Bangpeng Yao

Modeling mutual context of object and human pose in human-object interaction activities

Detecting objects in cluttered scenes and estimating articulated human body parts are two challenging problems in computer vision. The difficulty is particularly pronounced in activities involving human-object interactions (e.g. playing tennis), where the relevant object tends to be small or only partially visible, and the human body parts are often self-occluded. We observe, however, that objects and human poses can serve as mutual context to each other – recognizing one facilitates the recognition of the other. In this paper we propose a new random field model to encode the mutual context of objects and human poses in human-object interaction activities. We then cast the model learning task as a structure learning problem, of which the structural connectivity between the object, the overall human pose, and different body parts are estimated through a structure search approach, and the parameters of the model are estimated by a new max-margin algorithm. On a sports data set of six classes of human-object interactions [12], we show that our mutual context model significantly outperforms state-of-the-art in detecting very difficult objects and human poses.

Human action recognition by learning bases of action attributes and parts

In this work, we propose to use attributes and parts for recognizing human actions in still images. We define action attributes as the verbs that describe the properties of human actions, while the parts of actions are objects and poselets that are closely related to the actions. We jointly model the attributes and parts by learning a set of sparse bases that are shown to carry much semantic meaning. Then, the attributes and parts of an action image can be reconstructed from sparse coefficients with respect to the learned bases. This dual sparsity provides theoretical guarantee of our bases learning and feature reconstruction approach. On the PASCAL action dataset and a new “Stanford 40 Actions” dataset, we show that our method extracts meaningful high-order interactions between attributes and parts in human actions while achieving state-of-the-art classification performance.

Grouplet: A structured image representation for recognizing human and object interactions

Psychologists have proposed that many human-object interaction activities form unique classes of scenes. Recognizing these scenes is important for many social functions. To enable a computer to do this is however a challenging task. Take people-playing-musical-instrument (PPMI) as an example; to distinguish a person playing violin from a person just holding a violin requires subtle distinction of characteristic image features and feature arrangements that differentiate these two scenes. Most of the existing image representation methods are either too coarse (e.g. BoW) or too sparse (e.g. constellation models) for performing this task. In this paper, we propose a new image feature representation called “grouplet”. The grouplet captures the structured information of an image by encoding a number of discriminative visual features and their spatial configurations. Using a dataset of 7 different PPMI activities, we show that grouplets are more effective in classifying and detecting human-object interactions than other state-of-the-art methods. In particular, our method can make a robust distinction between humans playing the instruments and humans co-occurring with the instruments without playing.

Combining randomization and discrimination for fine-grained image categorization

In this paper, we study the problem of fine-grained image categorization. The goal of our method is to explore fine image statistics and identify the discriminative image patches for recognition. We achieve this goal by combining two ideas, discriminative feature mining and randomization. Discriminative feature mining allows us to model the detailed information that distinguishes different classes of images, while randomization allows us to handle the huge feature space and prevents over-fitting. We propose a random forest with discriminative decision trees algorithm, where every tree node is a discriminative classifier that is trained by combining the information in this node as well as all upstream nodes. Our method is tested on both subordinate categorization and activity recognition datasets. Experimental results show that our method identifies semantically meaningful visual information and outperforms state-of-the-art algorithms on various datasets.

Recognizing Human-Object Interactions in Still Images by Modeling the Mutual Context of Objects and Human Poses

Detecting objects in cluttered scenes and estimating articulated human body parts from 2D images are two challenging problems in computer vision. The difficulty is particularly pronounced in activities involving human-object interactions (e.g., playing tennis), where the relevant objects tend to be small or only partially visible and the human body parts are often self-occluded. We observe, however, that objects and human poses can serve as mutual context to each other-recognizing one facilitates the recognition of the other. In this paper, we propose a mutual context model to jointly model objects and human poses in human-object interaction activities. In our approach, object detection provides a strong prior for better human pose estimation, while human pose estimation improves the accuracy of detecting the objects that interact with the human. On a six-class sports data set and a 24-class people interacting with musical instruments data set, we show that our mutual context model outperforms state of the art in detecting very difficult objects and estimating human poses, as well as classifying human-object interaction activities.

A codebook-free and annotation-free approach for fine-grained image categorization

Fine-grained categorization refers to the task of classifying objects that belong to the same basic-level class (e.g. different bird species) and share similar shape or visual appearances. Most of the state-of-the-art basic-level object classification algorithms have difficulties in this challenging problem. One reason for this can be attributed to the popular codebook-based image representation, often resulting in loss of subtle image information that are critical for fine-grained classification. Another way to address this problem is to introduce human annotations of object attributes or key points, a tedious process that is also difficult to generalize to new tasks. In this work, we propose a codebook-free and annotation-free approach for fine-grained image categorization. Instead of using vector-quantized codewords, we obtain an image representation by running a high throughput template matching process using a large number of randomly generated image templates. We then propose a novel bagging-based algorithm to build a final classifier by aggregating a set of discriminative yet largely uncorrelated classifiers. Experimental results show that our method outperforms state-of-the-art classification approaches on the Caltech-UCSD Birds dataset.

Decision tree fields

This paper introduces a new formulation for discrete image labeling tasks, the Decision Tree Field (DTF), that combines and generalizes random forests and conditional random fields (CRF) which have been widely used in computer vision. In a typical CRF model the unary potentials are derived from sophisticated random forest or boosting based classifiers, however, the pairwise potentials are assumed to (1) have a simple parametric form with a pre-specified and fixed dependence on the image data, and (2) to be defined on the basis of a small and fixed neighborhood. In contrast, in DTF, local interactions between multiple variables are determined by means of decision trees evaluated on the image data, allowing the interactions to be adapted to the image content. This results in powerful graphical models which are able to represent complex label structure. Our key technical contribution is to show that the DTF model can be trained efficiently and jointly using a convex approximate likelihood function, enabling us to learn over a million free model parameters. We show experimentally that for applications which have a rich and complex label structure, our model achieves excellent results.

Action recognition with exemplar based 2.5d graph matching

This paper deals with recognizing human actions in still images. We make two key contributions. (1) We propose a novel, 2.5D representation of action images that considers both view-independent pose information and rich appearance information. A 2.5D graph of an action image consists of a set of nodes that are key-points of the human body, as well as a set of edges that are spatial relationships between the nodes. Each key-point is represented by view-independent 3D positions and local 2D appearance features. The similarity between two action images can then be measured by matching their corresponding 2.5D graphs. (2) We use an exemplar based action classification approach, where a set of representative images are selected for each action class. The selected images cover large within-action variations and carry discriminative information compared with the other classes. This exemplar based representation of action classes further makes our approach robust to pose variations and occlusions. We test our method on two publicly available datasets and show that it achieves very promising performance.

Social Role Discovery in Human Events

We deal with the problem of recognizing social roles played by people in an event. Social roles are governed by human interactions, and form a fundamental component of human event description. We focus on a weakly supervised setting, where we are provided different videos belonging to an event class, without training role labels. Since social roles are described by the interaction between people in an event, we propose a Conditional Random Field to model the inter-role interactions, along with person specific social descriptors. We develop tractable variational inference to simultaneously infer model weights, as well as role assignment to all people in the videos. We also present a novel YouTube social roles dataset with ground truth role annotations, and introduce annotations on a subset of videos from the TRECVID-MED11 [1] event kits for evaluation purposes. The performance of the model is compared against different baseline methods on these datasets.

Combining the Right Features for Complex Event Recognition

In this paper, we tackle the problem of combining features extracted from video for complex event recognition. Feature combination is an especially relevant task in video data, as there are many features we can extract, ranging from image features computed from individual frames to video features that take temporal information into account. To combine features effectively, we propose a method that is able to be selective of different subsets of features, as some features or feature combinations may be uninformative for certain classes. We introduce a hierarchical method for combining features based on the AND/OR graph structure, where nodes in the graph represent combinations of different sets of features. Our method automatically learns the structure of the AND/OR graph using score-based structure learning, and we introduce an inference procedure that is able to efficiently compute structure scores. We present promising results and analysis on the difficult and large-scale 2011 TRECVID Multimedia Event Detection dataset.