Qualcomm Incorporated

Qualcomm Technologies, Inc.

Arnold Wilhelmus Maria Smeulders

Efstratios Gavves

Noureldien Mahmoud Elsayed Hussein

Ran Tao

Mert Kilickaya

Cornelis Gerardus Maria Snoek

Tom Frederik Hugo Runia

Deepak Kumar Gupta

A method for object tracking includes receiving a target image of an object of interest. Latent space features of the target image is modified at a forward pass for a neural network by dropping at least one channel of the latent space features, dropping a channel corresponding to a slice of the latent space features, or dropping one or more features of the latent space features. At the forward pass, a location of the object of interest in a search image is predicted based on the modified latent space features. The location of the object of interest is identified by aggregating predicted locations from the forward pass.

Managing occlusion in Siamese tracking using structured dropouts

A method for recognizing long-range activities in videos includes segmenting an input video stream to generate multiple frame sets. For each of the frame sets, a frame with a highest likelihood of including one or more actions of a set of predefined actions is identified regardless of its order in the frame set. A global representation of the input stream is generated based on pooled representations of the identified frames. A long-range activity in the video stream is classified based on the global representation.

Permutation invariant convolution (PIC) for recognizing long-range activities, generating global representation of input streams and classifying activity based on global representation

A method for classifying a human-object interaction includes identifying a human-object interaction in the input. Context features of the input are identified. Each identified context feature is compared with the identified human-object interaction. An importance of the identified context feature is determined for the identified human-object interaction. The context feature is fused with the identified human-object interaction when the importance is greater than a threshold.

Context-driven learning of human-object interactions

A method for human-object interaction detection includes receiving an image. A set of features are extracted from multiple positions of the image. One or more human-object pairs may be predicted based on the extracted set of features. A human-object interaction may be determined based on a set of candidate interactions and the predicted human-object pairs.

Network for interacted object localization

A method is presented. The method includes receiving a first sequence of frames depicting a dynamic element. The method also includes decomposing each spatial position from multiple spatial positions in the first sequence of frames to a frequency domain. The method further includes determining a distribution of spectral power density over a range of frequencies of the multiple spatial positions. The method still further includes generating a first set of feature maps based on the determined distribution of spectral power density over the range of frequencies. The method still further includes estimating a first physical property of the dynamic element.

Video processing using a spectral decomposition layer

A method for processing an image is presented. The method locates a subject and an object of a subject-object interaction in the image. The method determines relative weights of the subject, the object, and a context region for classification. The method further classifies the subject-object interaction based on a classification of a weighted representation of the subject, a weighted representation of the object, and a weighted representation of the context region.

Subject-object interaction recognition model

A method for classifying subject activities in videos includes learning latent (previously generated) concepts that are analogous to nodes of a graph to be generated for an activity in a video. The method also includes receiving video segments of the video. A similarity between the video segments and the previously generated concepts is measured to obtain segment representations as a weighted set of latent concepts. The method further includes determining a relationship between the segment representations and their transitioning pattern over time to determine a reduced set of nodes and/or edges for the graph. The graph of the activity in the video represented by the video segments is generated based on the reduced set of nodes and/or edges. The nodes of the graph are represented by the latent concepts. Subject activities in the video are classified based on the graph.

Recognizing minutes-long activities in videos

A method is presented. The method includes receiving a first sequence of frames. The method also includes decomposing each spatial position from multiple spatial positions in the first sequence of frames to a frequency domain. The method further includes determining a distribution of spectral power density over a range of frequencies of the multiple spatial positions. The method still further includes generating a first set of feature maps based on the determined distribution of spectral power density over the range of frequencies.

A method of tracking a position of a target object in a video sequence includes identifying the target object in a reference frame. A generic mapping is applied to the target object being tracked. The generic mapping is generated by learning possible appearance variations of a generic object. The method also includes tracking the position of the target object in subsequent frames of the video sequence by determining whether an output of the generic mapping of the target object matches an output of the generic mapping of a candidate object.

Adapting to appearance variations when tracking a target object in video sequence

A method, a computer-readable medium, and an apparatus for zero-exemplar event detection are provided. The apparatus may receive a plurality of text blocks, each of which may describe one of a plurality of pre-defined events. The apparatus may receive a plurality of training videos, each of which may be associated with one of the plurality of text blocks. The apparatus may propagate each text block through a neural network to obtain a textual representation in a joint space of textual and video representations. The apparatus may propagate each training video through the neural network to obtain a visual representation in the joint space. The apparatus may adjust parameters of the neural network to reduce, for each pair of associated text block and training video, the distance in the joint space between the textual representation of the associated text block and the visual representation of the associated training video.

Growing community of inventors

Amsterdam, Netherlands

Arnold Wilhelmus Maria Smeulders