Deep-Readout Random Recurrent Neural Networks for Real-World Temporal Data

Evanusa, Matthew; Shrestha, Snehesh; Patil, Vaishnavi; Fermüller, Cornelia; Girvan, Michelle; Aloimonos, Yiannis

doi:10.1007/s42979-022-01118-9

Cited by 2 publications

(1 citation statement)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…EA includes behaviors, interactions, emotional response, speech, and movements [34,35,36]. Their application range across disciplines from computer science for activity recognition [37,12,38,39,40,41], psychology for behavior analysis [11,42,35], to journalism to track and present stories over timelines [43]. However, events annotation can be challenging due to the complex nature of temporal navigation, the ability to mark at the exact desired time of sliding events, use of available features of the tools to facilitate the annotation.…”

Section: Event Based Annotationmentioning

confidence: 99%

FEVA: Fast Event Video Annotation Tool

Shrestha¹,

Sentosatio²,

Peng³

et al. 2023

Preprint

View full text Add to dashboard Cite

Video Annotation is a crucial process in computer science and social science alike. Many video annotation tools (VATs) offer a wide range of features for making annotation possible. We conducted an extensive survey of over 59 VATs and interviewed interdisciplinary researchers to evaluate the usability of VATs. Our findings suggest that most current VATs have overwhelming user interfaces, poor interaction techniques, and difficult-to-understand features. These often lead to longer annotation time, label inconsistencies, and user fatigue. We introduce FEVA, a video annotation tool with streamlined interaction techniques and a dynamic interface that makes labeling tasks easy and fast. FEVA focuses on speed, accuracy, and simplicity to make annotation quick, consistent, and straightforward. For example, annotators can control the speed and direction of the video and mark the onset and the offset of a label in real time with single key presses. In our user study, FEVA users, on average, require 36% less interaction than the most popular annotation tools (Advene, ANVIL, ELAN, VIA, and VIAN). The participants (N=32) rated FEVA as more intuitive and required less mental demand. The code and demo are available at http://www.snehesh.com/feva. Figure 1: "Speed Label" enables you to create annotations (red rectangle) in real-time by marking start (st p ) and end time (et p ) with a single key press respectively. FEVA automatically adjusts these times of the event annotation based on your reaction-time (∆r) in order to give you the most precise intended times (st i and et i ).

show abstract