Diverse Deep Feature Ensemble Learning for Omni-Domain Generalized Person Reidentification Color Space Learning for Cross-Color Person Re-Identification Self-Supervised 3D Action Representation Learning with Skeleton Cloud Colorization One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching A Unified Deep Semantic Expansion Framework for Domain-Generalized Person Re-Identification
Cross-Modal Label Contrastive Learning for Unsupervised Audio-Visual Event Localization Temporal Coherent Test-Time Optimization for Robust Video Classification Chenyu Yi, Siyuan Yang, Yufei Wang, Haoliang Li, Yap-Peng Tan, and Alex C. Kot, 2023 International Conference on Learning Representations (ICLR)
DEX: Domain Embedding Expansion for Generalized Person Re-identification Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning Skeleton-based Relational Reasoning for Group Activity Analysis Dense Events Grounding in Video Interaction Relational Network for Mutual Action Recognition
Collaborative Learning of Gesture Recognition and 3D Hand Post Estimation with Multi-Order Feature Analysis Multi-Domain Adversarial Feature Generalization for Person Re-Identification Collaborative Learning of Gesture Recognition and 3D Hand Pose Estimation with Multi-Order Feature Analysis Multi-Camera Trajectory Forecasting: Pedestrian Trajectory Prediction in a Network of Cameras
Detection of Real-world Fights in Surveillance Videos Feature Boosting Network For 3D Pose Estimation Skeleton-Based Online Action Prediction Using Scale Selection Network A Scale Adaptive Network for Crowd Counting Multi-Resolution Attention Convolutional Neural Network for Crowd Counting AANet: Attribute Attention Network for Person Re-Identifications Scale-Aware Attention Network for Crowd Counting Attention Driven Person Re-Identification https://arxiv.org/abs/1810.05866 ) 2019NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding
Abandoned Object Detection Using Pixel-Based Finite State Machine and Single Shot Multibox Detector Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates Deformable Pose Traversal Convolution for 3D Action and Gesture Recognition SSNet: Scale selection network for online 3D action prediction Skeleton-Based Human Action Recognition With Global Context-Aware Attention LSTM Networks Recurrent Spatial Pyramid CNN for Optical Flow Estimation Dual Attention Matching Network for Context-Aware Feature Sequence based Person Re-Identification https://arxiv.org/abs/1803.09937 ) 2018Multi-task Mid-level Feature Alignment Network for Unsupervised Cross-Dataset Person Re-Identification Towards Achieving Robust Low-level and High-level Scene Parsing Multimodal data fusion for sensitive scene localization Stack-Captioning: Coarse-to-Fine Learning for Image Captioning Unpaired Image Captioning by Language Pivoting
Action Proposals Using Hierarchical Clustering of Super-Ttrajectories Skeleton Based Human Action Recognition with Global Context-Aware Attention LSTM Networks Deep Multimodal Feature Analysis for Action Recognition In RGB+ D Videos Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates Common Action Discovery and Localization in Unconstrained Videos Global Context-Aware Attention LSTM Networks For 3D Action Recognition Leveraging Deep Neural Networks to Fight Child Pornography in the Age of Social Media Temporal Robust Features for Violence Detection An Empirical Study of Language CNN for Image Captioning Episodic CAMN: Contextual Attention-Based Memory Networks with Iterative Feedback for Scene Labeling
Spatio-Temporal LSTM with Trust Gates For 3D Human Action Recognition NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis Efficient Object Feature Selection for Action Recognition Action and Event Recognition in Videos by Learning from Heterogeneous Web Sources Person Reidentification Using Multiple Egocentric Views Learning Invariant Color Features for Person Re-Identification Gated Siamese Convolutional Neural Network Architecture for Human Re-Identification A Siamese Long Short-Term Memory Architecture for Human Re-identification Video Pornography Detection Through Deep Learning Techniques and Motion Information Pornography Classification: The Hidden Clues in Video Space–Time DAG-Recurrent Neural Networks For Scene Labeling Discovering Class-Specific Spatial Layouts for Scene Recognition LBP-Structure Optimization With Symmetry and Uniformity Regularizations for Scene Classification Scene Parsing with Integration of Parametric and Non-parametric Models
Hierarchical Invariant Feature Learning with Marginalization for Person Re-Identification A Data-Driven Color Feature Learning Scheme for Image Retrieval Visual Tracking Using Learned Color Features Real-Time Part-Based Visual Tracking Via Adaptive Correlation Filters Visual Tracking via Temporally Smooth Sparse Coding Video Tacking using Learned Hierarchical Features Exploiting Privileged Information from Web Data for Action and Event Recognition Multimodal Multipart Learning for Action Recognition in Depth Videos
Multi-modal Feature Fusion for Action Recognition in {RGB-D} Sequences Pedestrian Detection in Highly Crowded Scenes Using "Online" Dictionary Learning for Occlusion Handling Tracklet Association by Online Target-Specific Metric Learning and Coherent Dynamics Estimation
Robust Part-Based Hand Gesture Recognition Using Kinect Sensor Video Anomaly Search in Crowded Scenes via Spatio-Temporal Motion Context Abnormal Event Detection in Crowded Scenes using Sparse Representation
