RWSurvil22
* *Real-World Surveillance: Applications and Challenges
* Class-aware Object Counting
* Cloth-Changing Person Re-identification with Self-Attention
* DIOR: DIstill Observations to Representations for Multi-Object Tracking and Segmentation
* Event-driven Re-Id: A New Benchmark and Method Towards Privacy-Preserving Person Re-Identification
* Fast and Lightweight Online Person Search for Large-Scale Surveillance Systems
* Fight Detection from Still Images in the Wild
* Improving Person Re-Identification with Temporal Constraints
* Learning from Synthetic Vehicles
* Multi-Target Multi-Camera Tracking of Vehicles by Graph Auto-Encoder and Self-Supervised Camera Link Model
* Multiple Object Tracking and Forecasting: Jointly Predicting Current and Future Object Locations
* On the Importance of Appearance and Interaction Feature Representations for Person Re-identification
* Real-time Bangla License Plate Recognition System for Low Resource Video-based Applications
* Semantic Segmentation Guided Real-World Super-Resolution
* Semantic-Guided Zero-Shot Learning for Low-Light Image/Video Enhancement
* Small or Far Away? Exploiting Deep Super-Resolution and Altitude Data for Aerial Animal Surveillance
* Video representation learning through prediction for online object detection
* Where are we with Human Pose Estimation in Real-World Surveillance?
18 for RWSurvil22
RWSurvil24
* *Real-World Surveillance: Applications and Challenges
* Accenture-MM1: A Multimodal Person Recognition Dataset
* Aerial View 3D Human Pose Estimation Using Double Vector Quantized-Variational AutoEncoders
* C2T-Net: Channel-Aware Cross-Fused Transformer-Style Networks for Pedestrian Attribute Recognition
* EarlyBird: Early-Fusion for Multi-View Tracking in the Bird's Eye View
* Enhancing Self-Supervised Monocular Depth Estimation via Piece-Wise Pose Estimation and Geometric Constraints
* Enhancing Skeleton-Based Action Recognition in Real-World Scenarios Through Realistic Data Augmentation
* Evaluating Supervision Levels Trade-Offs for Infrared-Based People Counting
* FedFSLAR: A Federated Learning Framework for Few-shot Action Recognition
* Filter-Pruning of Lightweight Face Detectors Using a Geometric Median Criterion
* GEFF: Improving Any Clothes-Changing Person ReID Model Using Gallery Enrichment with Face Features
* HOD: New Harmful Object Detection Benchmarks for Robust Surveillance
* Identifying Loitering Behavior with Trajectory Analysis
* Investigation of UAV Detection in Images with Complex Backgrounds and Rainy Artifacts
* Iterative Scale-Up ExpansionIoU and Deep Features Association for Multi-Object Tracking in Sports
* Knowledge-Distillation-Based Label Smoothing for Fine-Grained Open-Set Vehicle Recognition
* LiDAR-Assisted 3D Human Detection for Video Surveillance
* Multi-Head Approach with Shuffled Segments for Weakly-Supervised Video Anomaly Detection, A
* Overlooked Video Classification in Weakly Supervised Video Anomaly Detection
* Person Fall Detection Using Weakly Supervised Methods
* Security Fence Inspection at Airports Using Object Detection
* Spatio-Temporal Activity Detection via Joint Optimization of Spatial and Temporal Localization
* Swin on Axes: Extending Swin Transformers to Quadtree Image Representations
* Temporal 3D Shape Modeling for Video-based Cloth-Changing Person Re-Identification
* TextAug: Test Time Text Augmentation for Multimodal Person Re-Identification
* Unsupervised 3D Skeleton-Based Action Recognition using Cross-Attention with Conditioned Generation Capabilities
* Unsupervised Person Re-Identification in Aerial Imagery
* UPAR Challenge 2024: Pedestrian Attribute Recognition and Attribute-Based Person Retrieval - Dataset, Design, and Results
28 for RWSurvil24
RWSurvil26
* *Real-World Surveillance: Applications and Challenges
* Advancing Robust Infrared Object Detection: Practical Insights on Model Development and Evaluation
* Detecting Object Tracking Failure via Sequential Hypothesis Testing
* Detector-Augmented SAMURAI for Long-Duration Drone Tracking
* Exploring Diffusion-generated Guidance for Thermal Image Super-resolution
* Feature Alignment and Compositional Token for Human Pose Estimation
* FG-DINO: Inducing Foreground Approximation Into DINO for Low-Resolution Surveillance Videos
* Improving Thermal Object Detection Robustness via Zero-Shot Inpainting-Based Data Augmentation
* K-Track: Kalman-Enhanced Tracking for Accelerating Deep Point Trackers on Edge Devices
* PrismVAU: Prompt-Refined Inference System for Multimodal Video Anomaly Understanding
* Robust Object Detection for Long-Term Thermal Surveillance via Explicit Background Modeling
* Robust Thermal Image Object Detection Challenge: Advancing Multi-Object Detection Performance Under Long-Term Thermal Drift
* Robust Thermal Image Object Detection Via Appearance-Guided Mixture of Experts
* SiamTrackCaps: A Siamese-Based Single Object Tracker Using Capsule Networks
* SOVABench: A Vehicle Surveillance Action Retrieval Benchmark for Multimodal Large Language Models
* TrafficRAG: Temporal Grounding for Traffic Violations via Retrieval-Augmented Generation
* Training-Free Target Emphasis With Sam2 Pseudo-Masks for Robust Single Object Tracking
17 for RWSurvil26