Inventor

CHANDRAKER MANMOHAN

US108 patents

⚠️ This page may combine multiple inventors who share the name “CHANDRAKER MANMOHAN”. Patents are grouped by organization below to help distinguish them — per-person disambiguation is on the roadmap.

CHANDRAKER MANMOHAN

NEC LAB AMERICA INC

Action recognition system with landmark localization on objects in images using convolutional neural networks

Siamese reconstruction convolutional neural network for pose-invariant face recognition

Advanced driver-assistance system with landmark localization on objects in images using convolutional neural networks

Real-time monocular visual odometry

Moving object localization in 3D using a single camera

Surveillance system using deep network flow for multi-object tracking

Liveness detection for antispoof face recognition

Physical system access control

Baby detection for electronic-gate environments

Generating occlusion-aware bird eye view representations of complex road scenes

Universal correspondence network

Domain adaptation for structured output via disentangled representations

Attention and warping based domain adaptation for videos

Aerial drone utilizing pose estimation

Unsupervised cross-domain distance metric adaptation with feature transfer network

Video security system using a Siamese reconstruction convolutional neural network for pose-invariant face recognition

Real-time monocular structure from motion

Parking lot surveillance with viewpoint invariant object recognition by synthesization and domain adaptation

Face recognition using larger pose face frontalization

Face recognition system for face recognition in unlabeled videos with domain adversarial learning and knowledge distillation

High accuracy monocular moving object localization

Robust scale estimation in real-time monocular SFM for autonomous driving

Object detection with training from multiple datasets

Long-tail large scale face recognition by non-linear feature level domain adaptation

Cyclic generative adversarial network for unsupervised cross-domain image generation

System and method for learning random-walk label propagation for weakly-supervised semantic segmentation

Deep network flow for multi-object tracking

Security system for facility access control

Login access control for secure/private data

Camera system for traffic enforcement

Multi-agent trajectory prediction

Rolling shutter rectification in images/videos using convolutional neural networks with applications to SFM/SLAM with rolling shutter images/videos

Domain adaptation for instance detection and segmentation

Dynamic scene prediction with multiple interacting agents

Face recognition from unseen domains via learning of semantic features

Computer aided traffic enforcement using dense correspondence estimation with multi-level metric learning and hierarchical matching

Generating occlusion-aware bird eye view representations of complex road scenes

Multi-domain semantic segmentation with label shifts

Online flow guided memory networks for object detection in video

Deep face recognition based on clustering over unlabeled face data

Self-supervised visual odometry framework using long-term modeling and incremental learning

Learning to simulate

Atomic scenes for scalable traffic scene recognition in monocular videos

Unsupervised matching in fine-grained datasets for single-view object reconstruction

Continuous occlusion models for road scene understanding

Video domain adaptation via contrastive learning for decision making

NEC CORP

Recognition in unlabeled videos with domain adversarial learning and knowledge distillation

Surveillance system for recognition in unlabeled videos with domain adversarial learning and knowledge distillation

CHANDRAKER MANMOHAN

Structure and motion with stereo using lines

ADOBE INC

Extracting material properties from a single image