after simple spatial augmentations. In contrast, a frequency‑based detector remains robust across all datasets, indicating that frequency‑domain methods may generalize better for detecting AI‑generated videos.
arXiv:2606. 16742v1 Announce Type: cross Abstract: With the rapid advancement of video generation models, distinguishing between AI-generated and authentic videos has emerged as a challenging endeavor.
arXiv:2603.14733v2 Announce Type: replace Abstract: Multimodal Large Language Models have achieved strong performance in single-video understanding, yet their ability to reason across multiple videos...
The paper introduces a new protocol, Mistake Detection Video Question Answering (MD‑VQA), to evaluate whether models can determine if a step in a video follows its description, covering both seen and unseen actions. It proposes a post‑training approach for video‑language models that uses a reward function to highlight discrepancies between instructions and video content. Experiments show this method surpasses zero‑shot, fine‑tuned, and other post‑training baselines, especially on unseen procedures, improving performance by up to 11.6% on EP‑VQA.
VideoTIR introduces a reinforcement‑learning approach to improve long‑video understanding by encouraging multimodal large language models to use comprehensive multi‑level toolkits efficiently. It combines Zero‑RL and SFT cold‑starting strategies to help models retrieve and focus on meaningful video segments, images, and regions, thereby reducing hallucinations. The method includes Toolkit Action Grouped Policy Optimization (TAGPO) to streamline tool‑calling and a sandbox‑based trajectory synthesis framework for high‑quality data, achieving strong results on three long‑video QA benchmarks.
arXiv:2610.35148v1 Announce Type: new Abstract: Recent advances in generative video models have improved visual realism, making detection increasingly dependent on subtle temporal inconsistencies. Ho...
The paper introduces Short‑Films 20K (SF20K), a large publicly available movie dataset comprising 20,143 amateur films totaling 3,582 hours, with an average length of 12 minutes per film. Accompanying the dataset is SF20K‑Test, a manual open‑ended question‑answering benchmark featuring 95 movies and 979 question‑answer pairs. Analysis of the benchmark shows limited data leakage, highlights the necessity of long‑term reasoning, and demonstrates that instruction tuning on the large‑scale dataset significantly boosts vision‑language model performance.
GameVerse is a new minute‑scale gameplay video dataset designed to support long‑horizon interactive world modeling. It contains 69.7K clips totaling 1,655 hours and 349.6 million frames, including 1,358 hours of continuous two‑minute sequences—an order of magnitude longer than prior datasets. Each clip is processed through a unified pipeline that provides scene‑consistent segmentation, quality filtering, camera pose estimation, and event‑based caption annotation, with temporally stable camera trajectories and captions that distinguish static context from dynamic events.
arXiv:2609.25001v1 Announce Type: new Abstract: Modern video games provide a measurable testbed for AI models, combining abilities of visual understanding, instruction decomposition, goal planning, a...
The paper introduces Intrinsic Temporal Adaptation (ITA) for Partially Relevant Video Retrieval (PRVR), a task that seeks untrimmed videos containing moments relevant to a text query. ITA employs a Backbone-Internal Temporal Adaptation that lets the final visual transformer layers attend to neighboring frames, creating temporally aware embeddings while keeping CLIP frozen. Additionally, an Affinity-Weighted Gradient Propagation technique softly aggregates top‑k frames based on text‑frame affinities to better handle the weakly supervised nature of PRVR, leading to state‑of‑the‑art performance and more accurate frame‑level evidence retrieval.
arXiv:2608. 03096v1 Announce Type: cross Abstract: Recent advances in video generation models have significantly intensified the deepfake threat, yet the current deepfake video detection benchmarks remain underdeveloped.