Papers for
video surveillance teams
Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.
Region selection improves video anomaly detection and localization
Region-VAD: Video Anomaly Localization and Detection via Region Selection
Abstract: Anomalies are local events, yet weakly supervised video anomaly detection scores them globally. Most methods pool an entire frame into a single vector, rank frames by that vector, and derive a location afterwards as a saliency map of the score. Full-frame pooling mixes the anomaly with its background, so a detector can reach competitive benchmark scores from scene context without being able to show where in the scene the anomaly occurs. We introduce Region-VAD, which first selects a region and then detects the anomaly from that region alone. Region-VAD selects an explicit rectangle over the tokens of a frozen foundation model and scores anomalousness only from the tokens inside the box, through attention pooling followed by a standard temporal head. The rectangle is not learned, it is the box in which the frozen tokens change most between consecutive segments, in all four feature projections of the encoder, and it is found by exhaustive search over the rectangles of the token grid. Only the pooling and the temporal head are trained, from video-level labels without boxes, masks or frame-level annotations, and no trained component reads a token outside the selected region. Experiments on five datasets, with one localizer configuration shared by all datasets and backbones, show that Region-VAD achieves state-of-the-art anomaly localization on UCF-Crime and MSAD at competitive detection performance.
Faithful analysis method explains video anomaly detector decisions
How to Explain your Unexplainable Video Anomaly Detector
Abstract: Weakly-supervised Video Anomaly Detection (VAD) models assign anomaly scores from high-dimensional features, and their predictions remain unexplained. Saliency maps show where a model looks but not what it relies on, and the descriptions produced by Vision-Language Models (VLMs) are generated by branches that the anomaly score never reads. To address this faithfulness gap, we propose \textbf{Explain The Unexplainable (ETU)}, a classifier-agnostic framework that audits frozen VAD models through counterfactual interventions in their feature space. ETU maps video features to a discrete dependency graph of agents, actions and outcomes ($A_r \to A_a \to A_o$), regenerates the features by graph-conditioned diffusion with selected nodes of the graph masked, and measures the change in the score of a frozen detector; one set of interventions is applied unchanged to every detector. The generator is trained only to reconstruct the input features, so it cannot learn the contrast it is asked to measure, and we validate the audit with experiments that test every alternative explanation of its results, from the cost of regeneration to random deletions of matched size. On UCF-Crime features obtained from a CLIP encoder, we show that substituting the scene semantics results in the largest drop for most detectors, and that removing the outcome chain of the graph ($Δ_{rel}$) changes the anomaly score of all six audited detectors far more than removing the same number of random nodes, even though the random deletion perturbs the features about as much. We show that this targeted behavior comes from the divergence objective of the graph embedding. Without it, the two interventions become indistinguishable, and with a divergence objective in the generator as well, the score change of the detector follows the displacement of the reconstruction rather than the semantics that were removed.
Person actions help predict group intent in vision language models
Do the Details Help the Whole? One-Way Transfer from Person Actions to Group Intent in VLMs on JRDB-Social
Abstract: Social scene datasets label people at two levels: what each person is doing and what the group is there for. Training on both levels at once is often assumed to help each of them. We test this assumption for vision-language models (VLMs) on JRDB-Social, treating person actions as the details and group intent as the whole. We fine-tune Qwen3.5 4B under eight training arms with three seeds, repeat the core arms on Qwen3.5 9B and Qwen3-VL 4B, and judge every arm with a verdict rule fixed before testing. Writing each member's actions before the intent raises intent macro-F1 from 30.1 to 31.0, and writing the intent first reaches 31.2, while action F1 stays within 0.2 points of an action-only model. Under the selected recipe, no arm trained with intent improves actions. The gain requires correct, image-grounded actions: empty action lists or actions borrowed from another group with the same intent lower intent F1. Forced-prefix tests, occlusion, member masking, linear probes and component grafting show that the intent follows the written actions, relies more on people and partly resides in the vision tower. Supplying actions as input instead of as targets hurts both levels.
Visual feedback boosts interactive person search accuracy
Interactive Person Retrieval with On-the-Fly Visual Feedback
Abstract: Traditional text-based person retrieval (TPR) assumes that a witness provides a complete description at once, whereas interactive person retrieval (Inter-PR) refines a partial description through question-answer exchanges. In this setting, the questioner inspects retrieved candidates to decide what evidence to request next, while the answerer sees only the witness-side memory and cannot report candidate-specific visual differences. Existing methods mainly learn offline question orderings, leaving this visual-feedback loop underexplored. To address this limitation, we introduce visual-feedback interactive person retrieval (VFI-PR), a new interactive retrieval paradigm in which retrieved candidates produce visual feedback that becomes evidence for subsequent questioning and re-ranking. To support training and evaluation in this setting, we construct VFI-PEDES, a dataset and evaluation protocol for visual-feedback interaction, and propose VFI-ReID, a framework that learns to use visual feedback during interactive person retrieval. Through the Dynamic Accumulated-evidence Retriever (DAR) and retrieval-aware question optimization, VFI-ReID adapts retrieval and question generation to evolving evidence states, turning visual feedback into complementary evidence for subsequent retrieval. Experiments show that VFI-ReID consistently improves retrieval across VFI-PR interaction stages, demonstrating the utility of visual feedback for interactive person retrieval and outperforming existing Inter-PR baselines.
Cross view system tracks and captions people in videos consistently
CRTrack-Cap: A New Benchmark for Cross-View Dense Video Object Captioning
Abstract: Dense video object captioning (DVOC) localizes, tracks, and describes object trajectories within a video. Existing methods process each camera view independently, producing separate camera-local tracklets and captions for the same person across cameras. These outputs lack a unified description and leave complementary appearance evidence across views unused. We therefore formulate cross-view DVOC (CVDVOC), which associates these tracklets into scene-level global trajectories and generates one caption for each trajectory from synchronized views. To support this task, we construct CRTrack-Cap from CRTrack by auditing text-identity links and converting usable referring expressions into canonical captions. It retains 425 global trajectories and 838 local tracklets across 13 scenes, with canonical captions for 335 identities. We adapt CHOTA to the cross-view setting as CV-CHOTA to jointly evaluate tracking and caption quality. Our reference framework combines View-Exclusive Cross-Camera Association (VECA) for grouping tracklets with Conflict-Evidence Gating (CEG) for integrating caption evidence using its reliability and disagreement across views. Against three single-view methods adapted with MvMHAT for cross-view association, our framework achieves CV-CHOTA scores of 83.43 and 33.48 on the scene-disjoint in-domain and cross-domain tests, respectively. Together, CRTrack-Cap and our framework provide a benchmark and a strong baseline for describing the same person consistently across camera views.
Language queries improve multi-camera tracking of multiple targets
Refer-CityFlow and M3Track: A Benchmark Dataset and Reference Framework for Language-Driven Multi-Target Multi-Camera Tracking
Abstract: Referring multi-object tracking enables users to specify targets through natural language, but existing Refer-MOT benchmarks primarily focus on single-camera settings. We formalize Referring Multi-Target Multi-Camera Tracking (Refer-MTMCT), where free-form queries specify identity-consistent trajectories to be recovered across a network of sequential, sparse-overlap cameras. We introduce Refer-CityFlow, a benchmark built on CityFlow's global cross-camera identity annotations and augmented with language queries requiring joint language grounding, cross-camera association, and spatio-temporal reasoning. Refer-CityFlow covers 96 videos from 40 roadside cameras with 660+ identity-consistent cross-camera trajectories, 4,362 trajectory-level descriptions, and 7,699 queries, including 1,699 real-user queries collected from 50 participants. Reference experiments on the four-camera Scenario 02 show that single-camera referring trackers reach 14.95-18.28 HOTA on real-user queries, while the evaluated cross-view method achieves about 0.05 HOTA in direct transfer. To establish reference performance, we provide M3Track, a modular multimodal reference framework in which a large language model (LLM)-based agent orchestrates interchangeable detection, tracking, and cross-camera association modules. M3Track reaches 44.10 HOTA and 65.40 IDF1 on the same real-user query set. The project repository is available at https://github.com/phuongnguyen194/Refer-CityFlow-and--M3Track.
CoDecide speeds up video analytics by decoding only new content
CoDecide: Content-Adaptive Video Decoding for High-Throughput Video Analytics
Abstract: Analytics on video archives are bottlenecked by decoding. In a dense pipeline that runs a detector on every frame, decoding is a small fraction of the runtime, but once the detector is restricted to selected frames, decoding takes over as the main cost. We introduce CoDecide, a retrospective analytics system that only decodes the frames where new content appears, using signals from the compressed bitstream to find them. Motion tells us something is moving, but not whether it is new to the scene or has been there the whole time. To make that distinction, we supervise a lightweight compressed-domain student on a label-free novelty signal from a frozen DINOv2 teacher, which fires on semantically new regions rather than on any motion. Consequently, the student model generalizes to new camera deployments without requiring per-camera retraining. At inference, it decides which frames to decode and which regions to reconstruct. Detections from the decoded frames are propagated to the skipped frames using motion vectors. We evaluate CoDecide with a leave-one-dataset-out protocol on VIRAT, MEVA, and ShanghaiTech. Against a dense per-frame detector, CoDecide recovers more moving-object detections than prior compressed-domain selectors at an equivalent decoding budget, outperforming even a competitor trained directly on the target camera. CoDecide runs 15 to 24x faster than a pipeline that decodes and detects every frame. Code is available at https://github.com/shristy51/CoDecide.
Vision language model clusters faces online in long videos
VISTA: Vision-Language Integrated Semantic Triage Architecture for Online Face Clustering in Long Videos
Abstract: Clustering faces by identity in long, continuous video streams is a challenging task that serves as a building block for human-centric video analysis. The majority of existing face clustering models are offline, i.e., they assume the entire data to be available altogether. In many practical scenarios, however, the entire data is either unavailable or poses computational challenges to be processed in its entirety. A handful of online methods that exist rely on geometric visual features and simple thresholding techniques, which fail when the faces exhibit significant appearance variations in long, unconstrained videos. To this end, we present VISTA, the first vision language framework for online face clustering in long videos. VISTA leverages semantic reasoning in a controlled, uncertainty aware fashion to maintain both high cluster purity and long range identity continuity. This makes it robust to the variations in illumination, pose, and costume changes that the faces and characters exhibit in long real world videos. Extensive experiments on the VPCD benchmark dataset (with 15 full episodes from The Big Bang Theory [2007-2019], Buffy the Vampire Slayer [1997-2003], and Sherlock [2010-2017]) demonstrate that VISTA achieves a robust precision and recall balance, consistently improving over the strongest matched online unsupervised baseline (COFC) under identical detector, embeddings, and evaluation protocol. Code and supplementary material: https://github.com/SkyJiashu/VISTA.
Dynamic object detection improves by mixing motion and depth cues
DynOSeg: Dynamic Object Segmentation via Motion-Geometry Fusion
Abstract: Moving Object Segmentation (MOS) detects and separates dynamic objects from the static background in a video, which plays a fundamental role in dynamic-scene understanding. Most MOS methods rely on pure visual motion cues alone, such as optical flow or point tracks, which is inherently ambiguous due to the compounded camera and object motions as well as motion-induced appearance changes, e.g. shadows and reflections. Naive fusion of additional information such as depth and semantics, however, cannot leverage their complementarity to the fullest extent. We therefore propose DynOSeg, a novel MOS approach that takes on a two-stage fusion structure. DynOSeg first combines a geometry-aware residual map and depth encoding into a geometric representation of motion, delineating camera motions and object dynamics. We then further incorporate semantic features to refine object understanding. We have additionally curated a diverse training corpus including CARLA-MOS, a new synthetic urban-driving dataset for MOS training. Our experiments show that DynOSeg consistently outperforms published state-of-the-art MOS methods across a diverse range of datasets. Our code and pretrained models can be found at https://github.com/ACFR-RPG/DynOSeg
Vision language model improves person re-identification accuracy significantly
VLM-as-a-Judge for Person Re-Identification
Abstract: Cloth-changing person re-identification (CC-ReID) is still very challenging, and no method clearly dominates: methods that lead on one benchmark collapse on the others, because they rest on different identity cues. We show that a general-purpose vision-language model (VLM), used zero-shot as a judge for reranking a short candidate list, beats the expert retrieval models it reranks by a wide and consistent margin. On the four scenarios of CHIRLA, a long-term CC-ReID benchmark that no publicly released Re-ID model is trained on, reranking the candidates of two frozen experts raises rank-1 on every scenario, by 12.9 points on average over the best expert and 9.4 over the best naive ensemble of the two, with no component fine-tuned on the target data. Merging both experts' shortlists matches or beats reranking the stronger expert's shortlist alone, at lower cost. Introducing a VLM does, however, come at a cost: almost all of the pipeline's FLOPs are spent on it. We therefore borrow a criterion from ensembling and invoke the VLM judge only where the two experts disagree at rank 1. This threshold-free gate removes 40% of the calls, and a comparable share of total compute, with no significant drop in rank-1, trading 1.8 to 3.8 points of mAP. Judging remains the dominant cost, but on a benchmark where dedicated experts stall, we find a frozen general-purpose model to be the strongest judge of identity. The code is available at https://github.com/bdager/JudgeReID.
Tracking points beyond camera view using 360 degree video expansion
TAP-Out: Tracking Any Point in 360° via Outpainting
Abstract: Tracking points that leave the camera's field of view (FoV) requires reasoning about unobserved scene dynamics, a fundamentally different problem from tracking visible correspondences. We present TAP-Out, an offline method that makes this out-of-view (OOV) reasoning explicit by leveraging generative video outpainting as a world-model prior. Given a narrow-FoV input video, TAP-Out outpaints a complete 360° equirectangular video, locates target objects within the panoramic scene via video object segmentation, and synthesises object-centred perspective crops on which standard in-frame trackers operate. This decoupled design composes off-the-shelf foundation models without requiring task-specific architectural modifications. On the TAPVid360 benchmark, TAP-Out achieves state-of-the-art performance, improving OOV tracking accuracy by approximately 3x over the best prior method. We demonstrate its flexibility on out-of-frame object segmentation and detection and we provide detailed diagnostic analyses across motion regimes, static versus dynamic content, and hallucination quality, characterising when and why the approach succeeds or fails.
Panoramic video reasoning benchmark improves cross-view and time understanding
Think in 360°: Benchmarking and Bootstrapping Panoramic Video Reasoning
Abstract: A panoramic video captures all directions around the camera, but relevant evidence can appear in different directions and at different times. Understanding it requires models to connect observations across the viewing sphere and time. We introduce PanoVideoBench, the first manually annotated benchmark for comprehensive panoramic video understanding. Its 1,000 questions span five categories and 15 question types, with diagnostic annotations for target search and panoramic capabilities. Evaluation of 11 proprietary, open-source, and panoramic-specialized models identifies cross-view tracking and sphere-time evidence integration as their weakest capabilities. To strengthen these capabilities, we construct PanoVideoCoT, the first reasoning dataset grounded in real panoramic video, through sphere-time-grounded synthesis that converts verified panoramic observations and successful agentic explorations into 13,465 QA-CoT pairs. Starting from a general video MLLM, PanoVideoReasoner learns from this corpus through Panoramic CoT SFT and Evidence-Privileged On-Policy Self-Distillation, a panoramic instantiation of Vision-OPD's OPSD in which the teacher uses verified perspective views to guide student-generated trajectories. It reaches 55.7% on PanoVideoBench, improving the backbone by 12.5 points and the previous SOTA by 2.6. The gains concentrate on the same spatial, cross-view, and temporal capabilities exposed by the benchmark, showing that grounded sphere-time supervision can equip a general video MLLM with panoramic reasoning.
Hierarchical step decomposition improves online video step recognition and timing
Hierarchical Step Decomposition for Training-free Online Video Step Grounding
Abstract: Given a set of procedural steps, Video Step Grounding (VSG) aims to identify which steps occur in a video and localize when they are performed. Existing methods are either offline, requiring access to the full video before making predictions, or online, but relying on fixed-length video segments producing noisy, over-segmented outputs. In this work, we propose Hierarchical Step Decomposition (HSD), a training-free framework for online VSG that leverages the semantic understanding capabilities of Large Multimodal Models. HSD addresses two central challenges in online grounding: constructing semantically coherent temporal segments from a streaming video, and bridging the semantic gap between coarse procedural step descriptions and visual observations. To construct elementary temporal units, HSD incrementally groups incoming segments into semantically consistent events, using an anchor caption that is continuously validated against the visual stream. Based on these events, we perform zero-shot procedural step classification and selectively refine uncertain predictions by decomposing candidate steps into finegrained substeps that capture more nuanced visual evidence. By operating on semantically coherent events rather than every fixed-length segment, HSD reduces redundant computation and produces more stable predictions. Experiments on HT-Step, Ego4D Goal-Step, and CrossTask show that HSD substantially outperforms state-of-the-art methods, overall achieving better step recognition, more accurate temporal localization, and faster inference.
Track query updates improve identity tracking in multi-object video analysis
Calibrating Track-Query Updates at Test Time for Multi-Object Tracking
Abstract: Multi-Object Tracking (MOT) requires localizing multiple objects and maintaining their identities over time. Recent query-propagation trackers carry target-specific representations across frames and update them with current-frame image features, yet identity association remains difficult when visually similar targets overlap or cross. During such interactions, current-frame query updates may contain components directed toward nearby active tracks, which may affect identity association in later frames. To investigate this issue, we analyze track-query updates preceding identity switches (IDSWs), where the same target is assigned a different track ID. Our analysis shows that (i) propagated track-query representations change more abruptly before IDSWs, (ii) current-frame updates have larger positive projections along directions toward other active tracks, and (iii) bounding-box intersection over union (IoU) retrieves the counterpart track involved in a subsequent IDSW with high recall when that track remains active before the switch. Motivated by these findings, we propose Test-time Track-Query Calibration (TQC), a training-free and gradient-free method for query-propagation trackers. TQC calibrates the tracker output before propagation using a bounded correction estimated from update components directed toward nearby active tracks. It requires only track-query representations and bounding boxes available during inference, without retraining or architectural modification. Across nine DanceTrack and SportsMOT test settings, TQC improves HOTA and AssA in all settings and IDF1 in eight, with an average HOTA gain of +0.38 and limited inference overhead. Controlled variants on six validation settings further show that TQC's correction direction yields more consistent HOTA improvements than alternative directions with matched correction norms.
EARS uses sound and motion to pick key video frames for analysis
EARS: Evidence-Aware Retrieval via Sound and Motion for Budgeted Video Reasoning
Abstract: Uniform frame sampling can miss brief evidence in sparse-event videos when the VLM sees only K frames. We propose EARS (Evidence-Aware Retrieval via Sound and motion), a training-free, query-free front-end that ranks frames using optical-flow motion and audio energy, then applies temporal non-maximum suppression for diversity. The evidence score alone has frame-level AP 0.39; used only to select frames for the VLM, EARS with temporal diversity reaches localization AP 0.94, compared with 0.88 under Uniform sampling. In the updated matched study, at K = 1 EARS reaches XD-subset F1 0.660 versus 0.614 for centered Uniform (the paired interval includes zero); earlier backbone studies use separate protocols. On mostly-silent UCF-Crime, however, EARS slightly trails Uniform. A single configuration is used across both benchmarks; the new controls do not repeat the original held-out search. EARS therefore targets low-budget videos whose salient evidence aligns with motion or audio; on dense narratives or stealthy events, uniform or semantic selection remains preferable, and cheap modality statistics cannot reliably route between them. Code: https://github.com/mikeslin-ir/EARS
Efficient zero-shot video anomaly detection improves speed and accuracy
Efficient Zero-Shot Video Anomaly Detection via Signal-Aware Adaptive Fusion (SAAF)
Abstract: Deploying Vision-Language Models for video anomaly detection confronts a fundamental constraint. Their semantic reasoning demands computational budgets incompatible with the scale of real-world video streams. We present Signal-Aware Adaptive Fusion (SAAF), a framework that achieves efficient zero-shot anomaly detection through three key innovations. First, we introduce a dual-signal adaptive sampler operating in semantic embedding space: a delta signal captures sudden events via frame-to-frame cosine distance, while a drift signal detects static and gradual anomalies through deviation from rolling temporal context. Their OR-gated combination with adaptive EMA-based thresholding provides comprehensive anomaly coverage without training data. Second, we propose a threshold-gated cascaded architecture where lightweight frame-level scoring precedes expensive video-level temporal analysis, invoking it only when confidence warrants additional context. Third, we design a signal-aware weighted fusion mechanism that dynamically adapts score combination based on which signal triggered frame selection. Across four benchmarks, SAAF delivers competitive accuracy at substantially lower cost. Among training-free zero-shot methods, SAAF sets a new state of the art on XD-Violence (92.07%), MSAD (86.70%), and ShanghaiTech (80.54%) AUC-ROC, with XD-Violence and MSAD also surpassing supervised baselines. SAAF sustains 44.95, 48.61, and 41.06 FPS on XD-Violence, UCF-Crime, and MSAD, a 2.43$\times$, 2.63$\times$, and 2.22$\times$ throughput improvement over the prior best zero-shot method. Code: https://github.com/kdawoud91/SAAF
Motion guided vision language model speeds up video anomaly detection
MoG-VLM: Efficient Video Anomaly Detection through Motion-Guided Vision-Language Models
Abstract: Vision-Language Models (VLMs) have shown strong potential for video anomaly detection, but dense frame-level inference makes them impractical for real-time deployment. Existing acceleration commonly relies on uniform sampling, which ignores content dynamics and can either waste computation on static segments or miss localized anomalies. We propose MoG-VLM a motion-adaptive anomaly detection framework that leverages motion purely as a lightweight control signal to decide when VLM inference is necessary. To this end, we introduce Temporal Gradient Magnitude (TGM) which performs content-aware sampling to concentrate computation on informative regions while avoiding redundant processing. We further introduce a hierarchical dual-stream design in which dense multi-frame VLM reasoning is activated only around frames with elevated anomaly likelihood, via anchor-triggered context-window expansion with early termination. A fusion module then reconciles these instantaneous semantic cues with temporal action dynamics. Across four benchmarks, our method achieves 91.91%, 84.30%, 87.88%, and 78.96% AUC-ROC on XD-Violence, UCF-Crime, MSAD, and ShanghaiTech, respectively, establishing new state of the art on three benchmarks under the zero-shot, training-free setting. On XD-Violence, we improve over the previous best result by +0.57% while delivering a 1.31x inference speedup. These results demonstrate that content-aware allocation of VLM capacity, processing fewer frames more intelligently rather than all frames uniformly, is a more effective axis of progress than uniformly densifying VLM inference across frames. Code is available on GitHub: https://github.com/kdawoud91/MoG-VLM.
Pose refined model improves zero shot recognition of social bodily behaviors
PRIMA: Pose Refined Inductive Motion Adapter for Zero Shot Social Bodily Behavior Recognition
Abstract: Recognizing fine-grained bodily behaviors, such as self-grooming, postural shifts, and backchanneling, is a useful intermediate step for computational social signal analysis. But the behaviors that matter vary across social contexts, and retraining a model for each new taxonomy is expensive. Vision-language models (VLMs) can adapt to new categories through text prompts, yet they lack sensitivity to body structure and often confuse subtle postural distinctions. We propose PRIMA (Pose Refined Inductive Motion Adapter), a lightweight module that injects a body-structure prior into frozen VLMs using human pose as a training-time supervisory signal, requiring no pose input at inference. PRIMA separates a model-specific projection head from a shared core that encodes transferable body-configuration knowledge; adapting to a new VLM requires retraining only the head. We train PRIMA on a micro-action dataset and evaluate entirely through zero-shot prompting. The adapter improves recognition on its training domain, transfers to additional VLM backbones at different scales with the core frozen, and generalizes to two unseen target datasets from social psychology and daily activity recognition. In a supporting downstream study, the improved behavior predictions also yield higher correlations with human ratings of rapport and dominance in a collaboration context. Within the scope of the tested models and indoor datasets, the results indicate that pose-guided training can produce body-structure priors that generalize across unseen behavior vocabularies and can be partially reused across VLM backbones while preserving RGB-only inference.
Transformer improves detection of changing relationships in video scenes
RTAformer: Relation-Transition-Aware Transformer for Video Scene Graph Generation
Abstract: Video scene graph generation (VidSGG) aims to capture objects and their evolving relationships in videos. This requires accounting for both the persistence of object identities and abrupt changes in relationships. Existing methods aggregate information across frames to exploit temporal context, but an emphasis on consistency can obscure these changes. As a result, a model may retain its previous prediction even after the underlying relation has changed. We refer to this failure mode as relational semantic inertia. To address this issue, we propose Relation-Transition-Aware Transformer (RTAformer), a one-stage framework that separately models entity persistence and relation changes. It injects calibrated differences between adjacent-frame relation queries to guide predicate updates, while cross-frame instance alignment during training helps reduce cross-frame representational drift. Experiments on Action Genome show improvements in recall and mean recall over existing methods, with ablation studies supporting the contributions of the proposed components and comparisons using matched backbones showing larger gains on relation-transition frames than on non-transition frames.
Multi feature analysis improves detection of conversation groups
Breakdown of Conversational Involvement: A Joint Multi-Modal Analysis of Conversation Floors and F-formation Detection with Multiple Features
Abstract: Interactions happen universally and spontaneously in daily lives. Studying involvement in interactions helps us analyze who can influence who and has a wide potential in applications. Specifically, we consider conversational involvement in free-standing conversations. We study two operationalizations of an FCG: F-formations and conversation floors, and propose that current assumption that F-formations capture single conversations is insufficient. To illustrate how different implementations could impact the detected F-formations, we employ three analyses. First, we propose that speaking status can be used for estimating conversation floors, and leveraged it to analyze floors within F-formations. Second, we analyze spatial characteristics of the detection results by applying different feature sets on chosen baselines, and find that groups resulting from head features are more likely to be subsumed by groups detected using other features. Finally, we do a joint analysis which combines the spatial features and floor patterns in the conversation. We observe that certain pipelines can detect groups with single floors from upper body features, while retaining F-formations with lower body features. We conclude that a more detailed theory and framework is needed to holistically demonstrate conversational involvement within interactions.
Video anomaly detection suffers from motion observation quality shortcuts
Auditing Observation-Quality Shortcuts in the Evaluation of Person-Centered Motion for Video Anomaly Detection
Abstract: Video anomaly detection (VAD) identifies deviations from normal patterns, but such deviations do not necessarily correspond to safety-critical events. We focus on human-centered emergencies and violence and investigate whether motion-based anomaly discrimination reflects task-relevant motion information or observation-quality differences arising from person detection, pose estimation, and tracking. We introduce an observation-quality-aware evaluation framework that combines quality diagnostics, quality balancing, motion orthogonalization, and robustness analyses. On human-centered categories of UCF-Crime, quality-only features match or exceed the discrimination of multi-cue motion in the original cohort, revealing a strong observation-quality shortcut. After cardinality matching brings all 11 measured quality variables below a prespecified marginal balance threshold, multi-cue motion consistently outperforms quality-only features across Logistic Regression, Random Forest, and RBF-SVM, yielding ROC-AUC gains of 0.046-0.141. Because nonlinear quality-only prediction remains above chance after matching, we interpret this result as additional discrimination beyond measured marginal quality rather than as evidence of quality-free or causal motion understanding. These findings show that high VAD performance should not be interpreted as evidence of abnormal-motion modeling without auditing the reliability of the person-observation pipeline. Our study provides a systematic protocol for evaluating observation-quality shortcuts and for assessing whether motion-based discrimination survives explicit control of detection, pose-estimation, and tracking reliability.
Tracking moving objects in driver videos with camera motion removal
Referring Multi-Object Tracking in Moving-Camera Videos via Global Motion Compensation
Abstract: Referring multi-object tracking (RMOT) takes a video and a language expression as input and tracks all referred objects. Many tracking requirements involve how an object moves rather than how it appears. However, in a video captured by a moving camera, a parked vehicle may appear to move, while a moving vehicle may show little displacement. Existing RMOT methods relate motion with text but do not explicitly remove camera-induced motion. In this paper, we propose extracting residual motion across frames by estimating camera motion in driver-view videos and compare motion characteristics with the query expression. We consider the motion-matching extent and integrate it with the RMOT method's prediction result through late fusion. In the evaluation, we verify the performance gain of taking the motion compensation module as a plug-in across different RMOT hosts.
Video object segmentation struggles with brief object appearances
When Predicting Nothing Beats SAM 3: Revisiting Evaluation in Video Object Segmentation
Abstract: Video Object Segmentation (VOS) in complex and long videos is increasingly important for real-world applications, where target objects often appear only intermittently within long temporal horizons. However, existing benchmarks largely focus on temporally salient objects that remain visible for most of the video. To address this gap, we introduce FaVOS (A Benchmark for Video Object Segmentation with Fractional Temporal Visibility), a benchmark designed to evaluate VOS methods under low temporal visibility. We show that, in this regime, the standard J&F metric can collapse VOS evaluation into absence classification, because empty predictions receive high rewards on target-absent frames. Consequently, even a trivial empty-mask predictor can outperform strong models such as SAM 3, revealing a fundamental mismatch between current metrics and practical VOS performance. To mitigate this issue, we propose Volumetric J&F, which evaluates mask sequences as spatio-temporal volumes and reduces the dominance of target-absence rewards while preserving sensitivity to segmentation quality and temporal structure. Project page: https://aidaslab.github.io/FaVOS.
Ugo tracker improves multi-object video tracking with pixel masks
UGO: Unified Architecture for General Multi-Object Tracking by Segmentation
Abstract: General multi-object tracking (GMOT) tracks all instances of a user-specified category from a single first-frame exemplar. Prior work relies on bounding boxes and surrogate training, and struggles with non-rigid objects, crowded scenes, and distractors. We introduce UGO, a unified GMOT tracker that pairs a pretrained exemplar-conditioned detection head with an instance-propagation head in a common architecture. A novel training-free, energy-minimization consolidation method converts overlapping proposals into exclusive pixel-wise masks and detections, resolving over-segmentation, duplicates, and conflicts. A hierarchical memory spanning global and instance levels improves recall and per-instance segmentation accuracy using a new memory management protocol. UGO sets a new state-of-the-art on GMOT benchmarks and video object counting, and is competitive with specialist MOT methods, establishing a strong paradigm for unified, open-category multi-object tracking.
Hyperspectral tracker improves video target tracking with spectral memory
HyperDAM: Hyperspectral Distractor-Aware Memory with Amodal Expansion for SAM 3 Tracking
Abstract: Hyperspectral video provides material cues that can disambiguate targets with similar false-color appearance, yet foundation-model trackers update memory primarily from spatial and appearance evidence. We present HyperDAM, a DAM4SAM3-based hyperspectral tracker with three principal contributions. First, HOTC2026-Modal adds human-verified frame-wise modal masks and mask-tight boxes to all 481 organizer-provided HOTC 2026 videos. Second, a frame-zero-calibrated HSI gate rejects spectrally inconsistent updates to the distractor-resolving memory (DRM) without altering the current prediction. Third, a causal spatiotemporal expander adds outward-only amodal corrections from frozen SAM features. Static-scene recovery and empty-mask RTS smoothing address target switches and full occlusion. Model selection prioritizes cross-domain robustness over leaderboard-specific optimization. The final system ranked second in HOTC 2026, achieving 68.0093% AUC and 87.7703% DP@20 in the organizer's private evaluation.
Multi-camera pedestrian location without calibration or training needed
CAT-Free: Multi-View Pedestrian Localization without Calibration, Annotations, or Target-Scene Training via Adaptive Geometric Filtering
Abstract: Multi-camera pedestrian localization is useful for wide-area monitoring in public and commercial spaces. However, deploying these systems often requires considerable setup for each new environment. Existing methods typically require camera calibration, position annotations, or target-scene training. CAT-Free removes all three requirements. It uses synchronized RGB video as its only scene-specific input. Camera configuration is estimated directly from the video. Pedestrian locations are then estimated by combining observations from multiple cameras. Automatic camera estimation is not always accurate. This can produce unreliable pedestrian locations. CAT-Free therefore introduces two adaptive geometric filters. They remove unreliable position estimates. Their thresholds are estimated from each input sequence. CAT-Free achieves 82.5, 84.5, and 65.7 MODA on WildTrack, MultiviewX, and GMVD. It uses no supplied calibration, position annotations, or target-scene training. Published methods using such scene-specific information report 88.2--95.0 MODA on WildTrack and 83.9--96.5 on MultiviewX under their respective protocols. CAT-Free also transfers without retuning. It reaches 74.9 MODA on four additional sequences and 78.6 on an unseen 8-camera installation. Finally, localization uncertainty predicts MODA with $r=-0.98$. This provides a label-free estimate of localization reliability.
Pipeline filters miss workers in rare low poses on construction sites
Auditing Quality Filters for Long-Tail Human Data Curation
Abstract: Robots on construction sites must detect workers who are kneeling or bending, which we call low poses. These workers can be lost from training datasets during automatic labeling. We study a pipeline that detects people, estimates their body joints using NLF, and groups similar poses. Low poses account for only about 2 percent of the retained examples. This low share may partly reflect the pipeline's quality filter, which rejects examples with low detection confidence or uncertain joint estimates. We examine this filtering using four alternative pose clues: bounding-box shape, vertical body span, pose grouping aligned to the scene's vertical direction, and image appearance. All four suggest that low poses are rejected by the filter more often. Separately, controlled simulated scenes show that a person detector fine-tuned on a public construction dataset misses more workers in these poses even when we correct their bounding box height is matched to that of standing workers. These findings suggest that low poses are scarce and hard to find, and we cannot rely on bounding boxes or poses for long-tail human data curation.
Lifecycle-aware memory improves multi-object tracking with SAM2 models
LiAM-SAM: Lifecycle-Aware Memory for Robust SAM2-Based MOT
Abstract: Segmentation-based multi-object tracking (MOT) with foundation video models such as SAM2 offers strong localization quality, yet remains fragile in crowded, real-world scenes. In detector-prompted SAM2 pipelines, failures typically arise at three stages of the object lifecycle: (i) erroneous or duplicate track initiation, (ii) memory drift during close interactions, and (iii) unreliable re-identification after long occlusions or re-entry. These errors corrupt object memory and accumulate over time, making long-horizon tracking unstable. In this paper, we reframe MOT as a lifecycle memory integrity problem. We present LiAM-SAM, a Lifecycle-Aware Memory (LiAM) framework with targeted mechanisms for each of the three failure modes. At track birth, to prevent faulty or duplicate initiations, we apply contrastive track initiation, which conditions each prompt on existing nearby tracked instances. To preserve memory integrity during strong interactions, we introduce motion- and geometry-grounded memory correction that resolves interaction confusions and suppresses drift. For reliable re-identification after disappearance, we maintain an adaptive context memory that promotes diverse and trustworthy references as long-term identity anchors. Finally, similarity aware spatial pruning optionally selects the memory tokens to retain at cross-attention time, improving efficiency with minimal accuracy loss. LiAM-SAM represents a modular, detector-agnostic, SAM2-based MOT system that achieves state-of-the-art HOTA and IDF1 on the evaluated benchmarks. In association-challenging environments, our ablations show that LiAM improves a detector+SAM2 baseline by +10.5 HOTA, +17.4 AssA, and reduces identity switches by 96%.
Multi-object tracking improved by direction-aware occlusion handling
DOA-SORT: Directional Occlusion-Aware Multi-Object Tracking with Distributional Observations
Abstract: Identity association in multi-object tracking (MOT) is vulnerable to partial occlusion, truncated detections, and fluctuating confidence scores. Existing motion-dominant trackers commonly represent occlusion as a scalar penalty. This treatment misses the directional observation bias caused by occlusion: left, right, top, and bottom occlusions distort the location and shape of a detection in different ways. We propose \ours{} (Directional Occlusion-Aware SORT), an online and training-free tracker that models these biases explicitly. First, it infers a soft front--back ordering from box overlap and relative bottom positions, and estimates directional occlusion coverage and depth. It then constructs a mixture of one clean and four directional occlusion observation components. The model uses a five-dimensional observation comprising box center, area, confidence, and aspect ratio, and adapts observation noise to predicted occlusion and detection confidence. The directional mixture likelihood is used in high-confidence association, low-confidence association, and track recovery; ambiguity penalties and local order-consistency swaps further reduce identity errors among nearby objects. On the DanceTrack validation split, \ours{} improves HOTA from 63.00 to 66.34, AssA from 45.10 to 49.57, and IDF1 from 62.19 to 65.28 over OA-SORT with the same detector and evaluation protocol. The gains are concentrated in association quality while detection accuracy remains stable. Additional local evaluations on MOT17 and MOT20 train splits characterize cross-dataset behavior under the same no-ReID tracking protocol.
Simulated video features help find people from text descriptions
SCOUT: Sim-to-Real Text-Based Person Retrieval by Embedding-Space Prediction over Frozen Video Features
Abstract: Text-based person retrieval under a sim-to-real gap (synthetic training data, a real-image gallery) is usually tackled with costly fine-tuned cross-encoders. We ask whether a frozen-encoder system can compete. We present SCOUT, which casts cross-modal retrieval as prediction in embedding space. A trainable predictor maps the patch tokens of a frozen video encoder into the embedding space of a frozen text encoder under a bidirectional InfoNCE objective, and no encoder is fine-tuned in the base model. The video encoder is V-JEPA, the text encoder is EmbeddingGemma, and the predictor is initialized from a Qwen3.5-0.8B decoder. We make three findings. First, the best frozen text encoder is simply the one whose geometry best matches the video features. A training-free alignment score ranks three candidate text encoders in the same order as their retrieval accuracy on our held-out split (Spearman $ρ= 1.0$); a fourth, LLM-based encoder shows the rule is metric-dependent, holding for a neighborhood-overlap score ($ρ= 0.8$) but not for a linear probe ($ρ= -0.2$). Second, two precision-targeted levers, parameter-efficient ExPLoRA adaptation of the video encoder and a training-free attribute-decomposed reranker built on a vision-language model, improve the top-rank precision that otherwise limits the frozen system, adding 2.2 points of leaderboard R@1. Third, a local-versus-public calibration study explains which interventions transfer to the real domain. On AI City Challenge 2026 Track 4 the full retrieve-fuse-rerank system reaches 84.25 mAP@10 on the final leaderboard, while a single frozen model submitted alone reaches 60.63. Our trained components cost about 95 GPU-hours. CMP, the dataset authors' fine-tuned cross-encoder that trains for sixteen GPU-days, is one fusion member of the full system, not an alternative. Code and annotations: https://github.com/abtraore/SCOUT-ECCV
Video anomaly detection improved with training-free severity probing
Probe-VAD: Ordinal Likelihood Probing for Training-Free Video Anomaly Detection
Abstract: Video anomaly detection (VAD) aims to localize anomalous events in untrimmed videos. Vision-language models (VLMs) provide rich visual understanding for training-free VAD, but existing approaches impose restrictive interfaces between visual understanding and anomaly scoring. Caption-based pipelines compress visual evidence into text, potentially discarding subtle cues, while direct numerical generation forces the model to express its judgment through a small set of predefined scores. Such interfaces can obscure subtle differences in anomaly severity, causing visually distinct clips to receive similar representations or scores and thereby limiting the resolution of anomaly ranking. We propose \textbf{Probe-VAD}, an ordinal binary-probing framework that directly probes severity preferences from a frozen VLM. Given raw video clips, Probe-VAD queries ten ordered severity thresholds and extracts constrained \textit{YES}/\textit{NO} continuation likelihoods. Their normalized preferences form a cumulative severity profile, from which tail evidence is aggregated into a continuous anomaly score, with isotonic projection enforcing ordinal consistency. Experiments on public VAD benchmarks demonstrate superior performance with low computational cost. Probe-VAD provides a simple interface for translating frozen VLM visual understanding into continuous, rank-sensitive anomaly scores without task-specific training or caption-based compression. Code is available at: https://github.com/yvestine/COVAS-VAD.
Video segmentation predicts object movement without extra inputs
DynEoMT: Learning Object Dynamicity from Online Segmentation Queries
Abstract: Video segmentation models recognize and track objects over time, but they do not indicate whether each segmented region moves independently of the observing camera. This dynamicity attribute cannot be inferred from semantics alone and is confounded by camera ego-motion. We introduce \method, an online framework that augments query-based video segmentation with region-level dynamicity prediction. It jointly produces the original segmentation outputs and a dynamic or static state for each predicted region. At inference, DynEoMT uses only the current frame and propagated queries, without optical flow, depth, camera pose, previous RGB frames, or feature maps. Because established video segmentation benchmarks do not annotate this attribute, we also introduce a class-agnostic offline supervision pipeline using camera-compensated optical flow and confidence-aware temporal filtering. Across VIPSeg, OVIS, YouTube-VIS 2022, and VSPW, DynEoMT achieves balanced accuracies of 84.3, 68.0, 68.6, and 87.6, respectively, while largely preserving segmentation performance. These results show that segmentation-region dynamicity can be learned from propagated queries, enabling its online prediction without a dedicated motion-processing pipeline at inference. The complete code will be released as open source to enable full reproduction of the method and experiments.
Black-box attack lowers accuracy of human pose and action models
A Black-Box Adversarial Attack on Human Pose Estimation and Keypoint-Based Action Recognition Models
Abstract: Human pose estimation and keypoint-based action recognition models are increasingly deployed as components of video understanding pipelines, yet their vulnerability to adversarial attacks remains insufficiently studied. Temporally coherent black-box attacks have been previously studied in visual object tracking, where the attack feedback can be defined using bounding-box overlap measures such as Intersection over Union (IoU). However, human pose estimation produces keypoint configurations rather than enclosing boxes, making box-level similarity poorly suited for measuring pose degradation. We propose OKS Attack, a decision-based black-box attack that uses Object Keypoint Similarity (OKS) as the attack feedback signal, directly targeting the spatial structure of human poses rather than their enclosing boxes. Experiments on the Penn Action dataset show that OKS Attack consistently reduces pose quality across evaluated pose estimators, with mean OKS decreases ranging from 0.0802 to 0.1494. In a downstream cross-dataset action-recognition evaluation, the attack reduces accuracy by 6.18 to 13.86 percentage points and outperforms query-matched random-noise perturbations. The attack is effective across both top-down and single-stage pose estimation models. The source code will be made publicly available at https://github.com/KacperM33/OKS_attack