Image captioning is a challenging task that combines the field of computer vision and natural language processing. A variety of approaches have been proposed to achieve the goal of automatically describing an image, and recurrent neural network (RNN) or long-short term memory (LSTM) based models dominate this field. However, RNNs or LSTMs cannot be calculated in parallel and ignore the underlying hierarchical structure of a sentence. In this paper, we propose a framework that only employs convolutional neural networks (CNNs) to generate captions. Owing to parallel computing, our basic model is around 3 times faster than NIC (an LSTM-based model) during training time, while also providing better results. We conduct extensive experiments on MSCOCO and investigate the influence of the model width and depth. Compared with LSTM-based models that apply similar attention mechanisms, our proposed models achieves comparable scores of BLEU-1,2,3,4 and METEOR, and higher scores of CIDEr. We also test our model on the paragraph annotation dataset, and get higher CIDEr score compared with hierarchical LSTMs
Recently using convolutional neural networks (CNNs) has gained popularity in visual tracking, due to its robust feature representation of images. Recent methods perform online tracking by fine-tuning a pre-trained CNN model to the specific target object using stochastic gradient descent (SGD) back-propagation, which is usually time-consuming. In this paper, we propose a recurrent filter generation methods for visual tracking. We directly feed the target's image patch to a recurrent neural network (RNN) to estimate an object-specific filter for tracking. As the video sequence is a spatiotemporal data, we extend the matrix multiplications of the fully-connected layers of the RNN to a convolution operation on feature maps, which preserves the target's spatial structure and also is memory-efficient. The tracked object in the subsequent frames will be fed into the RNN to adapt the generated filters to appearance variations of the target. Note that once the off-line training process of our network is finished, there is no need to fine-tune the network for specific objects, which makes our approach more efficient than methods that use iterative fine-tuning to online learn the target. Extensive experiments conducted on widely used benchmarks, OTB and VOT, demonstrate encouraging results compared to other recent methods.
Color theme or color palette can deeply influence the quality and the feeling of a photograph or a graphical design. Although color palettes may come from different sources such as online crowd-sourcing, photographs and graphical designs, in this paper, we consider color palettes extracted from fine art collections, which we believe to be an abundant source of stylistic and unique color themes. We aim to capture color styles embedded in these collections by means of statistical models and to build practical applications upon these models. As artists often use their personal color themes in their paintings, making these palettes appear frequently in the dataset, we employed density estimation to capture the characteristics of palette data. Via density estimation, we carried out various predictions and interpolations on palettes, which led to promising applications such as photo-style exploration, real-time color suggestion, and enriched photo recolorization. It was, however, challenging to apply density estimation to palette data as palettes often come as unordered sets of colors, which make it difficult to use conventional metrics on them. To this end, we developed a divide-and-conquer sorting algorithm to rearrange the colors in the palettes in a coherent order, which allows meaningful interpolation between color palettes. To confirm the performance of our model, we also conducted quantitative experiments on datasets of digitized paintings collected from the Internet and received favorable results.
Computer vision tasks often have side information available that is helpful to solve the task. For example, for crowd counting, the camera perspective (e.g., camera angle and height) gives a clue about the appearance and scale of people in the scene. While side information has been shown to be useful for counting systems using traditional hand-crafted features, it has not been fully utilized in counting systems based on deep learning. In order to incorporate the available side information, we propose an adaptive convolutional neural network (ACNN), where the convolutional filter weights adapt to the current scene context via the side information. In particular, we model the filter weights as a low-dimensional manifold, parametrized by the side information, within the high-dimensional space of filter weights. With the help of side information and adaptive weights, the ACNN can disentangle the variations related to the side information, and extract discriminative features related to the current context. Since existing crowd counting datasets do not contain ground-truth side information, we collect a new dataset with the ground-truth camera angle and height as the side information. On experiments in crowd counting, the ACNN improves counting accuracy compared to a plain CNN with a similar number of parameters. We also apply ACNN to image deconvolution to show its potential effectiveness on other computer vision applications.
This paper focuses on structured-output learning using deep neural networks for 3D human pose estimation from monocular images. Our network takes an image and 3D pose as inputs and outputs a score value, which is high when the image-pose pair matches and low otherwise. The network structure consists of a convolutional neural network for image feature extraction, followed by two sub-networks for transforming the image features and pose into a joint embedding. The score function is then the dot-product between the image and pose embeddings. The image-pose embedding and score function are jointly trained using a maximum-margin cost function. Our proposed framework can be interpreted as a special form of structured support vector machines where the joint feature space is discriminatively learned using deep neural networks. We test our framework on the Human3.6m dataset and obtain state-of-the-art results compared to other recent methods. Finally, we present visualizations of the image-pose embedding space, demonstrating the network has learned a high-level embedding of body-orientation and pose-configuration.
We propose an heterogeneous multi-task learning framework for human pose estimation from monocular image with deep convolutional neural network. In particular, we simultaneously learn a pose-joint regressor and a sliding-window body-part detector in a deep network architecture. We show that including the body-part detection task helps to regularize the network, directing it to converge to a good solution. We report competitive and state-of-art results on several data sets. We also empirically show that the learned neurons in the middle layer of our network are tuned to localized body parts.
We present a multiple-person tracking algorithm, based on combining particle filters and RVO, an agent-based crowd model that infers collision-free velocities so as to predict pedestrian's motion. In addition to position and velocity, our tracking algorithm can estimate the internal goals (desired destination or desired velocity) of the tracked pedestrian in an online manner, thus removing the need to specify this information beforehand. Furthermore, we leverage the longer-term predictions of RVO by deriving a higher-order particle filter, which aggregates multiple predictions from different prior time steps. This yields a tracker that can recover from short-term occlusions and spurious noise in the appearance model. Experimental results show that our tracking algorithm is suitable for predicting pedestrians' behaviors online without needing scene priors or hand-annotated goal information, and improves tracking in real-world crowded scenes under low frame rates.
A generalized Gaussian process model (GGPM) is a unifying framework that encompasses many existing Gaussian process (GP) models, such as GP regression, classification, and counting. In the GGPM framework, the observation likelihood of the GP model is itself parameterized using the exponential family distribution (EFD). In this paper, we consider efficient algorithms for approximate inference on GGPMs using the general form of the EFD. A particular GP model and its associated inference algorithms can then be formed by changing the parameters of the EFD, thus greatly simplifying its creation for task-specific output domains. We demonstrate the efficacy of this framework by creating several new GP models for regressing to non-negative reals and to real intervals. We also consider a closed-form Taylor approximation for efficient inference on GGPMs, and elaborate on its connections with other model-specific heuristic closed-form approximations. Finally, we present a comprehensive set of experiments to compare approximate inference algorithms on a wide variety of GGPMs.
We propose a family of multivariate Gaussian process models for correlated outputs, based on assuming that the likelihood function takes the generic form of the multivariate exponential family distribution (EFD). We denote this model as a multivariate generalized Gaussian process model, and derive Taylor and Laplace algorithms for approximate inference on the generic model. By instantiating the EFD with specific parameter functions, we obtain two novel GP models (and corresponding inference algorithms) for correlated outputs: 1) a Von-Mises GP for angle regression; and 2) a Dirichlet GP for regressing on the multinomial simplex.
The hidden Markov model (HMM) is a widely-used generative model that copes with sequential data, assuming that each observation is conditioned on the state of a hidden Markov chain. In this paper, we derive a novel algorithm to cluster HMMs based on the hierarchical EM (HEM) algorithm. The proposed algorithm i) clusters a given collection of HMMs into groups of HMMs that are similar, in terms of the distributions they represent, and ii) characterizes each group by a "cluster center", i.e., a novel HMM that is representative for the group, in a manner that is consistent with the underlying generative model of the HMM. To cope with intractable inference in the E-step, the HEM algorithm is formulated as a variational optimization problem, and efficiently solved for the HMM case by leveraging an appropriate variational approximation. The benefits of the proposed algorithm, which we call variational HEM (VHEM), are demonstrated on several tasks involving time-series data, such as hierarchical clustering of motion capture sequences, and automatic annotation and retrieval of music and of online hand-writing data, showing improvements over current methods. In particular, our variational HEM algorithm effectively leverages large amounts of data when learning annotation models by using an efficient hierarchical estimation procedure, which reduces learning times and memory requirements, while improving model robustness through better regularization.