RECORD
SDFE-LV: A Large-Scale, Multi-Source, and Unconstrained Database for Spotting Dynamic Facial Expressions in Long Videos
Computer Vision and Pattern Recognition · Submitted 18 Sep 2022
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Finally, with the deep discussions on the experimental evaluation results, we attempt to point out several meaningful directions to deal with DFES tasks and hope that DFES can be better advanced in the future.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
In this paper, we present a large-scale, multi-source, and unconstrained database called SDFE-LV for spotting the onset and offset frames of a complete dynamic facial expression from long videos, which is known as the topic of dynamic facial expression spotting (DFES) and a vital prior step for lots of facial expression analysis tasks. Specifically, SDFE-LV consists of 1,191 long videos, each of which contains one or more complete dynamic facial expressions. Moreover, each complete dynamic facial expression in its corresponding long video was independently labeled for five times by 10 well-trained annotators. To the best of our knowledge, SDFE-LV is the first unconstrained large-scale database for the DFES task whose long videos are collected from multiple real-world/closely real-world media sources, e.g., TV interviews, documentaries, movies, and we-media short videos. Therefore, DFES tasks on SDFE-LV database will encounter numerous difficulties in practice such as head posture changes, occlusions, and illumination. We also provided a comprehensive benchmark evaluation from different angles by using lots of recent state-of-the-art deep spotting methods and hence researchers interested in DFES can quickly and easily get started. Finally, with the deep discussions on the experimental evaluation results, we attempt to point out several meaningful directions to deal with DFES tasks and hope that DFES can be better advanced in the future. In addition, SDFE-LV will be freely released for academic use only as soon as possible.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | In this paper, we present a large-scale, multi-source, and unconstrained database called SDFE-LV for spotting the onset and offset frames of a complete dynamic facial expression from long videos, which is known as the topic of dynamic facial expression spotting (DFES) and a vital prior step for lots of facial expression analysis tasks. | contribution 1.00 | 0.88 | 0.16 | asserted 1.00 |
| s1 | Specifically, SDFE-LV consists of 1,191 long videos, each of which contains one or more complete dynamic facial expressions. | method 0.53 | 0.91 | 0.04 | asserted 1.00 |
| s2 | Moreover, each complete dynamic facial expression in its corresponding long video was independently labeled for five times by 10 well-trained annotators. | method 0.95 | 0.90 | 0.03 | asserted 1.00 |
| s3 | To the best of our knowledge, SDFE-LV is the first unconstrained large-scale database for the DFES task whose long videos are collected from multiple real-world/closely real-world media sources, e.g., TV interviews, documentaries, movies, and we-media short videos. | contribution 0.73 | 0.72 | 0.11 | asserted 0.96 |
| s4 | Therefore, DFES tasks on SDFE-LV database will encounter numerous difficulties in practice such as head posture changes, occlusions, and illumination. | background 0.46 | 0.29 | 0.04 | asserted 0.85 |
| s5 | We also provided a comprehensive benchmark evaluation from different angles by using lots of recent state-of-the-art deep spotting methods and hence researchers interested in DFES can quickly and easily get started. | contribution 0.86 | 0.93 | 0.09 | asserted 1.00 |
| s6 | Finally, with the deep discussions on the experimental evaluation results, we attempt to point out several meaningful directions to deal with DFES tasks and hope that DFES can be better advanced in the future. | future work 0.99 | 0.82 | 0.27 | hedged possibility 0.54 |
| s7 | In addition, SDFE-LV will be freely released for academic use only as soon as possible. | contribution 0.69 | 0.54 | 0.04 | asserted 0.90 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
In this paper, we present a large-scale, multi-source, and unconstrained database called SDFE-LV for spotting the onset and offset frames of a complete dynamic facial expression from long videos, which is known as the topic of dynamic facial expression spotting (DFES) and a vital prior step for lots of facial expression analysis tasks. Specifically, SDFE-LV consists of 1,191 long videos, each of which contains one or more complete dynamic facial expressions. Moreover, each complete dynamic facial expression in its corresponding long video was independently labeled for five times by 10 well-trained annotators. To the best of our knowledge, SDFE-LV is the first unconstrained large-scale database for the DFES task whose long videos are collected from multiple real-world/closely real-world media sources, e.g., TV interviews, documentaries, movies, and we-media short videos. Therefore, DFES tasks on SDFE-LV database will encounter numerous difficulties in practice such as head posture changes, occlusions, and illumination. We also provided a comprehensive benchmark evaluation from different angles by using lots of recent state-of-the-art deep spotting methods and hence researchers interested in DFES can quickly and easily get started. Finally, with the deep discussions on the experimental evaluation results, we attempt to point out several meaningful directions to deal with DFES tasks and hope that DFES can be better advanced in the future. In addition, SDFE-LV will be freely released for academic use only as soon as possible.
Human review
How the literature uses it
What this paper does with the arXiv papers it cites
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.