Sukthankar, G.
Co Author Listing * Activity Recognition for Physically-Embodied Agent Teams
* Dynamic Shadow Elimination for Multi-Projector Displays
* Face Recognition: A Critical Look at Biologically-Inspired Approaches
* Importance-weighted label prediction for active learning with noisy annotations
* Motif Discovery and Feature Selection for CRF-based Activity Recognition
* Predicting Team Performance with Spatial Temporal Graph Convolutional Networks
* Self-Calibrating Camera Projector Systems for Interactive Displays and Presentations
* Shadow Elimination and Occluder Light Suppression for Multi-Projector Displays
Includes: Sukthankar, G. Sukthankar, G.[Gita]
8 for Sukthankar, G.
Sukthankar, R.[Rahul]
Co Author Listing * 2nd YouTube-8M Large-Scale Video Understanding Challenge, The
* Actor-Centric Relation Network
* Articulated motion discovery using pairs of trajectories
* AVA: A Video Dataset of Spatio-Temporally Localized Atomic Visual Actions
* Behavior Discovery and Alignment of Articulated Object Classes from Unstructured Video
* Beyond Local Appearance: Category Recognition from Pairwise Interactions of Simple Features
* Boosting Framework for Visuality-Preserving Distance Metric Learning and Its Application to Medical Image Retrieval, A
* Classification of Cinematographic Shots Using Lie Algebra and its Application to Complex Event Recognition
* Classification of plant structures from uncalibrated image sequences
* Classifier Ensemble Recommendation
* Cognitive Mapping and Planning for Visual Navigation
* Computer Vision for Music Identification
* Computer Vision for Music Identification: Video Demonstration
* Correlated Label Propagation with Application to Multi-label Learning
* CrowdCam: Instantaneous Navigation of Crowd Images Using Angled Graph
* D-Nets: Beyond patch-based image descriptors
* D3D: Distilled 3D Networks for Video Action Recognition
* DaMN: Discriminative and Mutually Nearest: Exploiting Pairwise Category Proximity for Video Action Recognition
* Deep Learning for Visual Understanding
* Deep Learning for Visual Understanding: Part 2
* Depth distillation: unsupervised metric depth estimation for UAVs by finding consensus between kinematics, optical flow and deep learning
* Discovering the Physical Parts of an Articulated Object Class from Multiple Videos
* Discriminative Cluster Refinement: Improving Object Category Recognition Given Limited Training Data
* Discriminative Segment Annotation in Weakly Labeled Video
* Dynamic Shadow Elimination for Multi-Projector Displays
* Efficient Closed-Form Solution to Generalized Boundary Detection
* Efficient Visual Event Detection Using Volumetric Features
* Event Detection in Crowded Videos
* Exploring the Trade-off Between Accuracy and Observational Latency in Action Recognition
* Fast and accurate global motion compensation
* Fast Motion Consistency through Matrix Quantization
* Feature seeding for action recognition
* Feature-based Part Retrieval for Interactive 3D Reassembly
* flexible projector-camera system for multi-planar displays, A
* Food recognition using statistics of pairwise local features
* Generalized Boundaries from Multiple Image Interpretations
* GHUM GHUML: Generative 3D Human Shape and Articulated Pose Models
* Importance-weighted label prediction for active learning with noisy annotations
* Industry and Object Recognition: Applications, Applied Research and Challenges
* JKanji: Wavelet-based Interactive Kanji Completion
* Large-Scale Multimedia Retrieval and Mining
* Large-Scale Video Classification with Convolutional Neural Networks
* Learning class-specific affinities for image labelling
* Localizing actions through sequential 2D video projections
* MatchNet: Unifying feature and metric learning for patch-based matching
* Measuring and reducing observational latency when recognizing actions
* Memory-based Face Recognition for Visitor Identification
* Model recommendation for action recognition
* Motif Discovery and Feature Selection for CRF-based Activity Recognition
* Neural Descent for Visual 3D Human Pose and Shape
* Object-based image retrieval using the statistical structure of images
* Optimizing one-shot recognition with micro-set learning
* Panacea: An Active Sensor Controller for the ALVINN Autonomous Driving System
* PCA-SIFT: a more distinctive representation for local image descriptors
* PFID: Pittsburgh fast-food image dataset
* Preface to 3D Reconstruction and Understanding with Video and Sound
* probabilistic representation for efficient large scale visual recognition tasks, A
* Prop-free pointing detection in dynamic cluttered environments
* Recognition of Complex Events: Exploiting Temporal Dynamics between Underlying Concepts
* Relational Action Forecasting
* Representing Pairwise Spatial and Temporal Relations for Action Recognition
* Rethinking the Faster R-CNN Architecture for Temporal Action Localization
* Robust video segment proposals with painless occlusion handling
* Self-Calibrating Camera Projector Systems for Interactive Displays and Presentations
* Self-supervised Hypergraphs for Learning Multiple World Interpretations
* Semantic Learning for Audio Applications: A Computer Vision Approach
* Semi-Supervised Clustering via Learnt Codeword Distances
* Shadow Elimination and Occluder Light Suppression for Multi-Projector Displays
* Smarter Presentations: Exploiting Homography in Camera-Projector Systems
* Space-Time Shapelets for Action Recognition
* Spatio-temporal Shape and Flow Correlation for Action Recognition
* Spatiotemporal Deformable Part Models for Action Detection
* Speech2Action: Cross-Modal Supervision for Action Recognition
* theory of the quasi-static world, A
* THUMOS challenge on action recognition for videos 'in the wild', The
* THUNDR: Transformer-based 3D HUmaN Reconstruction with Markers
* Trajectons: Action recognition through the motion analysis of tracked features
* Unifying discriminative visual codebook generation with classifier training for object category recognition
* Unsupervised Learning for Graph Matching
* Video Object Discovery and Co-Segmentation with Extremely Weak Supervision
* Violence Detection in Video Using Computer Vision Techniques
* Virtues of Peer Pressure: A Simple Method for Discovering High-Value Mistakes, The
* Volumetric Features for Video Event Detection
* Weakly Supervised 3d Human Pose and Shape Reconstruction with Normalizing Flows
* Weakly Supervised Learning of Object Segmentations from Web-Scale Video
Includes: Sukthankar, R.[Rahul] Sukthankar, R.
85 for Sukthankar, R.
Sukthanker, R.S.[Rhea Sanjay]
Co Author Listing * Generative Flows with Invertible Attentions