Nec Laboratories America, Inc.

Pericom Semiconductor Corporation

Diodes Inc.

Other

Kai Hung Yu

Shenghuo Zhu

Ming M Yang

Yihong Gong

Jin-sheng Wang

Yuanqing Lin

Fengjun Lv

Jinjun Wang

Chang Huang

Xiaoyu Wang

Wei Xu

Manmohan Chandraker

Yun Chi

Rob A Rutenbar

Fei-Fei Li

Kwok Wing Choy

Jianchao Yang

Xi Zhou

Shuiwang Ji

Timothee Cour

Olga Russakovsky

Shaoting Zhang

Multipath clock and data recovery circuits and multipath I/O devices are described that operate to provide flexible I/O paths for serial data communications. Active unidirectional components such as a clock and data recovery circuit may be used to implement different I/O paths. Bandwidth and signal degradation for high-speed serial data transmission is reduced.

Multipath clock and data recovery

Repeaters are described that operate to rapidly transition from low-power standby states to a low frequency signal transmission state. Bandwidth for high-frequency signal transmission is preserved.

Repeaters with fast transitions from low-power standby to low-frequency signal transmission

Referenceless clock and data recovery circuits are described that operate to align the clock/data strobe with each data eye to achieve a low bit error rate. The appropriate frequency and phase to be used is determined by an edge counter based frequency error detector and a phase error detector.

Referenceless clock and data recovery circuits

Systems and methods are disclosed to search for a query image, by detecting local invariant features and local descriptors; retrieving best matching images by quantizing the local descriptors with a vocabulary tree; and reordering retrieved images with results from the vocabulary tree quantization.

Contextual weighting and efficient re-ranking for vocabulary tree based image retrieval

A computer implemented method for determining shape from differential motion with unknown reflectance includes deriving a general relation that relates spatial and temporal image derivatives to bidirectional reflectance distribution function BRDF derivatives, responsive to 3D points and relative camera poses from images and feature tracks of an object in motion under colocated and unknown directional light conditions, employing a rank deficiency in image sequences from the deriving for shape determinations, under predetermined multiple camera and lighting conditions, to eliminate BDRF terms; and recovering a surface depth for determining a shape of the object.

Shape from differential motion with unknown reflectance

A nearest-neighbor-based distance metric learning process includes applying an exponential-based loss function to provide a smooth objective; and determining an objective and a gradient of both hinge-based and exponential-based loss function in a quadratic time of the number of instances using a computer.

Fast methods of learning distance metric for classification and retrieval

Systems and methods for metric learning include iteratively determining feature groups of images based on its derivative norm. Corresponding metrics of the feature groups are learned by gradient descent based on an expected loss. The corresponding metrics are combined to provide an intermediate metric matrix as a sparse representation of the images. A loss function of all metric parameters corresponding to features of the intermediate metric matrix are optimized, using a processor, to learn a final metric matrix. Eigenvalues of the final metric matrix are projected onto a simplex.

Large-scale strongly supervised ensemble metric learning

Systems and methods are disclosed to categorize images by detecting local features for each image; applying a tree structure to index local features in the images; and extracting a rank list of candidate images with category tags based on a tree indexing structure to estimate a label of a query image.

Fast image classification by vocabulary tree based image retrieval

A method is provided for classifying an image. The method includes inferring location information of an object of interest in an input representation of the image. The method further includes determining foreground object features and background object features from the input representation of the image. The method additionally includes pooling the foreground object features separately from the background object features using the location information to form a new representation of the image. The new representation is different than the input representation of the image. The method also includes classifying the image based on the new representation of the image.

Object-centric spatial pooling for image classification

Systems and methods for image retrieval include constructing a plurality of graphs including a first graph for candidate images retrieved based upon holistic features of a query image and a second graph for candidate images retrieved based upon local features of the query image, wherein constructing includes weighting connected images based upon a Jaccard similarity coefficient. The plurality of graphs are fused to provide a fused graph. Candidate images of the fused graph are ranked, using a processor, to provide retrieval results of the query image.

Query specific fusion for image retrieval

Systems and methods process an image having a plurality of pixels includes an image sensor to capture an image; a first-layer to encode local patches on an image region; and a second layer to jointly encode patches from the same image region.

Systems and methods for determining image representations at a pixel level

A hardware acoustic scoring unit for a speech recognition system and a method of operation thereof are provided. Rather than scoring all senones in an acoustic model used for the speech recognition system, acoustic scoring logic first scores a set of ciphones based on acoustic features for one frame of sampled speech. The acoustic scoring logic then scores senones associated with the N highest scored ciphones. In one embodiment, the number (N) is three. While the acoustic scoring logic scores the senones associated with the N highest scored ciphones, high score ciphone identification logic operates in parallel with the acoustic scoring unit to identify one or more additional ciphones that have scores greater than a threshold. Once the acoustic scoring unit finishes scoring the senones for the N highest scored ciphones, the acoustic scoring unit then scores senones associated with the one or more additional ciphones.

Acoustic scoring unit implemented on a single FPGA or ASIC

Systems and methods are disclosed for determining personal characteristics from images by generating a baseline gender model and an age estimation model using one or more convolutional neural networks (CNNs); capturing correspondences of faces by face tracking, and applying incremental learning to the CNNs and enforcing correspondence constraint such that CNN outputs are consistent and stable for one person.

Systems and methods for determining personal characteristics

Methods and systems are disclosed for image classification coding an image by nonlinearly mapping an image descriptor to form a high-dimensional sparse vector; spatially pooling each local region to form an image-level feature vector using a probability kernel incorporating a similarity metric of local descriptors; and classifying the image.

Growing community of inventors

San Jose, CA, United States of America

Kai Hung Yu