Recognize complex events from static images by fusing deep channels

By Yuanjun Xiong, Kai Zhu, Dahua Lin, Xiaoou Tang. 2015

129 citations recorded by the source corpus.

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

Temporal Segment Networks for Action Recognition in Videos (2017, neutral): “objects [7], [8], [9], scenes [10], [11], [12], and complex events [13], [14].”
Temporal Segment Networks: Towards Good Practices for Deep Action Recognition (2016, background): “Recently, Convolutional Networks (ConvNets) [7] have witnessed great success in classifying images of objects, scenes, and complex events [8,9,10,11].”
Factorizable Net: An Efficient Subgraph-based Framework for Scene Graph Generation (2018, background): “In the early stage, most of the works targeted on using speciﬁc types of visual relations, such as spatial relations [5, 10, 14, 20, 26, 30] and actions ( i . e . interactions between objects) [1, 9, 11, 16, 19, 46, 47, 50, 56, 57, 60].”
A Review of Human Activity Recognition Methods (2015, methodology): “Xiong et al. (2015) utilized CNNs to hierarchically combine information from different visual channels.”
Multi-Modal Knowledge Graph Construction and Application: A Survey (2022, background): “The visual arguments detection relies on the cooccurrence [94], [95] and relative positions [96] of detected objects.”
Scene Graph Generation With External Knowledge and Image Reconstruction (2019, background): “With recent breakthroughs in deep learning and image recognition, higher-level visual understanding tasks, such as visual relationship detection, has been a popular research topic [9, 19, 15, 40, 44].”
Actionness Estimation Using Hybrid Fully Convolutional Networks (2016, background): “Convolutional neural networks (CNNs) have achieved remarkable successes for various tasks, such as object recognition [19, 31, 33, 49], event recognition [43, 8], crowd analysis [27, 28] and so on.”
WIDER FACE: A Face Detection Benchmark (2015, methodology): “WIDER FACE dataset is a subset of the WIDER dataset [22].”
Knowledge Guided Disambiguation for Large-Scale Scene Classification With Multi-Resolution CNNs (2016, background): “object detection [13], [14], event recognition [15], [16], and action recognition [17], [18].”
Blind late fusion in multimedia event retrieval (2016, background): “[32] combine a spatial detection map and a holistic deep representation using a deep neural network.”
A Survey of the Four Pillars for Small Object Detection: Multiscale Representation, Contextual Information, Super-Resolution, and Region Proposal (2022, methodology): “2(d), WIDER FACE contains 32 203 images, which are extracted from the public WIDER dataset [62].”