Context-Aware CNNs for Person Head Detection

By Tuan-Hung Vu, Anton Osokin, Ivan Laptev. 2015

146 citations recorded by the source corpus.

Person detection is a key problem for many computer vision tasks. While face detection has reached maturity, detecting people under full variation of camera view-points, human poses, lighting conditions and occlusions is still a difficult challenge. In this work we focus on detecting human heads in natural scenes. Starting from the recent R-CNN object detector, we extend it in two ways. First, we leverage person-scene relations and propose a global CNN model trained to predict positions and scales of heads directly from the full image. Second, we explicitly model pairwise relations among the objects via energy-based model where the potentials are computed with a CNN framework. Our full combined model complements R-CNN with contextual cues derived from the scene. To train and test our model, we introduce a large dataset with 369,846 human heads annotated in 224,740 movie frames. We evaluate our method and demonstrate improvements of person head detection compared to several recent baselines on three datasets. We also show improvements of the detection speed provided by our model.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Faceless Person Recognition: Privacy Implications in Social Media (2016, background): “CRF often used for joint recognition problems in computer vision [42, 43, 50, 51].”
Fast, Exact and Multi-scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs (2016, methodology): “In independent work [2] proposed a similar approach for the task of image segmentation with CNNs, where as in [14,15,18] FCNs are augmented with discriminatively trained convolutional layers that model and enforce pairwise consistencies between neighbouring regions.”
Dense and Low-Rank Gaussian CRFs Using Deep Embeddings (2017, background): “Regarding (a), [2, 26, 27, 28, 33, 34, 40] showed that structured prediction can be unfolded in time and thus be trained end-to-end with CNNs for both sparselyconnected [33] and fully-connected [26, 28, 34, 40] graphical structures.”
Abnormal Event Detection in Videos using Spatiotemporal Autoencoder (2017, background): “Speciﬁcally, convolutional neural networks (ConvNet) have proved its eﬀectiveness in a wide range of applications such as object recognition [26], person detection [28], and action recognition [27, 25].”