Multi-modal learning, particularly among imaging and linguistic modalities, has made amazing strides in many high-level fundamental visual understanding problems, ranging from language grounding to dense event captioning. However, much of the research has been limited to approaches that either do not take audio corresponding to video into account at all, or those that model the audio-visual correlations in service of sound or sound source localization. In this paper, we present the evidence, that audio signals can carry surprising amount of information when it comes to high-level visual-lingual tasks. Specifically, we focus on the problem of weakly-supervised dense event captioning in videos and show that audio on its own can nearly rival performance of a state-of-the-art visual model and, combined with video, can improve on the state-of-the-art performance. Extensive experiments on the ActivityNet Captions dataset show that our proposed multi-modal approach outperforms state-of-the-art unimodal methods, as well as validate specific feature representation and architecture design choices.
Generation of realistic high-resolution videos of human subjects is a challenging and important task in computer vision. In this paper, we focus on human motion transfer - generation of a video depicting a particular subject, observed in a single image, performing a series of motions exemplified by an auxiliary (driving) video. Our GAN-based architecture, DwNet, leverages dense intermediate pose-guided representation and refinement process to warp the required subject appearance, in the form of the texture, from a source image into a desired pose. Temporal consistency is maintained by further conditioning the decoding process within a GAN on the previously generated frame. In this way a video is generated in an iterative and recurrent fashion. We illustrate the efficacy of our approach by showing state-of-the-art quantitative and qualitative performance on two benchmark datasets: TaiChi and Fashion Modeling. The latter is collected by us and will be made publicly available to the community.
Recently there is an increasing interest in scene generation within the research community. However, models used for generating scene layouts from textual description largely ignore plausible visual variations within the structure dictated by the text. We propose LayoutVAE, a variational autoencoder based framework for generating stochastic scene layouts. LayoutVAE is a versatile modeling framework that allows for generating full image layouts given a label set, or per label layouts for an existing image given a new label. In addition, it is also capable of detecting unusual layouts, potentially providing a way to evaluate layout generation problem. Extensive experiments on MNIST-Layouts and challenging COCO 2017 Panoptic dataset verifies the effectiveness of our proposed framework.
Recently there is an increasing interest in scene generation within the research community. However, scene layouts are largely being modeled in deterministic fashion, ignoring any plausible visual variations given the same textual description as input. We propose LayoutVAE, a variational autoencoder based framework for generating stochastic scene layouts. LayoutVAE is a versatile modeling framework that allows for generating full image layouts given a label set, or per label layouts for an existing image given a new label. In addition, it is also capable of detecting unusual layouts, potentially providing a way to evaluate layout generation problem. Extensive experiments on MNIST-Layouts and challenging COCO 2017 Panoptic dataset verifies the effectiveness of our proposed framework.
Visual attention mechanisms have proven to be integrally important constituent components of many modern deep neural architectures. They provide an efficient and effective way to utilize visual information selectively, which has shown to be especially valuable in multi-modal learning tasks. However, all prior attention frameworks lack the ability to explicitly model structural dependencies among attention variables, making it difficult to predict consistent attention masks. In this paper we develop a novel structured spatial attention mechanism which is end-to-end trainable and can be integrated with any feed-forward convolutional neural network. This proposed AttentionRNN layer explicitly enforces structure over the spatial attention variables by sequentially predicting attention values in the spatial mask in a bi-directional raster-scan and inverse raster-scan order. As a result, each attention value depends not only on local image or contextual information, but also on the previously predicted attention values. Our experiments show consistent quantitative and qualitative improvements on a variety of recognition tasks and datasets; including image categorization, question answering and image generation.
We propose a novel probabilistic generative model for action sequences. The model is termed the Action Point Process VAE (APP-VAE), a variational auto-encoder that can capture the distribution over the times and categories of action sequences. Modeling the variety of possible action sequences is a challenge, which we show can be addressed via the APP-VAE's use of latent representations and non-linear functions to parameterize distributions over which event is likely to occur next in a sequence and at what time. We empirically validate the efficacy of APP-VAE for modeling action sequences on the MultiTHUMOS and Breakfast datasets.
We propose an end-to-end approach for phrase grounding in images. Unlike prior methods that typically attempt to ground each phrase independently by building an image-text embedding, our architecture formulates grounding of multiple phrases as a sequential and contextual process. Specifically, we encode region proposals and all phrases into two stacks of LSTM cells, along with so-far grounded phrase-region pairs. These LSTM stacks collectively capture context for grounding of the next phrase. The resulting architecture, which we call SeqGROUND, supports many-to-many matching by allowing an image region to be matched to multiple phrases and vice versa. We show competitive performance on the Flickr30K benchmark dataset and, through ablation studies, validate the efficacy of sequential grounding as well as individual design choices in our model architecture.
We propose a generative approach to physics-based motion capture. Unlike prior attempts to incorporate physics into tracking that assume the subject and scene geometry are calibrated and known a priori, our approach is automatic and online. This distinction is important since calibration of the environment is often difficult, especially for motions with props, uneven surfaces, or outdoor scenes. The use of physics in this context provides a natural framework to reason about contact and the plausibility of recovered motions. We propose a fast data-driven parametric body model, based on linear-blend skinning, which decouples deformations due to pose, anthropometrics and body shape. Pose (and shape) parameters are estimated using robust ICP optimization with physics-based dynamic priors that incorporate contact. Contact is estimated from torque trajectories and predictions of which contact points were active. To our knowledge, this is the first approach to take physics into account without explicit {\em a priori} knowledge of the environment or body dimensions. We demonstrate effective tracking from a noisy single depth camera, improving on state-of-the-art results quantitatively and producing better qualitative results, reducing visual artifacts like foot-skate and jitter.
Image retrieval is one of the most popular tasks in computer vision. However, the proposed approaches in the literature can be roughly categorized into two groups: category- and instance-based retrieval. In this work, we show that the retrieval task is much richer and more complex, and can be viewed as a continuous spectrum spanning the space among these operational points. Hence, we propose to tackle a novel retrieval task where we want to smoothly traverse the simplex from category- to instance- and attribute-based retrieval. We propose a novel deep network architecture that learns to decompose an input query image into its basic components of categorical and attribute information. Moreover, using a continuous control parameter, our model learns to reconstruct a new embedding of the query by mixing these two signals, with different proportions, to target a specific point along the retrieval simplex. We demonstrate our idea in a detailed evaluation of the proposed model and highlight the advantages of our approach against a set of well-established retrieval model baselines.