Hewlett-packard Development Company, L.P.

University of California

Chuohao Yeo

Debargha Mukherjee

Wai-Tian Tan

Kannan Ramchandran

S Shankar Sastry

Parvez Ahammad

Decoding video data. At least one video stream including a first plurality of frames encoded at a first resolution and a second plurality of frames encoded at a second resolution are received, wherein the second plurality of frames encoded at the second resolution directly correspond to at least a subset of the first plurality of frames encoded at the first resolution, and wherein the first resolution is greater than the second resolution. The video stream is decoded based on at least one received frame of the first plurality of frames encoded at the first resolution and at least one received frame of the second plurality of frames encoded at the second resolution.

Decoding video data

Decoding video data. Receive a first video stream including a first plurality of frames encoded at a first resolution, a second video stream including a second plurality of frames encoded at a second resolution and a residual bitstream encoded at a third resolution. The second plurality of frames correspond to the first plurality of frames encoded at the first resolution and the first resolution is greater than the second resolution and the third resolution is at least between the first and second resolutions. Side information determined based at least on the first plurality of frames and the second plurality of frames. The video data decoded based at least on one received frame of the first plurality of frames, at least one received frame of the second plurality of frames encoded at the second resolution, the residual bitstream encoded at the third resolution, and the side information.

An apparatus for detecting an action in a test video. In an illustrative embodiment, the apparatus includes a first mechanism for receiving a query for a particular action via a query video. A second mechanism employs motion vectors associated with the test video to compute one or more motion-similarity values. The one or more motion-similarity values represent motion similarity between a first group of pixels in a first frame of a query video and a second group of pixels in a second frame of the test video based on the motion vectors. A third mechanism uses the one or more similarity values to search for the particular action or similar action in the test video. In a more specific embodiment, another mechanism aggregates the similarity values over a predetermined number of frames to facilitate estimating where the particular action or version thereof occurs or is likely to occur in the test video.

Growing community of inventors

Berkeley, CA, United States of America

Chuohao Yeo