Publications

@inproceedings{2021-Truong-AGTHTFIMV,

title = {Automatic Generation of Two-Level Hierarchical Tutorials from Instructional Makeup Videos},

author = {Anh Truong and Peggy Chi and David Salesin and Irfan Essa and Maneesh Agrawala},

url = {https://dl.acm.org/doi/10.1145/3411764.3445721

https://research.google/pubs/pub50007/

http://anhtruong.org/makeup_breakdown/},

doi = {10.1145/3411764.3445721},

year  = {2021},

date = {2021-05-01},

urldate = {2021-05-01},

booktitle = {ACM CHI Conference on Human factors in Computing Systems},

abstract = {We present a multi-modal approach for automatically generating hierarchical tutorials from instructional makeup videos. Our approach is inspired by prior research in cognitive psychology, which suggests that people mentally segment procedural tasks into event hierarchies, where coarse-grained events focus on objects while fine-grained events focus on actions. In the instructional makeup domain, we find that objects correspond to facial parts while fine-grained steps correspond to actions on those facial parts. Given an input instructional makeup video, we apply a set of heuristics that combine computer vision techniques with transcript text analysis to automatically identify the fine-level action steps and group these steps by facial part to form the coarse-level events. We provide a voice-enabled, mixed-media UI to visualize the resulting hierarchy and allow users to efficiently navigate the tutorial (e.g., skip ahead, return to previous steps) at their own pace. Users can navigate the hierarchy at both the facial-part and action-step levels using click-based interactions and voice commands. We demonstrate the effectiveness of segmentation algorithms and the resulting mixed-media UI on a variety of input makeup videos. A user study shows that users prefer following instructional makeup videos in our mixed-media format to the standard video UI and that they find our format much easier to navigate.},

keywords = {CHI, computational video, google, human-computer interaction, video summarization},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{2016-Bettadapura-LCCGBH,

title = {Leveraging Contextual Cues for Generating Basketball Highlights},

author = {Vinay Bettadapura and Caroline Pantofaru and Irfan Essa},

url = {https://dl.acm.org/doi/10.1145/2964284.2964286

http://www.vbettadapura.com/highlights/basketball/index.htm},

doi = {10.1145/2964284.2964286},

year  = {2016},

date = {2016-10-01},

urldate = {2016-10-01},

booktitle = {ACM International Conference on Multimedia (ACM-MM)},

organization = {ACM},

abstract = {The massive growth of sports videos has resulted in a need for automatic generation of sports highlights that are comparable in quality to the hand-edited highlights produced by broadcasters such as ESPN. Unlike previous works that mostly use audio-visual cues derived from the video, we propose an approach that additionally leverages contextual cues derived from the environment that the game is being played in. The contextual cues provide information about the excitement levels in the game, which can be ranked and selected to automatically produce high-quality basketball highlights. We introduce a new dataset of 25 NCAA games along with their play-by-play stats and the ground-truth excitement data for each basket. We explore the informativeness of five different cues derived from the video and from the environment through user studies. Our experiments show that for our study participants, the highlights produced by our system are comparable to the ones produced by ESPN for the same games.},

keywords = {ACM, ACMMM, activity recognition, computational video, computer vision, sports visualization, video summarization},

pubstate = {published},

tppubtype = {inproceedings}

}