Cartoon Face Recognition

Zheng, Yi; Zhao, Yifan; Ren, Mengyuan; He, Yan; Lu, Xiangju; Liu, Junhui; Li, Jia

doi:10.1145/3394171.3413726

Cited by 30 publications

(12 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our case, the AnyFace model achieved 100% for the indoor set and 99.2% for the outdoor set without test set augmentation. For iCartoonFace, the authors obtained 92.4% AP using the RetinaFace model [40]. In our case, the AnyFace model showed 90.61% AP.…”

Section: Results On the Test Setmentioning

confidence: 44%

“…The model was trained on manually annotated images of 3,760 frontal and 1,110 side-view faces. A large-scale annotated cartoon face dataset, iCartoonFace [40], was developed for cartoon face detection and face recognition tasks. As a baseline, the authors trained a RetinaFace model on 50,000 images (91,163 faces) and tested it on 10,000 images (18,647 faces).…”

Section: Related Workmentioning

confidence: 99%

“…The animal faces were annotated with nine key-point facial landmarks. iCartoonFace is a benchmark dataset for face detection and recognition of cartoon characters [40]. The dataset consists of 389,678 images of 5,013 cartoon characters.…”

Section: A Datasetsmentioning

confidence: 99%

“…The dataset contains 60,000 images (109,807 annotated faces) for the face detection task. TFW dataset [24] Images Faces Wider Face [22] 32,203 393,703 AnimalWeb [34] 19,079 22,451 iCartoonFace [40] 60,000 109,807 TFW [24] 9,982 16,509…”

Section: A Datasetsmentioning

confidence: 99%

See 3 more Smart Citations

AnyFace: A Data-Centric Approach For Input-Agnostic Face Detection

Kuzdeuov

Koishigarina

Varol

2023

2023 IEEE International Conference on Big Data and Smart Computing (BigComp)

View full text Add to dashboard Cite

Face detection is a mandatory step in many computer vision applications, such as face recognition, emotion recognition, age detection, virtual makeup, and vital sign monitoring. Thanks to advancements in deep learning and the introduction of annotated large-scale datasets, numerous applications have been developed for human faces. Recently, other domains, such as animals and cartoon characters, have started gaining attention but still lag far behind human faces. The biggest challenge is the limited number of annotated face datasets in these domains. The manual labeling of large-scale datasets is tedious and requires substantial human labor. In this regard, we present an inputagnostic face detector to ease the annotation of various face datasets. We propose a simple but effective data-centric approach instead of building a specific neural network architecture. Specifically, we trained a face detection model, YOLO5Face, on human, animal, and cartoon face datasets. The experiments show that the model can achieve accurate results in all domains. In addition, the model achieved decent results for animals and cartoon characters different from the ones in the training set. This implies that the model can extract agnostic facial features. We have made the source code and pre-trained models publicly available at https://github.com/IS2AI/AnyFace to stimulate research in these fields.

show abstract

Section: Results On the Test Setmentioning

confidence: 44%

Section: Related Workmentioning

confidence: 99%

Section: A Datasetsmentioning

confidence: 99%

Section: A Datasetsmentioning

confidence: 99%

See 2 more Smart Citations

AnyFace: A Data-Centric Approach For Input-Agnostic Face Detection

Kuzdeuov

Koishigarina

Varol

2023

2023 IEEE International Conference on Big Data and Smart Computing (BigComp)

View full text Add to dashboard Cite

show abstract

“…They have reported 88.5% accuracy on LTLL [FTT15] and 85.7% mAP on Oxford5k [Phi07]. Recently, [ZZR ∗ 20] have published iCartoonFace dataset for face detection and identification in animated images. While anthropomorphized faces tend to have the same facial features people have, an animated character's body shares less common attributes and perhaps makes the generalization a more challenging task.…”

Section: Related Workmentioning

confidence: 99%

CAST: Character labeling in Animation using Self‐supervision by Tracking

Nir

Rapoport²,

Shamir³

2022

Computer Graphics Forum

View full text Add to dashboard Cite

Cartoons and animation domain videos have very different characteristics compared to real-life images and videos. In addition, this domain carries a large variability in styles. Current computer vision and deep-learning solutions often fail on animated content because they were trained on natural images. In this paper we present a method to refine a semantic representation suitable for specific animated content. We first train a neural network on a large-scale set of animation videos and use the mapping to deep features as an embedding space. Next, we use self-supervision to refine the representation for any specific animation style by gathering many examples of animated characters in this style, using a multi-object tracking. These examples are used to define triplets for contrastive loss training. The refined semantic space allows better clustering of animated characters even when they have diverse manifestations. Using this space we can build dictionaries of characters in an animation videos, and define specialized classifiers for specific stylistic content (e.g., characters in a specific animation series) with very little user effort. These classifiers are the basis for automatically labeling characters in animation videos. We present results on a collection of characters in a variety of animation styles. Code and resources are available at: https://github.com/oronnir/CAST.

show abstract