Video Surveillance

Construction remains the deadliest industry sector in the United States, with 1,055 fatal worker injuries recorded in 2023, and the majority preventable. Existing monitoring approaches are expensive, require real-time human operators, or address only a narrow subset of violations. This paper presents a passive, end-of-shift construction safety monitoring pipeline processing video from POV body-worn and fixed wall-mounted cameras through a three-stage architecture: (1) fine-tuned YOLO11 for primary PPE and hazard detection, (2) SAM 3 for segmentation refinement and worker deduplication, and (3) Qwen3-VL-8B-Instruct with a method-prompted, persona-scaffolded three-pass adversarial chain-of-thought protocol for compliance verification and hallucination control. The principal contribution is the Stage 3 prompt design: professional persona backstories following the method-actor framing drive an observed 12% precision improvement over single-pass prompting in an informal three-author review of the 12-video Ironsite development corpus, with the largest gains on hallucination-prone violation categories. Structural message isolation enforces observational independence between a generator, discriminator, and reconciliation pass governed by asymmetric rules encoding priors about human observation versus automated detection reliability. The system maps violations to OSHA standards, performs REBA-inspired ergonomic risk scoring from pose keypoints, and produces per-worker safety reports with timestamped evidence. An evaluation harness is released for future reproduction.

RGB camera-based surveillance systems enable human action recognition for public safety and healthcare, yet raise serious privacy concerns. Existing methods rely on post-capture algorithms, which fail to protect privacy during data acquisition. We propose Lens Privacy Sealing (LPS), a simple hardware solution that physically obscures camera lenses with adjustable laminating film, providing pre-sensor privacy protection at minimal cost. Unlike software methods or expensive engineered optics, LPS achieves strong privacy through stochastic multi-layer scattering that is physically irreversible. We introduce the P$^3$AR dataset for privacy-preserving action recognition, featuring both large-scale replay-captured (P$^3$AR-NTU, 114K videos) and real-world collected (P$^3$AR-PKU) subsets with privacy attribute annotations. To handle video degradation from LPS, we propose MSPNet, a single-stage framework incorporating Inter-Frame Noise Suppressor (IFNS) and Cross-Frame Semantic Aggregator (CFSA), enhanced by contrastive language-image pre-training for robust semantic extraction. Extensive experiments demonstrate that MSPNet with IFNS and CFSA nearly doubles action recognition accuracy compared to baseline methods while suppressing identity recognition to low levels. Comprehensive validation shows LPS achieves a superior privacy-utility trade-off compared to state-of-the-art hardware methods, resists reconstruction attacks including PSF inversion and data-driven recovery, and generalizes robustly across optical configurations and challenging environments. Code is available at https://github.com/wangzy01/MSPNet.

Law enforcement agencies are accumulating vast amounts of body-worn camera (BWC) footage. However, this remains operationally opaque. That is, analysts and trainers still have to invest considerable time watching full-length videos to pinpoint the start of key encounters and identify the points where activity shifts to something more physically intense. We present an approach to process BWC video into a time-aligned sequence of fixed-length 10-second windows, processed and labeled using a privacy-conscious protocol. Each window is labeled with two dimensions of information: (i) the operational context of the window and (ii) the level of motion intensity within the window, with low-evidence labels for windows for which insufficient evidence exists due to darkness, blur or occlusion. We train models to classify windows based on these two axes using frames sampled from each window encoded using CLIP model and aggregated into a window-level representation. We extract dense optical flow statistics for each window to capture motion intensity. On test windows the best context model achieves 78.75% accuracy, and the best-accuracy activity model achieves 88.33%. We also included integrity audits to show the results and how the visual timeline representations support faster incident review and make the officer training workflow more practical.

While RGB-Thermal crowd counting has shown promise, the paradigm faces critical limitations: RGB data raises privacy concerns in public surveillance, and multi-modal misalignment degrades fusion performance. We propose the first thermal-only framework specifically designed for privacy-conscious crowd counting, eliminating RGB dependency at inference time and substantially reducing the privacy exposure associated with continuous RGB capture in public surveillance deployments. To mitigate thermal ambiguity, we leverage depth-to-RGB diffusion models as a cross-modal bridge, extracting discriminative features that enhance thermal representations. Critically, we demonstrate that single-step LCM denoising yields features most faithful to the structural content of the depth conditioning signal, while multi-step approaches progressively decouple features from the conditioning input and accumulate errors that degrade counting accuracy. Experiments on RGBT-CC and DroneRGBT datasets show our method achieves competitive performance against state-of-the-art RGB-T fusion methods, while requiring only thermal input during inference, eliminating the need for continuous RGB capture that constitutes the primary privacy concern in real-world surveillance deployment. The code will be made publicly available.

Camera traps have become a common tool for wildlife monitoring efforts in ecological research and biodiversity conservation. Wildlife classification models have benefited from the increase in wildlife visual data. These models reach high levels of accuracy on curated, high-quality datasets. However, their performance remains sensitive to real-world environmental constraints. They often produce inconsistent predictions when performing inference on temporally coherent sequences. The predicted label for a single individual shifts rapidly between frames. This study exploits the temporal nature of camera-trap data to augment inferred predictions from a wildlife classification model. Specifically, we adopt several standard Multi-Object Tracking (MOT) models to link detections across consecutive frames. The curated trajectories are used to fuse the softmax class probabilities. The fused probability score produces a single consensus class label estimate that overrides misclassifications caused by noise. The analysis of the experimental results shows that our proposed strategy improves over a standalone classifier over all datasets and for each metric. Specifically, the best-performing MOT models gain a weighted F1-Score of 5.1%, 3.1% and 2.0% over the classifier across three MOT datasets.

Video periocular recognition is the task of recognizing an individual's identity based on the region around an individual's eyes. The periocular area is one of the most discriminative regions of the human face, making it suitable for recognition tasks. Its use as a biometric modality has emerged as an alternative, especially in surveillance scenarios where conventional biometric traits such as face or iris recognition become unfeasible due to unconstrained acquisition conditions. This paper proposes an attention-aware approach for video-based periocular recognition in surveillance environments. The framework consists of two main modules: feature embedding and aggregation. The feature embedding module is a deep convolutional neural network that maps periocular data to feature vectors. The aggregation module is an encoder-only transformer that adaptively learns to aggregate frame-level features into a single video representation and a feature vector for the still reference image. Experiments on the publicly available COX Face dataset show the robustness of the proposed method, consistently outperforming naive aggregation schemes. In the best scenario, the approach achieves $99.8\%$ of TPR@$1e^{-1}$ and $96.6\%$ of Rank-5.

Event-based cameras (EBCs) are an attractive sensing modality for surveillance due to their reporting of pixel-level radiance changes with microsecond resolution and high dynamic range, enabling motion extraction while suppressing background. Their asynchronous, sparse output, however, necessitate algorithms that identify targets in event-space without processing full frames. We introduce Frequency Rate Information for Event Space (FRIES), a neuromorphic processing framework that detects periodicity in events, such as rotor rotation and mechanical vibrations, to discriminate and monitor man-made objects. FRIES first applies a time gate to suppress background and noise, then aggregates events into a pixel-wise activity (e.g., density) map and clusters pixels into regions-of-interest (ROIs). A localized spectral analysis is applied to each ROI to extract dominant frequencies used to distinguish structured object signatures from unstructured background and noise. Discriminated targets are visualized using a Resonant Time Surface (RTS), a frequency-selective method that weights events by their phase coherence with the extracted frequencies, rewarding in-sync content and suppressing out-of-sync clutter. We demonstrate FRIES and RTS in a controlled indoor experiment to recover the rotational frequency of a mechanical chopper and drone rotors against a moving background. We further test these methods on an outdoor data to detect a hovering drone against a realistic treeline. These preliminary results establish frequency-domain event processing as a promising front-end for selective surveillance in neuromorphic pipelines and a complementary surveillance modality, leveraging the high temporal resolution to enable spectral discrimination.

With the growing prevalence of always-on hardware such as smart glasses, body cameras, and home security systems, life-logging visual sensing is becoming inevitable, forming the backbone of persistent, always-on AI systems. Meanwhile, recent advances in proactive agents and world models signal a fundamental shift from episodic, prompt-driven tools to next-generation AI systems that continuously perceive and react to the physical world. Although life-logging video streams can substantially improve utility of these promising systems, they also introduce significant privacy risks by revealing sensitive information, such as behavioral patterns, emotional states, and social interactions, beyond what isolated images expose. If unresolved, these risks may undermine public trust and hinder the sustainable development of always-on AI technologies. Existing privacy protections are either attack-specific or incur substantial utility loss, and fail to consider the entire data exploitation pipeline. We therefore posit that the privacy-utility trade-off in life-logging video streams is a foundational challenge for next-generation AI systems that demands further investigation. We call for novel pipeline-aware privacy-preserving designs that jointly optimize utility and privacy for long-horizon life-logging visual data. In parallel, formal privacy leakage metrics and standardized benchmarks remain important open directions for future research.

This paper studies runtime monitoring for persistent surveillance by autonomous robots when the autonomy stack is a black box. The environment is partitioned into finitely many parts, each carrying an uncertainty state that decreases when observed and increases otherwise. We model the closed loop as a state-dependent hybrid system with linear parameter varying dynamics and design a monitor based on an invariant computed offline. As this invariant is typically hard to obtain for large to-be-surveyed spaces, we propose a compositional monitor obtained by decentralized computation of low-dimensional invariant sets for each uncertainty region, and checking their conjunction online. Under common independence assumptions, the compositional monitor is sound and complete with respect to the full-system invariant. The approach is applied in a case study with a real robot persistently monitoring a labyrinth, emphasizing its applicability in practice.

Reliable camera input is essential for safety-critical ADAS perception, but most monitoring approaches detect sensor failures only after downstream performance has degraded. We propose a proactive camera reliability monitoring framework that estimates perception risk from degradation-induced uncertainty patterns before downstream failure becomes observable. The method introduces a Global Sensor Health Index (GSHI), a continuous reliability score that aggregates per-degradation severities using a risk-aware multiplicative formulation, allowing severe single-mode failures such as lens occlusion or motion blur to dominate the health estimate. A lightweight multi-task network predicts degradation type, severity, GSHI, and spatial uncertainty maps from a single RGB image without downstream task feedback. Training uses physics- and geometry-aware synthetic supervision over twelve camera degradation modes. Experiments on KITTI-derived degradations show that GSHI decreases monotonically with severity, achieves a health-estimation MAE of 0.064, and provides positive early-warning lead time of 0.47 $\pm$ 0.25 severity units before YOLOv8 detection failure. GSHI also outperforms IQA, detector-confidence, and clean-feature OOD baselines, and transfers zero-shot to real adverse-weather driving data. These results support degradation-aware uncertainty analysis as a practical direction for proactive camera reliability monitoring in intelligent vehicles.

Artificial intelligence (AI) and computer vision are transforming transportation data collection. This study introduces an AI-enabled analytics framework leveraging existing CCTV infrastructure to evaluate the impact of soft interventions, such as temporary pedestrian refuges and curb extensions, on vehicle speed and safety. Using deep learning and perspective-based speed estimation, we evaluated driver behavior before and after interventions, with repeated post-installation monitoring in Week 1 and Week 2, in Minneapolis. Findings reveal that at unsignalized intersections, mean and 85th-percentile speeds fell by up to 18.75% and 16.56%, respectively, while pass-through traffic decreased by as much as 12.2%. Signalized intersections showed comparable reductions except one location, with mean and 85th-percentile speeds dropping by up to 20.0% and 17.19%. These results demonstrate the traffic-calming effectiveness of soft infrastructure and underscore the utility of AI-powered methods for rapid, low-cost, and evidence-based transport policy evaluation.

Diffusion models are rapidly redefining 3D anomaly detection in point cloud data. As 3D sensing becomes integral to modern manufacturing, reliable anomaly detection is essential for high-throughput quality assurance and process control. Yet practical deployment on resource-constrained, latency-critical systems remains limited. Existing methods are often computationally prohibitive or unreliable in complex, unmasked regions, and diffusion pipelines are inherently bottlenecked by iterative denoising. In this work, we address this bottleneck by reformulating reconstructionbased anomaly detection through consistency learning, enabling direct prediction of anomaly-free geometry in one or two network evaluations. We further introduce a novel hybrid loss formulation that explicitly enforces reconstruction toward clean data. This design substantially reduces inference cost, achieving up to 80x faster runtime than the current state-of-the-art method, without GPU acceleration, while preserving strong detection performance. It outperforms R3D-AD on Anomaly-ShapeNet with 76.20% I-AUROC and remains competitive on Real3DAD with 72.80% I-AUROC, enabling efficient, low-latency anomaly detection on resource-constrained platforms, including drones, smart industrial cameras, and other edge devices.

Physical violence in public spaces is a significant public health concern, with minor incidents such as pushing often serving as precursors to more severe escalations. This research develops an automated system for the real-time detection of moderate physical violence, specifically pushing, in surveillance camera footage. The proposed solution integrates state-of-the-art computer vision models, utilizing YOLO11 and YOLO11-Pose for human detection and skeletal keypoint extraction. By calculating body inclination and joint angles between shoulders and hips, a Random Forest classifier was trained to distinguish between normal behavior and aggressive physical contact. The system's performance was evaluated through three progressive case studies representing increasing levels of difficulty. In controlled environments with frontal views, the model achieved a precision of 0.98. In the most challenging scenario, featuring high-altitude, steep-angle recordings from real-world surveillance infrastructure, the system maintained a precision of 0.72 despite significant perspective distortion and visual noise. These results demonstrate the feasibility of using skeletal analysis for early violence intervention in urban security contexts.

Monitoring archaeological sites at scale is vital for protecting cultural heritage, yet pinpointing when disturbances occur remains difficult because visual cues are subtle and ground-truth data are sparse. We introduce WATCH, a framework for month-level change-event localization over PlanetScope satellite mosaics (2017-2024, 4.7 m/px) that supports three complementary scoring approaches: (i) Temporal Embedding Distance (TED), a training-free method that scores month-to-month deviations from a local temporal reference; (ii) Self-Supervised Change Detection (SSCD), an ensemble of reconstruction, forecasting, and latent-novelty signals; and (iii) a Weakly Supervised (WS) temporal localization model trained with sparse event-month labels. We benchmark WATCH on 1,943 archaeological sites in Afghanistan using embeddings from six foundation models (CLIP, GeoRSCLIP, SatMAE, Prithvi-EO-2.0, DINOv3, and Satlas-Pretrain) alongside a handcrafted spectral and texture baseline, and assess cross-regional generalization on sites in Syria, Turkey, Pakistan, and Egypt. The unsupervised approaches (TED, SSCD) consistently outperform the weakly supervised alternative. TED with SatMAE achieves the highest exact-month recall (55% at m=0), while TED with GeoRSCLIP, CLIP, or Satlas-Pretrain reaches 92.5% within a three-month tolerance (m=3). Handcrafted features remain competitive for exact-month detection under weak supervision. Our directional margin analysis reveals systematic temporal biases: SSCD paired with GeoRSCLIP or Prithvi-EO-2.0 exhibits the strongest early-warning profile, detecting anomalies before the recorded event, while TED favors confirmation-oriented detection after a change has materialized. These results show that satellite imagery combined with foundation-model embeddings enables scalable, decision-relevant heritage monitoring. Code: https://github.com/microsoft/WATCH

We propose HeroCrystal, a novel privacy-preserving framework for multi-camera domain-adaptive object detection, addressing challenges such as data privacy, class imbalance, and heterogeneous architectures. Our framework consists of three key stages. In the Generated Stage, we introduce a one-shot, target-aware diffusion-based generation module that learns visual style from a single target-domain image while leveraging prompt-based control to synthesize specific object instances. Unlike conventional style transfer-based methods that require large target datasets and ignore semantic-level discrepancies, our approach enables privacy-preserving augmentation to reduce ethical concerns, and introduces controllable rare object generation to mitigate long-tailed category degradation. In the Federated Stage, we employ probabilistic Faster R-CNN on the client side to improve localization accuracy, and a dynamic model contrastive strategy to suppress domain-specific bias. The server side performs model fusion across heterogeneous architectures without accessing raw data. Finally, in the Distilled Stage, we propose an inconsistent categories integration algorithm to resolve label inconsistency and architecture heterogeneity across clients. Extensive experiments on multiple cross-domain detection benchmarks demonstrate that our method outperforms existing multi-source domain adaptation and federated learning baselines under multi-class, privacy-preserving settings. Our method improves mAP by +2.1% over prior privacy-preserving approaches and achieves a new state-of-the-art mAP of 33.4%, highlighting the effectiveness of HeroCrystal in enabling practical multi-camera AI surveillance systems. The source code is publicly available at https://github.com/ccuvislab/HeroCrystal.

Grounding traffic accidents in real CCTV footage is a rare-event problem where training on labeled accident video is often prohibited, yet accurate joint localization in time, space, and collision type is required. We present a no-fine-tuning pipeline that elicits this joint output from frozen vision-language models through two ideas. First, a coarse-to-fine two-pass decomposition: a full-video pass at 1 fps produces a coarse (t, x, y, c) tuple, then a second pass at 5 fps within a +/- 3 s window refines time and location, with two deterministic confidence gates that revert to the coarse estimate on boundary hedges or edge-clamped coordinates. Second, a specialist role assignment: Qwen3-VL-Plus handles grounding, Gemini 3.1 Flash-Lite handles typing on a centered video clip. On the ACCIDENT@CVPR 2026 benchmark (2,027 real CCTV videos) we reach ACC^S = 0.539 (95% CI [0.525, 0.553]): +0.127 over the benchmark paper's best-of-baselines oracle (0.412), +0.143 over the strongest single-VLM baseline (Molmo-7B, 0.396), and +0.250 over the naive baseline (0.289). The VLM path uses up to three API calls per video (17% fall back to physics on API failures); the full run costs ~$20.

Mobile remote identity verification (RIdV) systems are exposed to attacks that manipulate or replace the facial video stream, including presentation attacks, real-time deepfakes, and video injection. Recent European requirements, including ETSI TS 119 461 and CEN/TS 18099, motivate evidence channels beyond camera-based presentation-attack detection. This paper studies whether passive motion traces recorded during selfie capture provide auxiliary evidence for spoof screening and user verification. We introduce CanSelfie, a dataset of 375 bona fide multi-sensor sequences collected at 50 Hz from 30 participants using a commercial mobile RIdV application, together with stationary, handheld, and temporally shifted attack-proxy scenarios. We benchmark 7 multivariate time-series classifiers and 8 whole-series anomaly detectors across sensor configurations and temporal windows. For spoof screening, accelerometer-only ROCKAD obtains 0.00% FRR and 43.8% FAR, while QUANT+3-NN obtains the lowest FAR of 32.0% at 2.37% FRR; both reject all stationary proxies. For same-device and same-session user verification, WEASEL+MUSE reaches 1.07% EER using 9 channels. Raw acceleration is the most informative modality, and closed-set accuracy alone does not imply good verification because threshold calibration depends on score distributions. The findings support selfie-capture motion as a low-friction auxiliary signal, while leaving cross-device, cross-session, and real injection-attack evaluation as necessary next steps. Code and data available at: https://github.com/Ergzar/Selfie-Motion-AD-TSC.

Robust vehicle detection from fixed CCTV cameras is critical for Intelligent Transportation Systems. Yet existing benchmarks predominantly feature relatively homogeneous, highly organized traffic patterns captured from ego-centric driving perspectives or controlled aerial views. This regional and sensor view bias creates a significant gap. Models trained on datasets such as UA-DETRAC and COCO struggle to generalize to the dense, heterogeneous, disorganized traffic conditions observed in rapidly developing urban centers in emerging economies. To address this limitation, we introduce BMD-45, a large-scale dataset comprising 480K bounding boxes annotated over 45K images captured from over 3.6K operational Safe City CCTV cameras. BMD-45 contains 14 fine-grained vehicle categories, including region-specific modes such as auto-rickshaws and tempo travellers, which are not present in existing benchmarks. The dataset captures real-world deployment challenges, including extreme viewpoint variation, occlusion, and vehicle density . We establish comprehensive baselines using state-of-the-art detectors and reveal a striking domain gap: models fine-tuned on UA-DETRAC achieve only 33.6% mAP@0.50:0.95, compared to 83.8% when trained in-domain on BMD-45, representing a 2.5x improvement that persists even when accounting for novel vehicle classes. This performance gap underscores the critical need for geographically diverse traffic benchmarks and establishes BMD-45 as a baseline for developing robust perception systems in underrepresented urban environments worldwide. The dataset is available at: https://huggingface.co/datasets/iisc-aim/BMD-45.

Expressway video anomaly detection is essential for safety management. However, identifying anomalies across diverse scenes remains challenging, particularly for far-field targets exhibiting subtle abnormal vehicle motions. While Vision-Language Models (VLMs) demonstrate strong semantic reasoning capabilities, processing global frames causes attention dilution for these far-field objects and incurs prohibitive computational costs. To address these issues, we propose VIBES, an asynchronous collaborative framework utilizing VLMs guided by Bayesian inference. Specifically, to overcome poor generalization across varying expressway environments, we introduce an online Bayesian inference module. This module continuously evaluates vehicle trajectories to dynamically update the probabilistic boundaries of normal driving behaviors, serving as an asynchronous trigger to precisely localize anomalies in space and time. Instead of processing the continuous video stream, the VLM processes only the localized visual regions indicated by the trigger. This targeted visual input prevents attention dilution and enables accurate semantic reasoning. Extensive evaluations demonstrate that VIBES improves detection accuracy for far-field anomalies and reduces computational overhead, achieving high real-time efficiency and explainability while demonstrating generalization across diverse expressway conditions.

Text-based person anomaly search retrieves specific behavioral events from surveillance archives using natural-language queries. Although recent pose-aware methods align geometric structures well, they face a fundamental Pose-Semantic Gap: semantically different actions can share similar skeletal geometries. While Multimodal Large Language Models (MLLMs) can reduce this ambiguity, using them for large-scale retrieval is computationally prohibitive. We propose the Structure-Semantic Decoupled Cascade (SSDC) framework, which decouples retrieval into two stages: (1) Structure-Aware Coarse Retrieval, where a lightweight model quickly filters candidates by skeletal similarity ; and (2) Detective Squad Interaction, a multi-agent semantic verification module. The squad consists of a Detective for fast binary filtering, an Analyst for evidence extraction, and a Writer for semantic synthesis. Finally, we re-rank candidates by fusing the synthesized captions with structural priors. Experiments on the PAB benchmark show that SSDC achieves state-of-the-art performance by balancing efficiency and semantic reasoning.

Low-Resolution License Plate Recognition (LRLPR) remains a challenging problem in real-world surveillance scenarios, where long capture distances, compression artifacts, and adverse imaging conditions can severely degrade license plate legibility. To promote progress in this area, we organized the ICPR 2026 Competition on Low-Resolution License Plate Recognition, the first competition specifically dedicated to LRLPR using real low-quality data collected under operationally relevant conditions. The competition was based on the LRLPR-26 dataset, which comprises 20,000 training tracks and 3,000 test tracks; each training track contains five low-resolution and five high-resolution images of the same license plate. Notably, a total of 269 teams from 41 countries registered for the competition, and 99 teams submitted valid entries in the Blind Test Phase. The winning team achieved a Recognition Rate of 82.13%, and four teams surpassed the 80% mark, highlighting both the high level of competition at the top of the leaderboard and the continued difficulty of the task. In addition to presenting the competition design, evaluation protocol, and main results, this paper summarizes the methods adopted by the top-5 teams and discusses current trends and promising directions for future research on LRLPR. The competition webpage is available at https://icpr26lrlpr.github.io/

Generating trajectories for synthetic aperture radar (SAR)-equipped aircraft poses significant challenges due to terrain constraints, and the need for straight-flight segments to ensure high-quality imaging. Related works usually focus on trajectory optimization for predefined straight-flight segments that do not adapt to the target visibility, which depends on the 3D terrain and aircraft orientation. In addition, this assumption does not scale well for the multi-target problem, where multiple straight-flight segments that maximize target visibility must be defined for real-time operations. For this purpose, this paper presents a multi-stage planning system. First, the waypoint sequencing to visit all the targets is estimated. Second, straight-flight segments maximizing target visibility according to the 3D terrain are predicted using a novel neural network trained with deep reinforcement learning. Finally, the segments are connected to create a trajectory via optimization that imposes 3D Dubins curves. Evaluations demonstrate the robustness of the system for SAR missions since it ensures high-quality multi-target SAR image acquisition aware of 3D terrain and target visibility, and real-time performance.

Despite decades of work, surveillance still struggles in searching and reasoning about specific targets across long, multi-camera videos. Existing methods - tracking, retrieval, and video LLMs require heavy manual filtering, capture only shallow attributes, and fail at temporal understanding. Prior benchmarks are also limited to basic retrieval and question answering, without addressing real world challenges that often involve multimodal queries and temporal grounding (e.g., "When did this person join the fight?" with the person's image). To address this gap, we introduce ForeSeaQA, a new benchmark specifically designed for video QA with image-and-text queries and timestamped annotations of key events. The dataset consists of long-horizon surveillance footage paired with diverse multimodal questions, enabling systematic evaluation of retrieval, temporal grounding, and multimodal reasoning in realistic forensic conditions. Not limited to this benchmark, we propose ForeSea, an AI forensic search system with a 3-stage, plug-and-play pipeline. (1) A tracking module filters irrelevant footage; (2) a multimodal embedding module indexes the remaining clips; and (3) during inference, the system retrieves top-K candidate clips for a video LLM to answer queries and localize events. On ForeSeaQA benchmark, ForeSea improves accuracy by 3.1 points and temporal IoU by 10.1 points over prior retrieval-augmented baselines. To our knowledge, ForeSeaQA is the first benchmark to support complex multimodal queries with precise temporal grounding, and ForeSea is the first VideoRAG system built to excel in this setting.

Agent safety benchmarks measure whether a monitor detects harm, not when. Yet timing is the difference between intervention and autopsy. We introduce StepShield, the first benchmark that treats detection timeliness as a first-class metric. On 9,429 incident-grounded code-agent trajectories, we define the Early Intervention Rate (EIR): the fraction of detected rogue trajectories where the alert fires within a k-step window after the divergence point, isolating timing quality from coverage. This metric exposes what we call the Forensics Trap: a pattern-based guardrail with 847 rules achieves 86% recall yet is statistically indistinguishable from random timing on EIR (0.23 vs. 0.24; p = 0.66, one-sided binomial; difference within CI), because over three-quarters of its alerts trigger on benign prefix code before any violation occurs. The 4x EIR gap between rule-based and semantic detectors is completely invisible to accuracy, recall, or F1. Our finding is structural: regex guardrails detect syntax, not intent, and therefore cannot distinguish the moment an agent turns rogue, rendering the entire deployed class of pattern-based monitors unsuited for real-time oversight. No existing method simultaneously achieves high recall, low false-positive rate, and timely intervention, establishing step-level rogue detection as genuinely unsolved.

Identifying when and where a news image was taken is crucial for journalists and forensic experts to produce credible stories and debunk misinformation. While many existing methods rely on reverse image search (RIS) engines, these tools often fail to return results, thereby limiting their practical applicability. In this work, we address the challenging scenario where RIS evidence is unavailable. We investigate the potential of news article corpora as an alternative to RIS, linking images to relevant articles to infer their dates and locations from article metadata. We evaluate the performance of a news article retrieval pipeline, NewsRECON, which leverages a corpus of over 85,000 articles. Experiments on the TARA dataset show that NewsRECON outperforms prior work and can be combined with a multimodal large language model (MLLM) to achieve new SOTA results in the absence of RIS evidence. Furthermore, NewsRECON generalizes to the 5Pils-OOC benchmark despite geographic and temporal shifts. We make our code available.

This paper proposes a Short-Window Sliding Learning framework for real-time violence detection in CCTV footages. Unlike conventional long-video training approaches, the proposed method divides videos into 1-2 second clips and applies Large Language Model (LLM)-based auto-caption labeling to construct fine-grained datasets. Each short clip fully utilizes all frames to preserve temporal continuity, enabling precise recognition of rapid violent events. Experiments demonstrate that the proposed method achieves 95.25% accuracy on RWF-2000 and significantly improves performance on long videos (UCF-Crime: 83.25%), confirming its strong generalization and real-time applicability in intelligent surveillance systems.

Accurately estimating urban rail platform occupancy can support more informed operational decision-making by transit agencies, particularly during periods of crowding. However, sensing real-time platform occupancy remains challenging and often relies on indirect proxies, such as automatic fare collection data or staff observations. Recently, Closed-Circuit Television (CCTV) footage has emerged as a promising data source for accurate, real-time occupancy estimation. The present study investigates this approach by comparing three state-of-the-art computer vision approaches for extracting crowd-related features from platform CCTV imagery: (a) object detection and counting using YOLOv11, RT-DETRv2, and APGCC; (b) crowd-level classification via a custom-trained Vision Transformer (Crowd-ViT); and (c) semantic segmentation using DeepLabV3. Additionally, we present a novel and efficient convex ridge regression over mean-pooled segmentation features to extract counts from the generated segmentation maps while accounting for image depth and passenger dispersion along a platform. Tested on a privacy-preserving dataset, created in collaboration with the Washington Metropolitan Area Transit Authority (WMATA), and including more than 600 hours of video material, our results demonstrate that computer vision approaches can provide substantive value for crowd estimation. This work demonstrates that CCTV image data, independent of other data sources available to transit agencies, can enable real-time crowding estimation and, eventually, timely operational responses to mitigate platform crowding.

Person retrieval in surveillance videos often depends on attributes described by witnesses or operators. However, the most useful cues in practice are not always common appearance descriptions (e.g., gender, clothing color), but rare and distinctive attributes that can sharply reduce the search space (e.g., holding a weapon, lying on the ground). Existing text-based person retrieval benchmarks and methods largely focus on identity-centric retrieval with common pedestrian descriptions, leaving such retrieval-critical attributes underexplored. In this paper, we introduce Open-Attribute Person Retrieval (OAPR), a practical retrieval setting that aims to retrieve all pedestrian instances matching a given attribute query, including rare or previously unseen visual concepts, regardless of identity. To support this task, we construct EPAD, an Expanded Pedestrian Attribute Dataset with 267,885 pedestrian images and a unified vocabulary of 65 attributes, including safety-critical actions, assistive devices, and object interactions that are rarely covered in prior benchmarks. We further propose GAP-CLIP, a lightweight CLIP-based framework that learns gated attribute-aware body-part representations for OAPR. Extensive experiments on EPAD demonstrate that GAP-CLIP achieves the strongest top-K retrieval performance on the full attribute space and on out-of-distribution attributes. The code and dataset are available at https://github.com/mlnjeongpark/Open-Attribute-Person-Retrieval.

Smart healthcare monitoring systems require precise action recognition to ensure well-being and timely intervention in critical situations such as falls, particularly for mobility-challenged individuals. Existing datasets are often clip-based, lacking the frame-level detail needed to recognize actions online, as they unfold. To address this, we introduce SAFER-Activities, a dataset for fall detection and physical activity monitoring, with a dedicated subset for wheelchair use scenarios. It comprises over 66 hours of video data captured by multiple cameras, with 85,310 action instances and frame-level annotations for 30 action classes. We benchmark action recognition on SAFER-Activities with 2D and 3D skeleton models, RGB models with frozen backbones, and multimodal fusion strategies, and evaluate on in-lab, out-of-distribution, and cross-dataset test sets. Skeleton-based models generalize best under domain shift; fusing frozen RGB features with the skeleton stream improves in-domain recognition over the baseline CNN1D, most clearly on the wheelchair subset, but degrades out of distribution. Cross-dataset and qualitative evaluations confirm that models trained on SAFER-Activities transfer well to unseen environments and external fall data. To support research on robust fall detection and activity monitoring, we release the dataset and code at https://safer-activities.github.io/.

This paper proposes a novel interdisciplinary framework for analyzing police body-worn camera (BWC) footage from the Rochester Police Department (RPD) using advanced artificial intelligence (AI) and statistical machine learning (ML) techniques. Our goal is to detect, classify, and analyze patterns of interaction between police officers and civilians to identify key behavioral dynamics, such as respect, disrespect, escalation, and de-escalation. We apply multimodal data analysis by integrating image, audio, and natural language processing (NLP) techniques to extract meaningful insights from BWC footage. The framework incorporates speaker separation, transcription, and large language models (LLMs) to produce structured, interpretable summaries of police-civilian encounters. We also employ a custom evaluation pipeline to assess transcription quality and behavior detection accuracy in high-stakes, real-world policing scenarios. Our methodology, computational techniques, and findings outline a practical approach for law enforcement review, training, and accountability processes while advancing the frontiers of knowledge discovery from complex police BWC data.

Document parsing aims to transform unstructured documents into structured and machine-readable representations. Recent advances in Vision-Language Models (VLMs) have significantly advanced document parsing. However, existing approaches still face two major challenges. First, decoupled VLM-based methods heavily rely on accurate layout analysis, where geometric distortions in camera-captured documents can introduce cascading errors. Second, although end-to-end VLM-based methods alleviate the dependence on explicit layout detection, they often suffer from redundant generation, hallucinations, and insufficient structural reasoning in high-resolution scenarios. To address these challenges, we propose TeleOCR, a unified framework for document parsing. TeleOCR introduces deformation-aware learning to incorporate geometric perception into VLMs and proposes an adaptive sampling mechanism for complex layout representation. Furthermore, a content-structure decoupled learning strategy is developed to explicitly model formula grammars and table structures, enabling more effective structured representation learning. Extensive experiments demonstrate that TeleOCR achieves state-of-the-art performance across diverse document parsing benchmarks. It obtains overall scores of 96.87, 88.53 and 78.41 on OmniDocBench v1.6, Wild-OmniDocBench, and PureDocBench, respectively, and ranks first in the ICDAR 2026 Sci-ImageMiner Challenge. These results validate the effectiveness and generalization capability of TeleOCR in complex document parsing scenarios.