Nec Corporation

Nec C Orporation

Nec Laboratories America, Inc.

Nec Hong Kong Limited

Manmohan Chandraker

Xiang Yu

Kihyuk Sohn

Yi-Hsuan Tsai

Samuel Schulter

Quoc-Huy Tran

Wongun Choi

Buyu Liu

Bingbing Zhuang

Paul Vernaza

Eric Lau

Elsa Wong

Muhammad Zeeshan Zia

Pan Ji

Shiyu Song

Gaurav Sharma

Masoud Faraki

Jong-Chyi Su

Xi Yin

Bharat Singh

Donghyun Kim

Chi Li

Ramin Moslemi

Sriram Nochur Narayanan

Sparsh Garg

Guobin Chen

Francesco Pittaluga

Yumin Suh

Yuanqing Lin

Silvio Savarese

Jinwoo Choi

Hyo Jin Kim

Vijay Kumar Baikampady Gopalkrishna

Menghua Zhai

Luan Tran

Tuan Hung Vu

Mohammed E F Salem

Ting Wang

Ming-Fang Huang

Yue Tian

Kai Hung Yu

Xiaoyu Wang

Yuheng Chen

Jian Fang

Xi Peng

Chang Liu

Xiangyu Chen

Christopher Bongsoo Choy

Dongwan Kim

Samuel Shulter

Junru Wu

Namhoon Lee

Xiangyun Zhao

Shuyang Dai

Angjoo Kim

Chao-Yeh Chen

Vikas Dhiman

Feng-Ju Chang

Du Tran

Yingze Bao

Lokender Tiwari

Nataniel Ruiz

Yichun Shi

Yuliang Zou

Mohammed E Fathy Salem

Aruni RoyChowdhury

Ziyan Wang

Xiang Xu

Video methods and systems include extracting features of a first modality and a second modality from a labeled first training dataset in a first domain and an unlabeled second training dataset in a second domain. A video analysis model is trained using contrastive learning on the extracted features, including optimization of a loss function that includes a cross-domain regularization part and a cross-modality regularization part. The video methods and systems can support real-time decision making in various applications, such as security surveillance where immediate responses to detected actions are required.

Video domain adaptation via contrastive learning for decision making

Video methods and systems include extracting features of a first modality and a second modality from a labeled first training dataset in a first domain and an unlabeled second training dataset in a second domain. A video analysis model is trained using contrastive learning on the extracted features, including optimization of a loss function that includes a cross-domain regularization part and a cross-modality regularization part.

Systems and methods are provided for identifying and retrieving semantically similar images from a database. Semantic analysis is performed on an input query utilizing a vision language model to identify semantic concepts associated with the input query. A preliminary set of images is retrieved from the database for semantic concepts identified. Relevant concepts are extracted for images with a tokenizer by comparing images against a predefined label space to identify relevant concepts. A ranked list of relevant concepts is generated based on occurrence frequency within the set. The preliminary set of images is refined based on selecting specific relevant concepts from the ranked list by the user by combining the input query with the specific relevant concepts. Additional semantic analysis is iteratively performed to retrieve additional sets of images semantically similar to the combined input query and selection of the specific relevant concepts until a threshold condition is met.

Multimodal semantic analysis and image retrieval

A computer-implemented method for rut detection is provided. The method includes detecting, by a rut detection system, areas in a road-scene image that include ruts with pixel-wise probability values, wherein a higher value indicates a better chance of being a rut. The method further includes performing at least one of rut repair and vehicle rut avoidance responsive to the pixel-wise probability values. The detecting step includes performing neural network-based, pixel-wise semantic segmentation with context information on the road-scene image to distinguish rut pixels from non-rut pixels on a road depicted in the road-scene image.

Rut detection for road infrastructure

A method for driving path prediction is provided. The method concatenates past trajectory features and lane centerline features in a channel dimension at an agent's respective location in a top view map to obtain concatenated features thereat. The method obtains convolutional features derived from the top view map, the concatenated features, and a single representation of the training scene the vehicle and agent interactions. The method extracts hypercolumn descriptor vectors which include the convolutional features from the agent's respective location in the top view map. The method obtains primary and auxiliary trajectory predictions from the hypercolumn descriptor vectors. The method generates a respective score for each of the primary and auxiliary trajectory predictions. The method trains a vehicle trajectory prediction neural network using a reconstruction loss, a regularization loss objective, and an IOC loss objective responsive to the respective score for each of the primary and auxiliary trajectory predictions.

Divide-and-conquer for lane-aware diverse trajectory prediction

A computer-implemented method for fusing geometrical and Convolutional Neural Network (CNN) relative camera pose is provided. The method includes receiving two images having different camera poses. The method further includes inputting the two images into a geometric solver branch to return, as a first solution, an estimated camera pose and an associated pose uncertainty value determined from a Jacobian of a reproduction error function. The method also includes inputting the two images into a CNN branch to return, as a second solution, a predicted camera pose and an associated pose uncertainty value. The method additionally includes fusing, by a processor device, the first solution and the second solution in a probabilistic manner using Bayes' rule to obtain a fused pose.

Learning to fuse geometrical and CNN relative camera pose via uncertainty

Methods and systems for detecting faults include capturing an image of a scene using a camera. The image is embedded using a segmentation model that includes an image branch having an image embedding layer that embeds images into a joint latent space and a text branch having a text embedding layer that embeds text into the joint latent space. Semantic information is generated for a region of the image corresponding to a predetermined static object using the embedded image. A fault of the camera is identified based on a discrepancy between the semantic information and semantic information of the predetermined static image. The fault of the camera is corrected.

Semantic image capture fault detection

A computer-implemented method for road layout prediction is provided. The method includes segmenting, by a first processor-based element, an RGB image to output pixel-level semantic segmentation results for the RGB image in a perspective view for both visible and occluded pixels in the perspective view based on contextual clues. The method further includes learning, by a second processor-based element, a mapping from the pixel-level semantic segmentation results for the RGB image in the perspective view to a top view of the RGB image using a road plane assumption. The method also includes generating, by a third processor-based element, an occlusion-aware parametric road layout prediction for road layout related attributes in the top view.

End-to-end parametric road layout prediction with cheap supervision

A method for employing facial information in unsupervised person re-identification is presented. The method includes extracting, by a body feature extractor, body features from a first data stream, extracting, by a head feature extractor, head features from a second data stream, outputting a body descriptor vector from the body feature extractor, outputting a head descriptor vector from the head feature extractor, and concatenating the body descriptor vector and the head descriptor vector to enable a model to generate a descriptor vector.

Face-aware person re-identification system

Methods and systems for training a model include combining data from multiple datasets, the datasets having different respective label spaces. Relationships between labels in the different label spaces are identified. A unified neural network model is trained, using the combined data and the identified relationships to generate a unified model, with a class relational binary cross-entropy loss.

Multi-domain semantic segmentation with label shifts

A method for simultaneous multi-agent recurrent trajectory prediction is presented. The method includes reconstructing a topological layout of a scene from a dataset including real-world data, generating a road graph of the scene, the road graph capturing a hierarchical structure of interconnected lanes, incorporating vehicles from the scene on the generated road graph by utilizing tracklet information available in the dataset, assigning the vehicles to their closest lane identifications, and identifying diverse plausible behaviors for every vehicle in the scene. The method further includes sampling one behavior from the diverse plausible behaviors to select an associated velocity profile sampled from the real-world data of the dataset that resembles the sampled one behavior and feeding the road graph and the sampled velocity profile with a desired destination to a dynamics simulator to generate a plurality of simulated diverse trajectories output on a visualization device.

Simulating diverse long-term future trajectories in road scenes

A method provided for 3D object localization predicts pairs of 2D bounding boxes. Each pair corresponds to a detected object in each of the two consecutive input monocular images. The method generates, for each detected object, a relative motion estimation specifying a relative motion between the two images. The method constructs an object cost volume by aggregating temporal features from the two images using the pairs of 2D bounding boxes and the relative motion estimation to predict a range of object depth candidates and a confidence score for each object depth candidate and an object depth from the object depth candidates. The method updates the relative motion estimation based on the object cost volume and the object depth to provide a refined object motion and a refined object depth. The method reconstructs a 3D bounding box for each detected object based on the refined object motion and refined object depth.

Monocular 3D object localization from temporal aggregation

A method for training a model for face recognition is provided. The method forward trains a training batch of samples to form a face recognition model w(t), and calculates sample weights for the batch. The method obtains a training batch gradient with respect to model weights thereof and updates, using the gradient, the model w(t) to a face recognition model what(t). The method forwards a validation batch of samples to the face recognition model what(t). The method obtains a validation batch gradient, and updates, using the validation batch gradient and what(t), a sample-level importance weight of samples in the training batch to obtain an updated sample-level importance weight. The method obtains a training batch upgraded gradient based on the updated sample-level importance weight of the training batch samples, and updates, using the upgraded gradient, the model w(t) to a trained model w(t+1) corresponding to a next iteration.

Domain generalized margin via meta-learning for deep face recognition

Growing community of inventors

Santa Clara, CA, United States of America

Manmohan Chandraker