Adobe, Inc.

Dingzeyu Li

Lubomira A Dontcheva

Joel Richard Brandt

Hijung Shin

Joy Oakyung Kim

Seth John Walker

Aseem Agarwala

Xue Bai

Jovan Popović

Cristin Ailidh Fraser

Kim Pascal Pimmel

Yang Zhou

Justin Salamon

Zhengyang Ma

Kyratso George Karahalios

Xuecong Xu

Pankaj Kumar Nathani

Anh Lan Truong

Deepali Aneja

Timothy Jeewun Ganter

Jui-hsien Wang

Elya Shechtman

Jimei Yang

Jose Ignacio Echevarria Vallespi

Nicholas J Bryan

Jun Saito

Timothy Langlois

Zhenyu Tang

Jianming Zhang

Oliver Wang

Jiyoung Lee

Li-Yi Wei

Wilmot Li

Stephen Diverdi

John Nelson

Hanieh Deilamsalehy

Zekun Hao

Morgan Nicole Evans

Rubaiat Habib

Jiaju Ma

Najika Skyler Halsema Yoo

Embodiments of the present invention provide systems, methods, and computer storage media for a visual and text search interface used to navigate a video transcript. In an example embodiment, a freeform text query triggers a visual search for frames of a loaded video that match the freeform text query (e.g., frame embeddings that match a corresponding embedding of the freeform query), and triggers a text search for matching words from a corresponding transcript or from tags of detected features from the loaded video. Visual search results are displayed (e.g., in a row of tiles that can be scrolled to the left and right), and textual search results are displayed (e.g., in a row of tiles that can be scrolled up and down). Selecting (e.g., clicking or tapping on) a search result tile navigates a transcript interface to a corresponding portion of the transcript.

Visual and text search interface for text-based video editing

Embodiments are disclosed for generating a gesture reenactment video sequence corresponding to a target audio sequence using a trained network based on a video motion graph generated from a reference speech video. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving a first input including a reference speech video and generating a video motion graph representing the reference speech video, where each node is associated with a frame of the reference video sequence and reference audio features of the reference audio sequence. The disclosed systems and methods further comprise receiving a second input including a target audio sequence, generating target audio features, identifying a node path through the video motion graph based on the target audio features and the reference audio features, and generating an output media sequence based on the identified node path through the video motion graph paired with the target audio sequence.

Generating gesture reenactment video from video motion graphs using machine learning

Embodiments of the present disclosure provide, a method, a system, and a computer storage media that provide mechanisms for multimedia effect addition and editing support for text-based video editing tools. The method includes generating a user interface (UI) displaying a transcript of an audio track of a video and receiving, via the UI, input identifying selection of a text segment from the transcript. The method also includes in response to receiving, via the UI, input identifying selection of a particular type of text stylization or layout for application to the text segment. The method further includes identifying a video effect corresponding to the particular type of text stylization or layout, applying the video effect to a video segment corresponding to the text segment, and applying the particular type of text stylization or layout to the text segment to visually represent the video effect in the transcript.

Video editing using transcript text stylization and layout

Display screen or portion thereof with graphical user interface

A method for detecting a cue (e.g., a visual cue or a visual cue combined with an audible cue) occurring together in an input video includes: presenting a user interface to record an example video of a user performing an act including the cue; determining a part of the example video where the cue occurs; applying a feature of the part to a neural network to generate a positive embedding; dividing the input video into a plurality of chunks and applying a feature of each chunk to the neural network to generate a plurality of negative embeddings; applying a feature of a given one of the chunks to the neural network to output a query embedding; and determining whether the cue occurs in the input video from the query embedding, the positive embedding, and the negative embeddings.

Automatic recognition of visual and audio-visual cues

Embodiments are directed to a snap point segmentation that defines the locations of selection snap points for a selection of video segments. Candidate snap points are determined from boundaries of feature ranges of the video indicating when instances of detected features are present in the video. In some embodiments, candidate snap point separations are penalized for being separated by less than a minimum duration corresponding to a minimum pixel separation between consecutive snap points on a video timeline. The snap point segmentation is computed by solving a shortest path problem through a graph that models different snap point locations and separations. When a user clicks or taps on the video timeline and drags, a selection snaps to the snap points defined by the snap point segmentation. In some embodiments, the snap points are displayed during a drag operation and disappear when the drag operation is released.

Snap point video segmentation identifying selection snap points for a video

Embodiments are directed to segmentation and hierarchical clustering of video. In an example implementation, a video is ingested to generate a multi-level hierarchical segmentation of the video. In some embodiments, the finest level identifies a smallest interaction unit of the video—semantically defined video segments of unequal duration called clip atoms. Clip atom boundaries are detected in various ways. For example, speech boundaries are detected from audio of the video, and scene boundaries are detected from video frames of the video. The detected boundaries are used to define the clip atoms, which are hierarchically clustered to form a multi-level hierarchical representation of the video. In some cases, the hierarchical segmentation identifies a static, pre-computed, hierarchical set of video segments, where each level of the hierarchical segmentation identifies a complete set (i.e., covering the entire range of the video) of disjoint (i.e., non-overlapping) video segments with a corresponding level of granularity.

Hierarchical segmentation based on voice-activity

Embodiments are directed to techniques for interacting with a hierarchical video segmentation using a metadata panel with a composite list of video metadata. The composite list is segmented into selectable metadata segments at locations corresponding to boundaries of video segments defined by a hierarchical segmentation. In some embodiments, the finest level of a hierarchical segmentation identifies the smallest interaction unit of a video—semantically defined video segments of unequal duration called clip atoms, and higher levels cluster the clip atoms into coarser sets of video segments. One or more metadata segments can be selected in various ways, such as by clicking or tapping on a metadata segment or by performing a metadata search. When a metadata segment is selected, a corresponding video segment is emphasized on the video timeline, a playback cursor is moved to the first video frame of the video segment, and the first video frame is presented.

Interacting with hierarchical clusters of video segments using a metadata panel

Hierarchical segmentation based software tool usage in a video

The technology described herein is directed to a cross-domain training framework that iteratively trains a domain adaptive refinement agent to refine low quality real-world image acquisition data, e.g., depth maps, when accompanied by corresponding conditional data from other modalities, such as the underlying images or video from which the image acquisition data is computed. The cross-domain training framework includes a shared cross-domain encoder and two conditional decoder branch networks, e.g., a synthetic conditional depth prediction branch network and a real conditional depth prediction branch network. The shared cross-domain encoder converts synthetic and real-world image acquisition data into synthetic and real compact feature representations, respectively. The synthetic and real conditional decoder branch networks convert the respective synthetic and real compact feature representations back to synthetic and real image acquisition data (refined versions) conditioned on data from the other modalities. The cross-domain training framework iteratively trains the domain adaptive refinement agent.

Refining image acquisition data through domain adaptation

Embodiments are directed to techniques for interacting with a hierarchical video segmentation using a video timeline. In some embodiments, the finest level of a hierarchical segmentation identifies the smallest interaction unit of a video—semantically defined video segments of unequal duration called clip atoms, and higher levels cluster the clip atoms into coarser sets of video segments. A presented video timeline is segmented based on one of the levels, and one or more segments are selected through interactions with the video timeline. For example, a click or tap on a video segment or a drag operation dragging along the timeline snaps selection boundaries to corresponding segment boundaries defined by the level. Navigating to a different level of the hierarchy transforms the selection into coarser or finer video segments defined by the level. Any operation can be performed on selected video segments, including playing back, trimming, or editing.

Zoom and scroll bar for a video timeline

Hierarchical segmentation of screen captured, screencasted, or streamed video

Growing community of inventors

Seattle, WA, United States of America

Dingzeyu Li