Bag of Attributes for Video Event Retrieval

Abstract

In this paper, we present the Bag-of-Attributes (BoA) model for video representation aiming at video event retrieval. The BoA model is based on a semantic feature space for representing videos, resulting in high-level video feature vectors. For creating a semantic space, i.e., the attribute space, we can train a classifier using a labeled image dataset, obtaining a classification model that can be understood as a high-level codebook. This model is used to map low-level frame vectors into high-level vectors (e.g., classifier probability scores). Then, we apply pooling operations on the frame vectors to create the final bag of attributes for the video. In the BoA representation, each dimension corresponds to one category (or attribute) of the semantic space. Other interesting properties are: compactness, flexibility regarding the classifier, and ability to encode multiple semantic concepts in a single video representation. Our experiments considered the semantic space created by a deep convolutional neural network (OverFeat) pre-trained on 1000 object categories of ImageNet. OverFeat was then used to classify each video frame and max pooling combined the frame vectors in the BoA representation for the video. Results using BoA outperformed the baselines with statistical significance in the task of video event retrieval using the EVVE dataset.

Faster and Accurate Compressed Video Action Recognition Straight from the Frequency Domain

“…Numerous deep learning methods for human action recognition have appeared in the literature [2], [7]- [11]. In most of them, a video is parsed frame by frame with convolutional neural networks (CNNs) designed for images [12], [13]. Other methods process videos as image sequences using 2D CNNs, 3D CNNs, or recurrent neural networks (RNNs) [14]- [16].…”