Microsoft Technology Licensing, LLC

Ye Yu

Mei Chen

Gaurav Mittal

Junwen Chen

Zicheng Liu

Yinpeng Chen

Dongdong Chen

Lu Yuan

Peng Chen

Mengchen Liu

Xiyang Dai

Jie Zhang

Jianyong Wang

Yunsheng Li

Jay Sanjay Patravali

Jialin Yuan

Zeyu Shang

Example solutions for video object segmentation (VOS) use a bilateral attention transformer in motion-appearance neighboring space, and perform a process that includes: receiving a video stream comprising a plurality of video frames in a sequence; receiving a first object mask for an initial video frame of the plurality of video frames; selecting a video frame of the plurality of video frames as a current query frame, the current query frame following, in the sequence, a reference frame of a reference frame set, wherein each reference frame has a corresponding object mask; using the current query frame and a video frame in the reference frame set, determining a bilateral attention; and using the bilateral attention, generating an object mask for the current query frame.

Bilateral attention transformer in motion-appearance neighboring space for video object segmentation

A computer device for automatic feature detection comprises a processor, a communication device, and a memory configured to hold instructions executable by the processor to instantiate a dynamic convolution neural network, receive input data via the communication network, and execute the dynamic convolution neural network to automatically detect features in the input data. The dynamic convolution neural network compresses the input data from an input space having a dimensionality equal to a predetermined number of channels into an intermediate space having a dimensionality less than the number of channels. The dynamic convolution neural network dynamically fuses the channels into an intermediate representation within the intermediate space and expands the intermediate representation from the intermediate space to an expanded representation in an output space having a higher dimensionality than the dimensionality of the intermediate space. The features in the input data are automatically detected based on the expanded representation.

Dynamic matrix convolution with channel fusion

Example solutions for video frame action detection use a gated history and include: receiving a video stream comprising a plurality of video frames; grouping the plurality of video frames into a set of present video frames and a set of historical video frames, the set of present video frames comprising a current video frame; determining a set of attention weights for the set of historical video frames, the set of attention weights indicating how informative a video frame is for predicting action in the current video frame; weighting the set of historical video frames with the set of attention weights to produce a set of weighted historical video frames; and based on at least the set of weighted historical video frames and the set of present video frames, generating an action prediction for the current video frame.

Video frame action detection using gated history

The present disclosure provides a method and an apparatus for providing responses in an event-related session. The event is associated with a predefined domain, and the session comprises an electronic conversational agent and at least one participant. At least one message from the at least one participant may be detected. A set of candidate responses may be retrieved, from an index set being based on the domain, according to the at least one message. The set of candidate responses may be optimized through filtering the set of candidate responses according to predetermined criteria. A response to the at least one message may be selected from the filtered set of candidate responses. The selected response may be provided in the session.

Providing responses in an event-related session

The disclosure herein describes preparing and using a cross-attention model for action recognition using pre-trained encoders and novel class fine-tuning. Training video data is transformed into augmented training video segments, which are used to train an appearance encoder and an action encoder. The appearance encoder is trained to encode video segments based on spatial semantics and the action encoder is trained to encode video segments based on spatio-temporal semantics. A set of hard-mined training episodes are generated using the trained encoders. The cross-attention module is then trained for action-appearance aligned classification using the hard-mined training episodes. Then, support video segments are obtained, wherein each support video segment is associated with video classes. The cross-attention module is fine-tuned using the obtained support video segments and the associated video classes. A query video segment is obtained and classified as a video class using the fine-tuned cross-attention module.

Leveraging unsupervised meta-learning to boost few-shot action recognition

Growing community of inventors

Redmond, WA, United States of America

Ye Yu