arXiv subjects

Song-Chun Zhu

Publications and source records attributed to Song-Chun Zhu.

At least 235 records · Page 13Linked to original sources

arXiv2017

Synthesizing Dynamic Patterns by Spatial-Temporal Generative ConvNet

Video sequences contain rich dynamic patterns, such as dynamic texture patterns that exhibit stationarity in the temporal domain, and action patterns that are non-stationary in either spatial or temporal domain. We show that a spatial-temporal generative ConvNet can be used to model and synthesize dynamic patterns. The model defines a probability distribution on the video sequence, and the log probability is defined by a spatial-temporal ConvNet that consists of multiple layers of spatial-temporal filters to capture spatial-temporal patterns of different scales. The model can be learned from the training video sequences by an "analysis by synthesis" learning algorithm that iterates the following two steps. Step 1 synthesizes video sequences from the currently learned model. Step 2 then updates the model parameters based on the difference between the synthesized video sequences and the observed training sequences. We show that the learning algorithm can synthesize realistic dynamic patterns.

stat.ML↗

arXiv2017

Mining Object Parts from CNNs via Active Question-Answering

Given a convolutional neural network (CNN) that is pre-trained for object classification, this paper proposes to use active question-answering to semanticize neural patterns in conv-layers of the CNN and mine part concepts. For each part concept, we mine neural patterns in the pre-trained CNN, which are related to the target part, and use these patterns to construct an And-Or graph (AOG) to represent a four-layer semantic hierarchy of the part. As an interpretable model, the AOG associates different CNN units with different explicit object parts. We use an active human-computer communication to incrementally grow such an AOG on the pre-trained CNN as follows. We allow the computer to actively identify objects, whose neural patterns cannot be explained by the current AOG. Then, the computer asks human about the unexplained objects, and uses the answers to automatically discover certain CNN patterns corresponding to the missing knowledge. We incrementally grow the AOG to encode new knowledge discovered during the active-learning process. In experiments, our method exhibits high learning efficiency. Our method uses about 1/6-1/3 of the part annotations for training, but achieves similar or better part-localization performance than fast-RCNN methods.

cs.CV↗

arXiv2017

CERN: Confidence-Energy Recurrent Network for Group Activity Recognition

This work is about recognizing human activities occurring in videos at distinct semantic levels, including individual actions, interactions, and group activities. The recognition is realized using a two-level hierarchy of Long Short-Term Memory (LSTM) networks, forming a feed-forward deep architecture, which can be trained end-to-end. In comparison with existing architectures of LSTMs, we make two key contributions giving the name to our approach as Confidence-Energy Recurrent Network -- CERN. First, instead of using the common softmax layer for prediction, we specify a novel energy layer (EL) for estimating the energy of our predictions. Second, rather than finding the common minimum-energy class assignment, which may be numerically unstable under uncertainty, we specify that the EL additionally computes the p-values of the solutions, and in this way estimates the most confident energy minimum. The evaluation on the Collective Activity and Volleyball datasets demonstrates: (i) advantages of our two contributions relative to the common softmax and energy-minimization formulations and (ii) a superior performance relative to the state-of-the-art approaches.

cs.CV↗

arXiv2017

Growing Interpretable Part Graphs on ConvNets via Multi-Shot Learning

This paper proposes a learning strategy that extracts object-part concepts from a pre-trained convolutional neural network (CNN), in an attempt to 1) explore explicit semantics hidden in CNN units and 2) gradually grow a semantically interpretable graphical model on the pre-trained CNN for hierarchical object understanding. Given part annotations on very few (e.g., 3-12) objects, our method mines certain latent patterns from the pre-trained CNN and associates them with different semantic parts. We use a four-layer And-Or graph to organize the mined latent patterns, so as to clarify their internal semantic hierarchy. Our method is guided by a small number of part annotations, and it achieves superior performance (about 13%-107% improvement) in part center prediction on the PASCAL VOC and ImageNet datasets.

cs.CV↗

arXiv2017

Learning Social Affordance Grammar from Videos: Transferring Human Interactions to Human-Robot Interactions

In this paper, we present a general framework for learning social affordance grammar as a spatiotemporal AND-OR graph (ST-AOG) from RGB-D videos of human interactions, and transfer the grammar to humanoids to enable a real-time motion inference for human-robot interaction (HRI). Based on Gibbs sampling, our weakly supervised grammar learning can automatically construct a hierarchical representation of an interaction with long-term joint sub-tasks of both agents and short term atomic actions of individual agents. Based on a new RGB-D video dataset with rich instances of human interactions, our experiments of Baxter simulation, human evaluation, and real Baxter test demonstrate that the model learned from limited training data successfully generates human-like behaviors in unseen scenarios and outperforms both baselines.

cs.RO↗

arXiv2016

Alternating Back-Propagation for Generator Network

This paper proposes an alternating back-propagation algorithm for learning the generator network model. The model is a non-linear generalization of factor analysis. In this model, the mapping from the continuous latent factors to the observed signal is parametrized by a convolutional neural network. The alternating back-propagation algorithm iterates the following two steps: (1) Inferential back-propagation, which infers the latent factors by Langevin dynamics or gradient descent. (2) Learning back-propagation, which updates the parameters given the inferred latent factors by gradient descent. The gradient computations in both steps are powered by back-propagation, and they share most of their code in common. We show that the alternating back-propagation algorithm can learn realistic generator models of natural images, video sequences, and sounds. Moreover, it can also be used to learn from incomplete or indirect training data.

stat.ML↗

arXiv2016

Online Object Tracking, Learning and Parsing with And-Or Graphs

This paper presents a method, called AOGTracker, for simultaneously tracking, learning and parsing (TLP) of unknown objects in video sequences with a hierarchical and compositional And-Or graph (AOG) representation. %The AOG captures both structural and appearance variations of a target object in a principled way. The TLP method is formulated in the Bayesian framework with a spatial and a temporal dynamic programming (DP) algorithms inferring object bounding boxes on-the-fly. During online learning, the AOG is discriminatively learned using latent SVM to account for appearance (e.g., lighting and partial occlusion) and structural (e.g., different poses and viewpoints) variations of a tracked object, as well as distractors (e.g., similar objects) in background. Three key issues in online inference and learning are addressed: (i) maintaining purity of positive and negative examples collected online, (ii) controling model complexity in latent structure learning, and (iii) identifying critical moments to re-learn the structure of AOG based on its intrackability. The intrackability measures uncertainty of an AOG based on its score maps in a frame. In experiments, our AOGTracker is tested on two popular tracking benchmarks with the same parameter setting: the TB-100/50/CVPR2013 benchmarks, and the VOT benchmarks --- VOT 2013, 2014, 2015 and TIR2015 (thermal imagery tracking). In the former, our AOGTracker outperforms state-of-the-art tracking algorithms including two trackers based on deep convolutional network. In the latter, our AOGTracker outperforms all other trackers in VOT2013 and is comparable to the state-of-the-art methods in VOT2014, 2015 and TIR2015.

cs.CV↗

arXiv2016

Attribute And-Or Grammar for Joint Parsing of Human Attributes, Part and Pose

This paper presents an attribute and-or grammar (A-AOG) model for jointly inferring human body pose and human attributes in a parse graph with attributes augmented to nodes in the hierarchical representation. In contrast to other popular methods in the current literature that train separate classifiers for poses and individual attributes, our method explicitly represents the decomposition and articulation of body parts, and account for the correlations between poses and attributes. The A-AOG model is an amalgamation of three traditional grammar formulations: (i) Phrase structure grammar representing the hierarchical decomposition of the human body from whole to parts; (ii) Dependency grammar modeling the geometric articulation by a kinematic graph of the body pose; and (iii) Attribute grammar accounting for the compatibility relations between different parts in the hierarchy so that their appearances follow a consistent style. The parse graph outputs human detection, pose estimation, and attribute prediction simultaneously, which are intuitive and interpretable. We conduct experiments on two tasks on two datasets, and experimental results demonstrate the advantage of joint modeling in comparison with computing poses and attributes independently. Furthermore, our model obtains better performance over existing methods for both pose estimation and attribute prediction tasks.

cs.CV↗

arXiv2016

Modeling and Inferring Human Intents and Latent Functional Objects for Trajectory Prediction

This paper is about detecting functional objects and inferring human intentions in surveillance videos of public spaces. People in the videos are expected to intentionally take shortest paths toward functional objects subject to obstacles, where people can satisfy certain needs (e.g., a vending machine can quench thirst), by following one of three possible intent behaviors: reach a single functional object and stop, or sequentially visit several functional objects, or initially start moving toward one goal but then change the intent to move toward another. Since detecting functional objects in low-resolution surveillance videos is typically unreliable, we call them "dark matter" characterized by the functionality to attract people. We formulate the Agent-based Lagrangian Mechanics wherein human trajectories are probabilistically modeled as motions of agents in many layers of "dark-energy" fields, where each agent can select a particular force field to affect its motions, and thus define the minimum-energy Dijkstra path toward the corresponding source "dark matter". For evaluation, we compiled and annotated a new dataset. The results demonstrate our effectiveness in predicting human intent behaviors and trajectories, and localizing functional objects, as well as discovering distinct functional classes of objects by clustering human motion behavior in the vicinity of functional objects.

cs.CV↗

arXiv2016

A Theory of Generative ConvNet

We show that a generative random field model, which we call generative ConvNet, can be derived from the commonly used discriminative ConvNet, by assuming a ConvNet for multi-category classification and assuming one of the categories is a base category generated by a reference distribution. If we further assume that the non-linearity in the ConvNet is Rectified Linear Unit (ReLU) and the reference distribution is Gaussian white noise, then we obtain a generative ConvNet model that is unique among energy-based models: The model is piecewise Gaussian, and the means of the Gaussian pieces are defined by an auto-encoder, where the filters in the bottom-up encoding become the basis functions in the top-down decoding, and the binary activation variables detected by the filters in the bottom-up convolution process become the coefficients of the basis functions in the top-down deconvolution process. The Langevin dynamics for sampling the generative ConvNet is driven by the reconstruction error of this auto-encoder. The contrastive divergence learning of the generative ConvNet reconstructs the training images by the auto-encoder. The maximum likelihood learning algorithm can synthesize realistic natural image patterns.

stat.ML↗

arXiv2016

Learning Social Affordance for Human-Robot Interaction

In this paper, we present an approach for robot learning of social affordance from human activity videos. We consider the problem in the context of human-robot interaction: Our approach learns structural representations of human-human (and human-object-human) interactions, describing how body-parts of each agent move with respect to each other and what spatial relations they should maintain to complete each sub-event (i.e., sub-goal). This enables the robot to infer its own movement in reaction to the human body motion, allowing it to naturally replicate such interactions. We introduce the representation of social affordance and propose a generative model for its weakly supervised learning from human demonstration videos. Our approach discovers critical steps (i.e., latent sub-events) in an interaction and the typical motion associated with them, learning what body-parts should be involved and how. The experimental results demonstrate that our Markov Chain Monte Carlo (MCMC) based learning algorithm automatically discovers semantically meaningful interactive affordance from RGB-D videos, which allows us to generate appropriate full body motion for an agent.

cs.RO↗

arXiv2016

Recognizing Car Fluents from Video

Physical fluents, a term originally used by Newton [40], refers to time-varying object states in dynamic scenes. In this paper, we are interested in inferring the fluents of vehicles from video. For example, a door (hood, trunk) is open or closed through various actions, light is blinking to turn. Recognizing these fluents has broad applications, yet have received scant attention in the computer vision literature. Car fluent recognition entails a unified framework for car detection, car part localization and part status recognition, which is made difficult by large structural and appearance variations, low resolutions and occlusions. This paper learns a spatial-temporal And-Or hierarchical model to represent car fluents. The learning of this model is formulated under the latent structural SVM framework. Since there are no publicly related dataset, we collect and annotate a car fluent dataset consisting of car videos with diverse fluents. In experiments, the proposed method outperforms several highly related baseline methods in terms of car fluent recognition and car part localization.

cs.CV↗

arXiv2015

A Restricted Visual Turing Test for Deep Scene and Event Understanding

This paper presents a restricted visual Turing test (VTT) for story-line based deep understanding in long-term and multi-camera captured videos. Given a set of videos of a scene (such as a multi-room office, a garden, and a parking lot.) and a sequence of story-line based queries, the task is to provide answers either simply in binary form "true/false" (to a polar query) or in an accurate natural language description (to a non-polar query). Queries, polar or non-polar, consist of view-based queries which can be answered from a particular camera view and scene-centered queries which involves joint inference across different cameras. The story lines are collected to cover spatial, temporal and causal understanding of input videos. The data and queries distinguish our VTT from recently proposed visual question answering in images and video captioning. A vision system is proposed to perform joint video and query parsing which integrates different vision modules, a knowledge base and a query engine. The system provides unified interfaces for different modules so that individual modules can be reconfigured to test a new method. We provide a benchmark dataset and a toolkit for ontology guided story-line query generation which consists of about 93.5 hours videos captured in four different locations and 3,426 queries split into 127 story lines. We also provide a baseline implementation and result analyses.

cs.CV↗

arXiv2015

Joint Image-Text News Topic Detection and Tracking with And-Or Graph Representation

In this paper, we aim to develop a method for automatically detecting and tracking topics in broadcast news. We present a hierarchical And-Or graph (AOG) to jointly represent the latent structure of both texts and visuals. The AOG embeds a context sensitive grammar that can describe the hierarchical composition of news topics by semantic elements about people involved, related places and what happened, and model contextual relationships between elements in the hierarchy. We detect news topics through a cluster sampling process which groups stories about closely related events. Swendsen-Wang Cuts (SWC), an effective cluster sampling algorithm, is adopted for traversing the solution space and obtaining optimal clustering solutions by maximizing a Bayesian posterior probability. Topics are tracked to deal with the continuously updated news streams. We generate topic trajectories to show how topics emerge, evolve and disappear over time. The experimental results show that our method can explicitly describe the textual and visual data in news videos and produce meaningful topic trajectories. Our method achieves superior performance compared to state-of-the-art methods on both a public dataset Reuters-21578 and a self-collected dataset named UCLA Broadcast News Dataset.

cs.IR↗

arXiv2015

Learning FRAME Models Using CNN Filters

The convolutional neural network (ConvNet or CNN) has proven to be very successful in many tasks such as those in computer vision. In this conceptual paper, we study the generative perspective of the discriminative CNN. In particular, we propose to learn the generative FRAME (Filters, Random field, And Maximum Entropy) model using the highly expressive filters pre-learned by the CNN at the convolutional layers. We show that the learning algorithm can generate realistic and rich object and texture patterns in natural scenes. We explain that each learned model corresponds to a new CNN unit at a layer above the layer of filters employed by the model. We further show that it is possible to learn a new layer of CNN units using a generative CNN model, which is a product of experts model, and the learning algorithm admits an EM interpretation with binary latent variables.

cs.CV↗

arXiv2015

Learning And-Or Models to Represent Context and Occlusion for Car Detection and Viewpoint Estimation

This paper presents a method for learning And-Or models to represent context and occlusion for car detection and viewpoint estimation. The learned And-Or model represents car-to-car context and occlusion configurations at three levels: (i) spatially-aligned cars, (ii) single car under different occlusion configurations, and (iii) a small number of parts. The And-Or model embeds a grammar for representing large structural and appearance variations in a reconfigurable hierarchy. The learning process consists of two stages in a weakly supervised way (i.e., only bounding boxes of single cars are annotated). Firstly, the structure of the And-Or model is learned with three components: (a) mining multi-car contextual patterns based on layouts of annotated single car bounding boxes, (b) mining occlusion configurations between single cars, and (c) learning different combinations of part visibility based on car 3D CAD simulation. The And-Or model is organized in a directed and acyclic graph which can be inferred by Dynamic Programming. Secondly, the model parameters (for appearance, deformation and bias) are jointly trained using Weak-Label Structural SVM. In experiments, we test our model on four car detection datasets --- the KITTI dataset \cite{Geiger12}, the PASCAL VOC2007 car dataset~\cite{pascal}, and two self-collected car datasets, namely the Street-Parking car dataset and the Parking-Lot car dataset, and three datasets for car viewpoint estimation --- the PASCAL VOC2006 car dataset~\cite{pascal}, the 3D car dataset~\cite{savarese}, and the PASCAL3D+ car dataset~\cite{xiang_wacv14}. Compared with state-of-the-art variants of deformable part-based models and other methods, our model achieves significant improvement consistently on the four detection datasets, and comparable performance on car viewpoint estimation.

cs.CV↗

arXiv2015

Joint Inference of Groups, Events and Human Roles in Aerial Videos

With the advent of drones, aerial video analysis becomes increasingly important; yet, it has received scant attention in the literature. This paper addresses a new problem of parsing low-resolution aerial videos of large spatial areas, in terms of 1) grouping, 2) recognizing events and 3) assigning roles to people engaged in events. We propose a novel framework aimed at conducting joint inference of the above tasks, as reasoning about each in isolation typically fails in our setting. Given noisy tracklets of people and detections of large objects and scene surfaces (e.g., building, grass), we use a spatiotemporal AND-OR graph to drive our joint inference, using Markov Chain Monte Carlo and dynamic programming. We also introduce a new formalism of spatiotemporal templates characterizing latent sub-events. For evaluation, we have collected and released a new aerial videos dataset using a hex-rotor flying over picnic areas rich with group events. Our results demonstrate that we successfully address above inference tasks under challenging conditions.

cs.CV↗

arXiv2015

Video Primal Sketch: A Unified Middle-Level Representation for Video

This paper presents a middle-level video representation named Video Primal Sketch (VPS), which integrates two regimes of models: i) sparse coding model using static or moving primitives to explicitly represent moving corners, lines, feature points, etc., ii) FRAME /MRF model reproducing feature statistics extracted from input video to implicitly represent textured motion, such as water and fire. The feature statistics include histograms of spatio-temporal filters and velocity distributions. This paper makes three contributions to the literature: i) Learning a dictionary of video primitives using parametric generative models; ii) Proposing the Spatio-Temporal FRAME (ST-FRAME) and Motion-Appearance FRAME (MA-FRAME) models for modeling and synthesizing textured motion; and iii) Developing a parsimonious hybrid model for generic video representation. Given an input video, VPS selects the proper models automatically for different motion patterns and is compatible with high-level action representations. In the experiments, we synthesize a number of textured motion; reconstruct real videos using the VPS; report a series of human perception experiments to verify the quality of reconstructed videos; demonstrate how the VPS changes over the scale transition in videos; and present the close connection between VPS and high-level action models.

cs.CV↗