Crowd15
* *Group And Crowd Behavior Analysis And Understanding
* comparison of crowd commotion measures from generative models, A
* Discovering human interactions in videos with limited data labeling
* Dominant flow extraction and analysis in traffic surveillance videos
* GRODE metrics: Exploring the performance of group detection approaches, The
* Learning to identify leaders in crowd
* MuseumVisitors: A dataset for pedestrian and group detection, gaze estimation and behavior understanding
* Real-time anomaly detection and localization in crowded scenes
* Subject centric group feature for person re-identification
* Walking and talking: A bilinear approach to multi-label action recognition
10 for Crowd15
Crowd16
* *Group And Crowd Behavior Analysis And Understanding
* Abnormal Crowd Behavior Detection Based on Gaussian Mixture Model
* Anomaly Detection and Activity Perception Using Covariance Descriptor for Trajectories
* Automatic Calibration of Stationary Surveillance Cameras in the Wild
* Data-Driven Motion Pattern Segmentation in a Crowded Environments
* Density-Aware Pedestrian Proposal Networks for Robust People Detection in Crowded Scenes
* LCrowdV: Generating Labeled Videos for Simulation-Based Crowd Behavior Learning
* Multi-person Pose Estimation with Local Joint-to-Person Associations
* People Counting in Videos by Fusing Temporal Cues from Spatial Context-Aware Convolutional Neural Networks
* Pixel Level Tracking of Multiple Targets in Crowded Environments
* Unsupervised Deep Domain Adaptation for Pedestrian Detection
11 for Crowd16
Crowd17
* *Visual Understanding of Humans in Crowd Scene and the 1st Look Into Person Challenge
* Human Activity Recognition Using Combinatorial Deep Belief Networks
* Self-Supervised Neural Aggregation Networks for Human Parsing
Crowd18
* *Visual Understanding of Humans in Crowd Scene and the 1st Look Into Person Challenge
* Adaptation and Re-identification Network: An Unsupervised Deep Transfer Learning Approach to Person Re-identification
* Aggregated Multicolumn Dilated Convolution Network for Perspective-Free Counting, An
* Attention in Multimodal Neural Networks for Person Re-identification
* Crowd Activity Change Point Detection in Videos via Graph Stream Mining
* Learning to Refine Human Pose Estimation
* Pose Encoding for Robust Skeleton-Based Action Recognition
7 for Crowd18
Crowded24
* *Robot Visual Perception in Human Crowded Environments
* DSTCFuse: A Method based on Dual-cycled Cross-awareness of Structure Tensor for Semantic Segmentation via Infrared and Visible Image Fusion
* GM-DETR: Generalized Muiltispectral DEtection TRansformer with Efficient Fusion Encoder for Visible-Infrared Detection
* HumanFormer: Human-centric Prompting Multi-modal Perception Transformer for Referring Crowd Detection
* InViG: Benchmarking Open-Ended Interactive Visual Grounding with 500K Dialogues
* Is Our Continual Learner Reliable? Investigating Its Decision Attribution Stability through SHAP Value Consistency
* Must Unsupervised Continual Learning Relies on Previous Information?
* Pre-trained Bidirectional Dynamic Memory Network For Long Video Question Answering
8 for Crowded24