Improving the Utility of Automated Processing for Digital

Improving the Utility of Automated Processing for Digital Video Archives Mike Christel christel@cs. cmu. edu Entertainment Technology Center Carnegie Mellon University Penn State March 1, 2010

Talk Outline • Automatically creating metadata for digital video • Informedia demonstrations (oral history collection, news video collection) • Types of search: beyond fact-finding • Exploratory search through multiple views • Evaluation hurdles • Discussion …now is a perfect opportunity for leveraging user involvement for better video information-seeking experiences

User Involvement • User Correction: Corrective action for metadata errors (analogous to Harry Shum’s vision at Microsoft for human-assisted computer vision success) • User Control: Driving the interface to overcome metadata errors • User Context: More useful interfaces driven implicitly by context

CMU Informedia Digital Video Research • Details at: http: //www. informedia. cs. cmu. edu • Speech recognition and alignment • Image processing • Named entity tagging • Synchronized metadata for search and navigation • Fast, direct video access to oral histories, news, etc. • Demonstration oral history corpus: 913 hours of interviews from 400 individuals, 18, 254 interview story segments (average story segment length of 3 minutes) • Demonstration news corpus: TRECVID 2006 test set (165 hours of U. S. , Arabic, and Chinese news with 79, 484 reference shots)

Speech Recognition Functions • Generates transcript (if one is not given) to enable textbased retrieval from spoken language documents • Improves text synchronization to audio/video in presence of scripts (align speech with text) • Supplies necessary information for library segmentation and multimedia abstractions (e. g. , break stories apart at silence points rather than in the middle of sentences)

Speech Alignment Example

Image Understanding Functions • Scene segmentation • Similarity matching • Camera motion determination and object tracking • Optical Character Recognition (OCR) on video text and titles • Face detection and recognition • Ongoing research work in object identification and scene characterization, e. g. , indoor/outdoor, road, building, etc.

Images containing similar colors… Image search with tropical rainforest image leads to…

Images containing similar colors

Images containing similar shapes

Images containing similar content

Goal: Automatic Video Characterization Shots Yellowstone Camera Static Zoom Objects Adult Female Animal Two adults Action Head Motion Left Motion None CNN An Online First Outdoor Indoor Captions CNN LIVE Scenery Studio

Goal: Automatic Video Characterization Shots Yellowstone Camera Static Zoom Objects Adult Female Animal Two adults Action Head Motion Left Motion None CNN An Online First Outdoor Indoor Captions CNN LIVE Scenery Studio

Automated Video Processing • Produces descriptive metadata for video libraries • Metadata has errors greater than metadata produced by a careful, human-provided annotation • Errors in metadata can be reduced: By more computation-intensive algorithms By taking advantage of video frame-to-frame redundancy By folding in context, e. g. , probable text sizes in video By folding in extra sources of knowledge, e. g. , a dictionary for cleaning up VOCR, or labeled data revealing patterns for named entity detection • By human review and correction, which can generate additional labeled data for machine learning • •

Camera and Motion Detection Pan Success through Lucas-Kanade optical flow algorithm Right object motion (not pan left)

Text and Face Detection

Face Detection: A Success Story • Many deployments, from digital cameras to remove redeye and improve focus, to interactive art (see ETC hallways) • Henry Schneiderman, Ph. D from Carnegie Mellon who worked with Informedia group at CMU • Founder of Pittsburgh Pattern Recognition (Pitt. Patt) • Test out state of the art yourself at www. pittpatt. com

Video OCR Block Diagram Video Text Area Detection Text Area Preprocessing Commercial OCR ASCII Text

Video Frames (1/2 s intervals) Filtered Frames AND-ed Frames

VOCR Preprocessing Problems

Augmenting VOCR with Dictionary Look-up

“Name-It” Face/Name Association Video Face Extraction Transcript …said President Clinton. Al Gore presented his policies…. Gore stated…. In a gala affair, Clinton addressed…. Name Extraction Face/Name Association (Co-occurrence evaluation) Who is Gore? Clinton

Named Entity Extraction F. Kubala, R. Schwartz, R. Stone, and R. Weischedel, “Named Entity Extraction from Speech”, Proc. DARPA Workshop on Broadcast News Understanding Systems, Lansdowne, VA, February 1998. CNN national correspondent John Holliman is at Hartsfield International Airport in Atlanta. Good morning, John. …But there was one situation here at Hartsfield where one airplane flying from Atlanta to Newark, New Jersey yesterday had a mechanical problem and it caused a backup that spread throughout the whole system because even though there were a lot of planes flying to the New York area from the Atlanta area yesterday, …. Key: Place, Time, Organization/Person

Enhancing Library Utility via Better Metadata Extractor People Perspective Templates Event Affiliation Location Summarizer Topics Time User Interface (final representation)

Improving the Interface via Usage Context Example: query-based thumbnail selection

Improving Utility through End-User Control Example: filtering storyboard based on visual concepts with user controlling precision and recall

Improving the Metadata via User Interaction • Example: collecting positive and implicit negative sets of labeled shot data for visual concepts • Reference: Ming-yu Chen, et al. , ACM Multimedia 2005

User Involvement ü User Correction: Corrective action for metadata errors (analogous to Harry Shum’s vision at Microsoft for human-assisted computer vision success) ü User Control: Driving the interface to overcome metadata errors • User Context: More useful interfaces driven implicitly by context

Video Summaries (without User Context) • BBC rushes video summarization task in TRECVID 2007 and TRECVID 2008 shows difficulty of the task • Video summary is “a condensed version of some information, such that various judgments about the full information can be made using only the summary and taking less time and effort than would be required using the full information source” • Maximum 4% duration (2% in TRECVID 2008) • Benefits of this TRECVID task: provides a reasonably large video collection to be summarized, a uniform method of creating ground truth, and a uniform scoring mechanism

BBC Rushes • 42 test videos (+ development ones) from BBC Archive • Test videos: • minimum duration 3. 3 minutes • maximum duration 36. 4 minutes • mean duration 25 minutes • Raw (unedited) rush video with a great deal of redundancy (repeated takes), mixed quality audio, “junk” frames

Video Summaries (with/without User Context) • BBC Rush video has no context to build from • However, users often provide cues as to what is important, as will be seen shortly

Storyboards: TRECVID Search Success • For the shot-based directed search information retrieval task evaluated at TRECVID, storyboards have consistently and overwhelmingly produced the best performance (see references in paper, e. g. , [Snoek et al. 2007]) • Motivated users can navigate through thousands of shot thumbnails in storyboards, better even than with “extreme video retrieval” interfaces: 2487 shots on average per 15 minute topic for TRECVID 2006 [Christel/Yan CIVR 2007] • Storyboard benefits: packed visual overview, trivial interactive control needed for “overview, zoom and filter, details on demand” – Shneiderman’s Visual Information -Seeking Mantra

Beyond Fact-Finding • CACM April 2006 special issue on this topic • G. Marchionini (“Exploratory Search: From Finding to Understanding, ” CACM 49, April 2006) breaks down 3 types of search activities: • Lookup (fact-finding; solving stated/understood need) • Learn • Investigate • Computer scientists and information retrieval specialists emphasize evaluation of lookup activities (NIST TREC) • Real world interest in learn/investigate: for an oral history collection, State Univ. New York at Buffalo Workshop library science and humanities participants quite interested in learn/investigate activities

Exploratory Search (Demonstrations) • Examples where storyboards still useful: visual review, e. g. , of disaster field footage • Where storyboards fail: • Showing other facets like time, space, co-occurrence, named entities (When did disasters occur? Which ones? Where? ) • Providing collection understanding, a holistic view of what’s in say 100 s of segments of 1000 s of matching shots • Providing window into visually homogenous results, e. g. , results from color search perhaps, or a corpus of just lecture slides, or head-and-shoulder interview shots • Claim: Storyboards are not sufficient, but are part of a useful suite of tools/interfaces for interactive video search

Anecdotal Support for Claim • Collected 2006 -2007 from: • Government analysts with news data • History students and faculty with oral history data • Views Tested: • • • Timeline Visualization By Example (VIBE) Plot (query terms) Map View Named Entity view (people, places, organizations) Text-dominant views: • Nested Lists (pre-defined clusters by contributor) • Common Text (on-the-fly grouping of common phrases)

Anecdotal Results • 38 History. Makers corpus users (mostly students, 15 female, average 24), experienced web searchers, modest digital video experience • 6 intelligence analysts (1 female; 2 older than 40, 3 in their 30 s, 1 in 20 s), very experienced text searchers, experienced web searchers, novice video searchers • View use minimal aside from Common Text • Text titling and text transcripts used frequently • A bit of evidence for collection understanding (e. g. , diffs in topic between New York and Chicago), but overall, cautious use of default settings for initial trial(s).

Evaluation Hurdles • How does one evaluate information visualization for promoting exploratory video search? • Low level simple tasks vs. complex real-world tasks • Traditional effectiveness, efficiency, satisfaction are even problematic: is “fast” interface for exploration good or bad? • HCI discount usability techniques offer some support, but ecological validity may limit impact of conclusions (e. g. , HCII students found Common Text well suited for History students) • Look to field of Visual Analytics for help, e. g. , Plaisant • “First hour with system” studies, or “developer as user” insights too limiting. Rather, consider Multi-dimensional In-depth Long-term Case-studies (MILC)

Concluding Points - 1 • “Interactive” allows human direction to compensate for automation shortcomings and varying needs • Interactive fact-finding better than automated fact-finding in visual shot retrieval (TRECVID) • Interactive computer vision has successes (Harry Shum at Microsoft, Michael Brown et al. at NUS) • Interactive view/facet control == ? ? ? (too early to tell) • Users need scaffolding/support to get started • Evaluations need to run longer term, in depth, with case studies to see what has benefit (Multidimensional In-depth Long-term Case studies - MILC)

Concluding Points - 2 • Storyboards work well for visual overview • Video surrogates can be made more effective, efficient, and satisfying when tailored to user activity (leverage context) • Interface should provide easy tuning of precision vs. recall • As cheap storage and transmission is producing a wealth of digital video, exploratory search will gain emphasis regarding video repositories • Augment automatically produced metadata with humanprovided descriptors (take advantage of what users are willing to volunteer, and in fact solicit additional feedback from humans through motivating games that allow for human computation, a research focus of Luis von Ahn at Carnegie Mellon University)

Games with a Purpose • Spearheaded by von Ahn, www. gwap. com • ESP Game showed success of “human computation” for tagging imagery • Ongoing projects, including a current one at CMU Entertainment Technology Center, Prometheus, to further explore crowd-sourced games (www. etc. cmu. edu/projects)

Credits Many members of the Informedia Project, CMU research community, and The History. Makers contributed to this work, including: Informedia Project Director: Howard Wactlar The History. Makers Executive Director: Julieanna Richardson History. Makers Beta Testers: Joe Trotter (CMU History Dept. ), SUNY at Buffalo and all UB Workshop participants: Schomburg Center for Research in Black Culture, NY Public Library, Randforce Associates, University of Illinois (3 campuses) Informedia User Interface: Ron Conescu, Neema Moraveji Informedia Processing: Alex Hauptmann, Ming-yu Chen, Wei-Hao Lin, Rong Yan, Jun Yang Informedia Library Essentials: Scott Stevens, Bob Baron, Bryan Maher This work supported by the National Science Foundation under Grant Nos. IIS -0205219 and IIS-0705491