ActivityForensics: A Comprehensive Benchmark for Localizing Manipulated Activity in Videos

• URL: http://arxiv.org/abs/2604.03819v1
• Date: Sat, 04 Apr 2026 18:00:05 GMT
• Title: ActivityForensics: A Comprehensive Benchmark for Localizing Manipulated Activity in Videos
• Abstract summary: We introduce ActivityForensics, the first large-scale benchmark for localizing manipulated activity in videos.<n>It contains over 6K forged video segments that are seamlessly blended into the video context.<n>Based on ActivityForensics, we introduce comprehensive evaluation protocols covering intra-domain, cross-domain, and open-world settings.
• Score: 62.94038307981723
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• TF-CADE: Foreground-Concentrated Text-Video Alignment for Zero-Shot Temporal Action Detection [54.38725298163703]
  We propose a Text-Foreground Concentrated Alignment for zero-shot temporal action DEtector (TF-CADE)<n>ACA extracts action concentrate scores to aggregate temporally informative video segments into a foreground- weighted video embedding.<n> CCR strategy refines per-snippet confidence scores by lever- aging foreground-aware similarity, effectively suppressing irrelevant action classes during inference.
  arXiv  Detail & Related papers  (2026-08-18T06:43:45Z)
• Detecting Temporally Localized Manipulations in Authentic Video Streams [1.9116784879310027]
  Video editing and generative artificial intelligence technologies have made realistic video manipulation increasingly accessible.<n>Existing datasets do not adequately model scenarios in which a short manipulated segment is inserted into an otherwise authentic video.<n>We create a new dataset specifically designed for authentic videos containing short and highly realistic manipulated intervals.
  arXiv  Detail & Related papers  (2026-06-05T09:35:51Z)
• Explainable Forensics of Manipulated Segments in Untrimmed Long Videos [50.190474724159465]
  We formulate the task of Temporal AI-Generated Segment localization and Explanation.<n>We introduce TASLE, a large-scale benchmark comprising 12,472 untrimmed videos with diverse manipulation patterns and rich annotation signals.<n>We propose MSLoc, a coarse-to-fine forensic baseline that combines a boundary-sensitive proposal generation module for efficient long-video scanning with an MLLM-based refinement module for precise boundary localization and interpretable reasoning.
  arXiv  Detail & Related papers  (2026-06-01T15:48:38Z)
• Detecting Localized Deepfake Manipulations Using Action Unit-Guided Video Representations [4.449835214520726]
  Deepfake techniques are increasingly narrowing the gap between real and synthetic videos, raising serious privacy and security concerns.<n>This work presents the first detection approach explicitly designed to generalize to localized edits in deepfake videos.<n>Our method achieves a $20%$ improvement in accuracy over current state-of-the-art detection methods.
  arXiv  Detail & Related papers  (2025-03-28T03:49:00Z)
• Multi-Modal Domain Adaptation Across Video Scenes for Temporal Video Grounding [59.599378814835205]
  Temporal Video Grounding (TVG) aims to localize the temporal boundary of a specific segment in an untrimmed video based on a given language query. We introduce a novel AMDA method to adaptively adjust the model's scene-related knowledge by incorporating insights from the target data.
  arXiv  Detail & Related papers  (2023-12-21T07:49:27Z)
• Segment Anything Meets Point Tracking [116.44931239508578]
  This paper presents a novel method for point-centric interactive video segmentation, empowered by SAM and long-term point tracking. We highlight the merits of point-based tracking through direct evaluation on the zero-shot open-world Unidentified Video Objects (UVO) benchmark. Our experiments on popular video object segmentation and multi-object segmentation tracking benchmarks, including DAVIS, YouTube-VOS, and BDD100K, suggest that a point-based segmentation tracker yields better zero-shot performance and efficient interactions.
  arXiv  Detail & Related papers  (2023-07-03T17:58:01Z)
• Video Action Detection: Analysing Limitations and Challenges [70.01260415234127]
  We analyze existing datasets on video action detection and discuss their limitations. We perform a biasness study which analyzes a key property differentiating videos from static images: the temporal aspect. Such extreme experiments show existence of biases which have managed to creep into existing methods inspite of careful modeling.
  arXiv  Detail & Related papers  (2022-04-17T00:42:14Z)
• Do You Really Mean That? Content Driven Audio-Visual Deepfake Dataset and Multimodal Method for Temporal Forgery Localization [19.490174583625862]
  We introduce a content-driven audio-visual deepfake dataset, termed Localized Audio Visual DeepFake (LAV-DF) Specifically, the content-driven audio-visual manipulations are performed strategically to change the sentiment polarity of the whole video. Our extensive quantitative and qualitative analysis demonstrates the proposed method's strong performance for temporal forgery localization and deepfake detection tasks.
  arXiv  Detail & Related papers  (2022-04-13T08:02:11Z)
• Real-time Human-Centric Segmentation for Complex Video Scenes [16.57620683425904]
  Most existing video tasks related to "human" focus on the segmentation of salient humans, ignoring the unspecified others in the video. Few studies have focused on segmenting and tracking all humans in a complex video, including pedestrians and humans of other states. We propose a novel framework, abbreviated as HVISNet, that segments and tracks all presented people in given videos based on a one-stage detector.
  arXiv  Detail & Related papers  (2021-08-16T16:07:51Z)
• JOKR: Joint Keypoint Representation for Unsupervised Cross-Domain Motion Retargeting [53.28477676794658]
  unsupervised motion in videos has seen substantial advancements through the use of deep neural networks. We introduce JOKR - a JOint Keypoint Representation that handles both the source and target videos, without requiring any object prior or data collection. We evaluate our method both qualitatively and quantitatively, and demonstrate that our method handles various cross-domain scenarios, such as different animals, different flowers, and humans.
  arXiv  Detail & Related papers  (2021-06-17T17:32:32Z)
• Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detection [118.37239586697139]
  LipForensics is a detection approach capable of both generalising manipulations and withstanding various distortions. It consists in first pretraining a-temporal network to perform visual speech recognition (lipreading) A temporal network is subsequently finetuned on fixed mouth embeddings of real and forged data in order to detect fake videos based on mouth movements without over-fitting to low-level, manipulation-specific artefacts.
  arXiv  Detail & Related papers  (2020-12-14T15:53:56Z)

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.