# ActivityForensics: A Comprehensive Benchmark for Localizing Manipulated Activity in Videos

arXiv: https://arxiv.org/abs/2604.03819 · HTML: https://mlsanity.com/paper/2604.03819/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 47 references that are in the map.
- First posted on arXiv 4 Apr 2026.

## Builds on (most cited first, 29 of 29)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [FaceForensics++: Learning to Detect Manipulated Facial Images](https://mlsanity.com/paper/1901.08971/) (2019)
- [Dense-Captioning Events in Videos](https://mlsanity.com/paper/1705.00754/) (2017)
- [TALL: Temporal Activity Localization via Language Query](https://mlsanity.com/paper/1705.02101/) (2017)
- [LTX-Video: Realtime Video Latent Diffusion](https://mlsanity.com/paper/2501.00103/) (2024)
- [VACE: All-in-One Video Creation and Editing](https://mlsanity.com/paper/2503.07598/) (2025)
- [VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation](https://mlsanity.com/paper/2303.08320/) (2023)
- [ActionFormer: Localizing Moments of Actions with Transformers](https://mlsanity.com/paper/2202.07925/) (2022)
- [A Survey on Video Diffusion Models](https://mlsanity.com/paper/2310.10647/) (2023)
- [Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Models](https://mlsanity.com/paper/2405.04233/) (2024)
- [ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis](https://mlsanity.com/paper/2103.05630/) (2021)
- [Harnessing Large Language Models for Training-free Video Anomaly Detection](https://mlsanity.com/paper/2404.01014/) (2024)
- [Deepfake Generation and Detection: A Benchmark and Survey](https://mlsanity.com/paper/2403.17881/) (2024)
- [Number it: Temporal Grounding Videos like Flipping Manga](https://mlsanity.com/paper/2411.10332/) (2024)
- [Diffusion Model-Based Video Editing: A Survey](https://mlsanity.com/paper/2407.07111/) (2024)
- [UMMAFormer: A Universal Multimodal-adaptive Transformer Framework for Temporal Forgery Localization](https://mlsanity.com/paper/2308.14395/) (2023)
- [Generative Inbetweening through Frame-wise Conditions-Driven Video Generation](https://mlsanity.com/paper/2412.11755/) (2024)
- [Test-Time Zero-Shot Temporal Action Localization](https://mlsanity.com/paper/2404.05426/) (2024)
- [Synchronized Video Storytelling: Generating Video Narrations with Structured Storyline](https://mlsanity.com/paper/2405.14040/) (2024)
- [Video Anomaly Detection with Motion and Appearance Guided Patch Diffusion Model](https://mlsanity.com/paper/2412.09026/) (2024)
- [Semantic Contextualization of Face Forgery: A New Definition, Dataset, and Detection Method](https://mlsanity.com/paper/2405.08487/) (2024)
- [Open-Set Deepfake Detection: A Parameter-Efficient Adaptation Method with Forgery Style Mixture](https://mlsanity.com/paper/2408.12791/) (2024)
- [1M-Deepfakes Detection Challenge](https://mlsanity.com/paper/2409.06991/) (2024)
- [DiGIT: Multi-Dilated Gated Encoder and Central-Adjacent Region Integrated Decoder for Temporal Action Detection Transformer](https://mlsanity.com/paper/2505.05711/) (2025)
- [EF-VI: Enhancing End-Frame Injection for Video Inbetweening](https://mlsanity.com/paper/2505.21205/) (2025)
- [Bi-Level Optimization for Self-Supervised AI-Generated Face Detection](https://mlsanity.com/paper/2507.22824/) (2025)

## Built on by (most cited first, 1 of 1)

- [HumanForge: A Human-Centric Deepfake Video Benchmark with Multi-Agent Forgery Rationales](https://mlsanity.com/paper/2607.08705/) (2026)

## Abstract (arXiv)

Temporal forgery localization aims to temporally identify manipulated segments in videos. Most existing benchmarks focus on appearance-level forgeries, such as face swapping and object removal. However, recent advances in video generation have driven the emergence of activity-level forgeries that modify human actions to distort event semantics, resulting in highly deceptive forgeries that critically undermine media authenticity and public trust. To overcome this issue, we introduce ActivityForensics, the first large-scale benchmark for localizing manipulated activity in videos. It contains over 6K forged video segments that are seamlessly blended into the video context, rendering high visual consistency that makes them almost indistinguishable from authentic content to the human eye. We further propose Temporal Artifact Diffuser (TADiff), a simple yet effective baseline that exposes artifact cues through a diffusion-based feature regularizer. Based on ActivityForensics, we introduce comprehensive evaluation protocols covering intra-domain, cross-domain, and open-world settings, and benchmark a wide range of state-of-the-art forgery localizers to facilitate future research. The dataset and code are available at https://activityforensics.github.io.