Abstract. This paper proposes a metric learning based approach for human activity recognition with two main objectives: (1) reject unfamiliar activities and (2) learn with few examples. We show that our approach outperforms all state-of-the-art methods on numerous standard datasets for traditional action classification problem. Furthermore, we demonstrate that our method not only can accurately label activities but also can reject unseen activities and can learn from few examples with high accuracy. We finally show that our approach works well on noisy YouTube videos. 1

We describe a “bag-of-rectangles ” method for representing and recognizing human actions in videos. In this method, each human pose in an action sequence is represented by oriented rectangular patches extracted over the whole body. Then, spatial oriented histograms are formed to represent the distribution of these rectangular patches. In order to carry the information from the spatial domain described by the bag-of-rectangles descriptor to temporal domain for recognition of the actions, four different methods are proposed. These are namely, (i) frame by frame voting, which recognizes the actions by matching the descriptors of each frame, (ii) global histogramming, which extends the idea of Motion Energy Image proposed by Bobick and Davis by rectangular patches, (iii) a classifier based approach using SVMs, and (iv) adaptation of Dynamic Time Warping on the temporal representation of the descriptor. The detailed experiments are carried out on the action dataset of Blank et. al. High success rates (100%) prove that with a very simple and compact representation, we can achieve robust recognition of human actions, compared to complex representations.

Abstract. Most state-of-the-art approaches to action recognition rely on global representations either by concatenating local information in a long descriptor vector or by computing a single location independent histogram. This limits their performance in presence of occlusions and when running on multiple viewpoints. We propose a novel approach to providing robustness to both occlusions and viewpoint changes that yields significant improvements over existing techniques. At its heart is a local partitioning and hierarchical classification of the 3D Histogram of Oriented Gradients (HOG) descriptor to represent sequences of images that have been concatenated into a data volume. We achieve robustness to occlusions and viewpoint changes by combining training data from all viewpoints to train classifiers that estimate action labels independently over sets of HOG blocks. A top level classifier combines these local labels into a global action class decision. 1

We present a compact representation for human action recognition in videos using line and optical flow histograms. We introduce a new shape descriptor based on the distribution of lines which are fitted to boundaries of human figures. By using an entropy-based approach, we apply feature selection to densify our feature representation, thus, minimizing classification time without degrading accuracy. We also use a compact representation of optical flow for motion information. Using line and flow histograms together with global velocity information, we show that high-accuracy action recognition is possible, even in challenging recording conditions. 1 1.

Abstract not found

Abstract. We present a simple approach to action classification which constructs a vector quantization of primitive motions from time series data corresponding to relative limb position estimates. The temporal scale, mean, and shape of primitive motion trajectories are independently modeled, thus creating a flexible dictionary of action primitives. We then explore two inference techniques that leverage our action dictionary representation, and evaluate their performance on both motion capture and video benchmark data. Our results indicate that even simplistic algorithms can outperform significantly more sophisticated ones in existing benchmark datasets. 1

sminchisescu.ins.uni-bonn.de Recognizing human action in non-instrumented video is a challenging task not only because of the variability produced by general scene factors like illumination, background, occlusion or intra-class variability, but also because of subtle behavioral patterns among interacting people or between people and objects in images. To improve recognition, a system may need to use not only low-level spatio-temporal video correlations but also relational descriptors between people and objects in the scene. In this paperwepresentcontextualscenedescriptorsandBayesian multiplekernellearningmethodsforrecognizinghumanaction in complex non-instrumented video. Our contribution is threefold: (1) we introduce bag-of-detector scene descriptorsthatencodepresence/absenceandstructuralrelations