Adobe, Inc.

Google Inc.

Microsoft Technology Licensing, LLC

Aseem Agarwala

Lubomira A Dontcheva

Joel Richard Brandt

Hijung Shin

Xue Bai

Dingzeyu Li

Jovan Popović

Joy Oakyung Kim

Seth John Walker

Hailin Jin

Cristin Ailidh Fraser

Jue Wang

Elya Shechtman

Gregg Darryl Wilensky

Walter Chang

Justin Salamon

Gierad P Laput

Jianchao Yang

Jonathan Worthen Brandt

Timothy Jeewun Ganter

Haoran Cai

Jui-hsien Wang

Sarah Kong

Daniel Goldman

Feng Liu

Alan Lee Erickson

Yuyan Song

Kshitiz Garg

Bradee Rae Evans

Fabian David Caba Heilbron

Ali Aminian

Robert E Carroll

Guang Chen

Shai Bagon

Raviteja Vemulapalli

Hanieh Deilamsalehy

Richard S Szeliski

Michael F Cohen

Aaron Phillip Hertzmann

Maneesh Agrawala

Chintan Intwala

David H Salesin

Kim Pascal Pimmel

William L Marino

Aashish Misraa

Michael Lee Gleicher

Yuanzhen Li

Sujit Kuthirummal

Daniel Leventhal

Morgan Nicole Evans

Yiming Liu

Najika Skyler Halsema Yoo

Erik Randall Johnson

Zhangyang Wang

Mohammad Amin Sadeghi

Ziwei Liu

Embodiments of the present invention provide systems, methods, and computer storage media for extracting moments of interest (e.g., video frames, video segments) from a video. In an example embodiment, independent and/or orthogonal machine learning models are used to extract different types of features considering different modalities, and each frame in the video is assigned an importance score for each model. The importance scores for each model are combined into an aggregated importance score for each frame in the video. Depending on the embodiment, the aggregated importance scores are used to visualize the score per frame, identify moments of interest, automatically crop down the video into a highlight reel, browse or visualize the moments of interest within the video, and/or search across multiple videos.

Customizable framework to extract moments of interest

Some aspects of the technology described herein perform identity identification on faces in a video. Object tracking is performed on detected faces in frames of a video to generate tracklets. Each tracklet comprises a sequence of consecutive frames in which each frame includes a detected face for a person. The tracklets are clustered using face feature vectors for detected faces of each tracklet to generate a plurality of clusters. Information is stored in an identity datastore, including a first identifier for a first identity in association with an indication of frames from tracklets in a first cluster from the plurality of clusters.

Tracking unique face identities in videos

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 of the present invention provide systems, methods, and computer storage media for selection of the best image of a particular speaker's face in a video, and visualization in a diarized transcript. In an example embodiment, candidate images of a face of a detected speaker are extracted from frames of a video identified by a detected face track for the face, and a representative image of the detected speaker's face is selected from the candidate images based on image quality, facial emotion (e.g., using an emotion classifier that generates a happiness score), a size factor (e.g., favoring larger images), and/or penalizing images that appear towards the beginning or end of a face track. As such, each segment of the transcript is presented with the representative image of the speaker who spoke that segment and/or input is accepted changing the representative image associated with each speaker.

Speaker thumbnail selection and speaker visualization in diarized transcripts for text-based video

Embodiments of the present invention provide systems, methods, and computer storage media for segmenting a transcript into paragraphs. In an example embodiment, a transcript is segmented to start a new paragraph whenever there is a change in speaker and/or a long pause in speech. If any remaining paragraphs are longer than a designated length or duration (e.g., 50 or 100 words), each of those paragraphs is segmented using dynamic programming to minimize a cost function that penalizes candidate paragraphs based on divergence from a target paragraph length and/or that rewards candidate paragraphs that group semantically similar sentences. As such, the transcript is visualized, segmented at the identified paragraphs.

Transcript paragraph segmentation and visualization of transcript paragraphs

Embodiments of the present invention provide systems, methods, and computer storage media for music-aware speaker diarization. In an example embodiment, one or more audio classifiers detect speech and music independently of each other, which facilitates detecting regions in an audio track that contain music but do not contain speech. These music-only regions are compared to the transcript, and any transcription and speakers that overlap in time with the music-only regions are removed from the transcript. In some embodiments, rather than having the transcript display the text from this detected music, a visual representation of the audio waveform is included in the corresponding regions of the transcript.

Music-aware speaker diarization for transcripts and text-based video editing

Embodiments of the present invention provide systems, methods, and computer storage media for face-aware speaker diarization. In an example embodiment, an audio-only speaker diarization technique is applied to generate an audio-only speaker diarization of a video, an audio-visual speaker diarization technique is applied to generate a face-aware speaker diarization of the video, and the audio-only speaker diarization is refined using the face-aware speaker diarization to generate a hybrid speaker diarization that links detected faces to detected voices. In some embodiments, to accommodate videos with small faces that appear pixelated, a cropped image of any given face is extracted from each frame of the video, and the size of the cropped image is used to select a corresponding active speaker detection model to predict an active speaker score for the face in the cropped image.

Face-aware speaker diarization for transcripts and text-based video editing

Embodiments of the present invention provide systems, methods, and computer storage media for identifying candidate boundaries for video segments, video segment selection using those boundaries, and text-based video editing of video segments selected via transcript interactions. In an example implementation, boundaries of detected sentences and words are extracted from a transcript, the boundaries are retimed into an adjacent speech gap to a location where voice or audio activity is a minimum, and the resulting boundaries are stored as candidate boundaries for video segments. As such, a transcript interface presents the transcript, interprets input selecting transcript text as an instruction to select a video segment with corresponding boundaries selected from the candidate boundaries, and interprets commands that are traditionally thought of as text-based operations (e.g., cut, copy, paste) as an instruction to perform a corresponding video editing operation using the selected video segment.

Video segment selection and editing using transcript interactions

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

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

Embodiments are directed to interactive tiles that represent video segments of a segmentation of a video. In some embodiments, each interactive tile represents a different video segment from a particular video segmentation (e.g., a default video segmentation). Each interactive tile includes a thumbnail (e.g., the first frame of the video segment represented by the tile), some transcript from the beginning of the video segment, a visualization of detected faces in the video segment, and one or more faceted timelines that visualize a category of detected features (e.g., a visualization of detected visual scenes, audio classifications, visual artifacts). In some embodiments, interacting with a particular interactive tile navigates to a corresponding portion of the video, adds a corresponding video segment to a selection, and/or scrubs through tile thumbnails.

Interacting with semantic video segments through interactive tiles

Growing community of inventors

Seattle, WA, United States of America

Aseem Agarwala