header image

This paper presents an approach to estimating the 2.1D sketch from monocular, low-level visual cues. We use a low-level segmenter to partition the image into regions, and, then, estimate their 2.1D sketch, subject to figure-ground and similarity constraints between neighboring regions. The 2.1D sketch assigns a depth ordering to image regions which are expected to correspond to objects and surfaces in the scene. This is cast as a constrained convex optimization problem, and solved within the optimization transfer framework. The optimization objective takes into account the curvature and convexity of parts of region boundaries, appearance, and spatial layout properties of regions. Our new optimization transfer algorithm admits a closed-form expression of the duality gap, and thus allows explicit computation of the achieved accuracy. The algorithm is efficient with quadratic complexity in the number of constraints between image regions. Quantitative and qualitative results on challenging, real-world images of Berkeley segmentation, Geometric Context, and Stanford Make3D datasets demonstrate our high accuracy, efficiency, and robustness. Preprint  Supplement  Code

under: Publications

This dissertation addresses the problem of recognizing human activities in videos. Our focus is on activities with stochastic structure, where the activities are characterized by variable space-time arrangements of actions, and conducted by a variable number of actors. These activities occur frequently in sports and surveillance videos. They may appear jointly in multiple instances, at different spatial and temporal scales, under occlusion, and amidst background clutter. These challenges have never been addressed in the literature. Our hypothesis is that these challenges can be successfully addressed using expressive, hierarchical models explicitly encoding activity parts and their spatio-temporal relations. Our hypothesis is formalized using two novel paradigms. One specifies a new constrained hierarchical model of activities allowing efficient activity recognition. Specifically, we formulate Sum-Product Networks (SPNs) for modeling activities, and develop two new learning algorithms using variational learning. The other paradigm considers a more expressive (unconstrained) hierarchical model, And-Or Graphs (AOGs), requiring cost-efficient algorithms for activity recognition. In particular, we develop a new, Monte Carlo Tree Search based inference of AOGs. Our theoretical and empirical studies advance computer vision through demonstrated advantages of each paradigm, compared to the state-of-the-art. Dissertation

under: Dissertation
This paper addresses the problem of recognizing and localizing coherent activities of a group of people, called collective activities, in video. Related work has argued the benefits of capturing long-range and higher-order dependencies among video features for robust recognition. To this end, we formulate a new deep model, called Hierarchical Random Field (HiRF). HiRF models only hierarchical dependencies between model variables. This effectively amounts to modeling higher-order temporal dependencies of video features. We specify an efficient inference of HiRF that iterates in each step linear programming for estimating latent variables. Learning of HiRF parameters is specified within the max-margin framework. Our evaluation on the benchmark New Collective Activity and Collective Activity datasets, demonstrates that HiRF yields superior recognition and localization as compared to the state of the art. Paper
under: Main Conference, Publications

We propose a novel staged hybrid model for emotion detection in speech. Hybrid models exploit the strength of discriminative classifiers along with the representational power of generative models. Discriminative classifiers have been shown to achieve higher performances than the corresponding generative likelihood-based classifiers. On the other hand, generative models learn a rich informative representations. Our proposed hybrid model consists of a generative model, which is used for for unsupervised representation learning of short term temporal phenomena and a discriminative model,which is used for for event detection and classification of long range temporal dynamics. We evaluate our approach on multiple audio datasets (AVEC, VAM, and SPD) and demonstrate its superiority compared to the state-of-the-art. Paper

under: Main Conference, Publications

1st Workshop on Computational Models of Social Interactions and Behavior: Scientific Grounding, Sensing, and Applications (CVPR 2014)

Humans form a multitude of social groups through their life and regularly interact with other humans in these groups producing social behavior. Social behavior is behavior that is socially relevant or is situated in an identifiable social context. Interacting or observant humans sense, interpret and understand these behaviors mostly using aural and visual sensory stimuli. Most previous research has focused on detection, classification and recognition of humans and their poses progressing onto actions, activities and events but it mostly lacks grounding in socially relevant contexts. Moreover, this research is largely driven by applications in security & surveillance or in search & retrieval. The time is ripe to ground these technologies in richer social contexts and milieus. This workshop is positioned to show case this rich domain of applications, which will provide the necessary next boost for these technologies. At the same time, it seeks to ground computational models of social behavior in the sociopsychological and neuroscientific theories of human action and behavior. This would allow us to leverage decades of research in these theoretically and empirically rich fields and to spur interdisciplinary research thereby opening up new problem domains for the vision community. Call For Papers

Organized by:

Ajay Divakaran (SRI International)
Maneesh Singh (SRI International)
Mohamed R. Amer (Oregon State University)
Behjat Siddiquie (SRI International)
Saad Khan (SRI International)

under: Workshops

We propose a novel staged hybrid model that exploits the strength of discriminative classifiers along with the representational power of generative models. Our focus is on detecting multimodal events in time varying data sequences. Discriminative classifiers have been shown to achieve higher performances than the corresponding generative likelihood-based classifiers. On the other hand, generative models learn a rich informative space which allows for data generation and joint feature representation that discriminative models lack. We employ a deep temporal generative model for unsupervised learning of a shared representation across multiple modalities with time varying data. The temporal generative model takes into account short term temporal phenomena and allows for filling in missing data by generating data within or across modalities. The hybrid model involves augmenting the temporal generative model with a Conditional Random Field based temporal discriminative model for event detection, classification, and generation, which enables modeling long range temporal dynamics. We evaluate our approach on multiple audio-visual datasets (AVEC, AVLetters, and CUAVE) and demonstrate its superiority compared to the state-of-the-art. Paper

under: Main Conference, Publications
This paper presents an efficient approach to video parsing. Our videos show a number of co-occurring individual and group activities. To address challenges of the domain, we use an expressive spatiotemporal AND-OR graph (ST-AOG) that jointly models activity parts, their spatiotemporal relations, and context, as well as enables multitarget tracking. The standard ST-AOG inference is prohibitively expensive in our setting, since it would require running a multitude of detectors, and tracking their detections in a long video footage. This problem is addressed by formulating a cost-sensitive inference of ST-AOG as Monte Carlo Tree Search (MCTS). For querying an activity in the video, MCTS optimally schedules a sequence of detectors and trackers to be run, and where they should be applied in the space-time volume. Evaluation on the benchmark datasets demonstrates that MCTS enables two-magnitude speed-ups without compromising accuracy relative to the standard cost-insensitive inference. Paper Poster Code
under: Main Conference, Publications

1st Workshop on Understanding Human Activities: Context and Interactions (ICCV2013)

Activity recognition is one of the core problems in computer vision. Recently it has attracted the attention of many researchers in the field. It is significant to many vision related applications such as surveillance, video search, human-computer interaction, and human-human, or social, interactions. Recent advances in feature representations, modeling, and inference techniques led to a significant progress in the field.

Motivated by the rich and complex temporal, spatial, and social structure of human activities, activity recognition today features several new challenges, including modeling group activities, complex temporal reasoning, activity hierarchies, human-object interactions and human-scene interactions. These new challenges aim to answer questions regarding the semantic understanding and high-level reasoning of image and video content. At this level, other classical problems in computer vision, like object detection and tracking, not only impact, but are often intertwined with activity recognition. This inherent complexity prompts more time and thought to be spent on developing solutions to tackle auxiliary problems to the human activity recognition problem. Call for papers

Organized by:

Sameh Khamis (University of Maryland)
Mohamed R. Amer (Oregon State University)
Wongun Choi (NEC-Labs)
Tian Lan (Stanford University)

under: Workshops

This paper addresses a new problem, that of multiscale activity recognition. Our goal is to detect and localize a wide range of activities, including individual actions and group activities, which may simultaneously co-occur in high resolution video. The video resolution allows for digital zoom-in (or zoom-out) for examining fine details (or coarser scales), as needed for recognition. The key challenge is how to avoid running a multitude of detectors at all spatiotemporal scales, and yet arrive at a holistically consistent video interpretation. To this end,we use a three-layered AND-OR graph to jointly model group activities, individual actions, and participating objects. The AND-OR graph allows a principled formulation of efficient, cost-sensitive inference via an explore-exploit strategy. Our inference optimally schedules the following computational processes: 1) direct application of activity detectors – called α process; 2) bottom-up inference based on detecting activity parts – called β process; and 3) top-down inference based on detecting activity context – called γ process. The scheduling iteratively maximizes the log-posteriors of the resulting parse graphs. For evaluation, we have compiled and benchmarked a new dataset of high-resolution videos of group and individual activities co-occurring in a courtyard of the UCLA campus. Paper Presentation Code Dataset

under: Main Conference, Publications

This paper addresses recognition of human activities with stochastic structure, characterized by variable space-time arrangements of primitive actions, and conducted by a variable number of actors. We demonstrate that modeling aggregate counts of visual words is surprisingly expressive enough for such a challenging recognition task. An activity is represented by a sum-product network (SPN). SPN is a mixture of bags-of-words (BoWs) with exponentially many mixture components, where sub components are reused by larger ones. SPN consists of terminal nodes representing BoWs, and product and sum nodes organized in a number of layers. The products are aimed at encoding particular configurations of primitive actions, and the sums serve to capture their alternative configurations. The connectivity of SPN and parameters of BoW distributions are learned under weak supervision using the EM algorithm. SPN inference amounts to parsing the SPN graph, which yields the most probable explanation (MPE) of the video in terms of activity detection and localization. SPN inference has linear complexity in the number of nodes, under fairly general conditions, enabling fast and scalable recognition. A new Volleyball dataset is compiled and annotated for evaluation.Our classification accuracy and localization precision and recall are superior to those of the state-of-the-art on the benchmark and our Volleyball datasets. Paper Poster Code Dataset

under: Main Conference, Publications

Older Posts »

Categories