The paper introduces a Short-Window Sliding Learning framework for real‑time violence detection in CCTV footage. It splits videos into 1–2 second clips and uses LLM‑based auto‑caption labeling to build fine‑grained datasets, preserving temporal continuity for accurate recognition of rapid violent events. The method achieves 95.25% accuracy on RWF‑2000 and 83.25% on UCF‑Crime, demonstrating strong generalization and real‑time applicability in intelligent surveillance systems.
arXiv:2506. 03162v3 Announce Type: replace-cross Abstract: The rapid proliferation of surveillance cameras has increased the demand for automated violence detection.
arXiv:2607. 03131v1 Announce Type: cross Abstract: Modern video surveillance systems generate far more video streams than human operators can effectively monitor, making automated analysis essential for timely detection of security events.
arXiv:2608.29759v1 Announce Type: cross Abstract: We present SynCrash, a multi-stage pipeline for zero-shot accident detection, spatial localization, and collision-type classification in fixed-view C...
The paper introduces an interdisciplinary framework that uses AI and machine learning to analyze police body‑worn camera footage from the Rochester Police Department. It combines image, audio, and natural language processing—including speaker separation, transcription, and large language models—to detect and classify interaction patterns such as respect, disrespect, escalation, and de‑escalation. A custom evaluation pipeline assesses transcription quality and behavior detection accuracy, aiming to support law‑enforcement review, training, and accountability.
arXiv:2510. 14904v4 Announce Type: replace-cross Abstract: Dense Video Object Captioning (DVOC) is the task of jointly detecting, tracking, and captioning object trajectories in a video, requiring the ability to understand spatio-temporal details and describe them in natural language.
arXiv:2505.01583v2 Announce Type: replace Abstract: Understanding causal event relationships and achieving fine-grained temporal grounding in videos remain challenging for vision-language models (VLM...
Video panoptic segmentation (VPS) aims to jointly detect, segment, and track all objects while partitioning the video into semantically consistent regions. We introduce the task setting of unsupervised VPS, omitting any human supervision.
arXiv:2608. 19737v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) have achieved remarkable progress in video understanding and reasoning.
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.
Children are naturally energetic, and during their spontaneous activities, they often encounter potentially dangerous situations, especially when lacking parental supervision. Identifying actions that pose risks plays a crucial role in ensuring their safety.
VidOmni-Bench is a new benchmark for fine‑grained video understanding that asks models to verify whether each event in dense video captions is supported by the video. It contains 500 videos covering five complexity types and durations from 4 seconds to 90 minutes, and uses human‑verified sentence‑level labels to create hard negatives. Experiments show that Video‑LLMs often hallucinate events, struggle to detect incorrect descriptions, and exhibit varying weaknesses depending on video complexity and duration.
The paper introduces Seeing Before Synthesizing (SBS), a weakly-supervised dense video captioning framework that uses a vision‑language model to generate frame‑level narratives for gaps between events and detect transitions based on semantic changes. SBS refines temporal masks by aligning transition points with vision‑language cues, rather than relying on rigidly placed synthetic captions. Experiments on ActivityNet Captions and YouCook2 show that SBS achieves state‑of‑the‑art results in both captioning and localization tasks.