Learning Subject-Aware Cropping by Outpainting Professional Photos

no code implementations • 19 Dec 2023 • James Hong, Lu Yuan, Michaël Gharbi, Matthew Fisher, Kayvon Fatahalian

How to frame (or crop) a photo often depends on the image subject and its context; e. g., a human portrait.

Image Cropping

Spotting Temporally Precise, Fine-Grained Events in Video

2 code implementations • 20 Jul 2022 • James Hong, Haotian Zhang, Michaël Gharbi, Matthew Fisher, Kayvon Fatahalian

We introduce the task of spotting temporally precise, fine-grained events in video (detecting the precise moment in time events occur).

Action Detection Action Spotting +2

Video Pose Distillation for Few-Shot, Fine-Grained Sports Action Recognition

1 code implementation • ICCV 2021 • James Hong, Matthew Fisher, Michaël Gharbi, Kayvon Fatahalian

This leads to poor accuracy when downstream tasks, such as action recognition, depend on pose.

Action Understanding Fine-grained Action Recognition +2

Rekall: Specifying Video Events using Compositions of Spatiotemporal Labels

1 code implementation • 7 Oct 2019 • Daniel Y. Fu, Will Crichton, James Hong, Xinwei Yao, Haotian Zhang, Anh Truong, Avanika Narayan, Maneesh Agrawala, Christopher Ré, Kayvon Fatahalian

Many real-world video analysis applications require the ability to identify domain-specific events in video, such as interviews and commercials in TV news broadcasts, or action sequences in film.

Learning in situ: a randomized experiment in video streaming

no code implementations • 3 Jun 2019 • Francis Y. Yan, Hudson Ayers, Chenzhi Zhu, Sadjad Fouladi, James Hong, Keyi Zhang, Philip Levis, Keith Winstein

We describe the results of a randomized controlled trial of video-streaming algorithms for bitrate selection and network prediction.

Networking and Internet Architecture