Human actions in video sequences are characterized by the complex interplay between spatial features and their temporal dynamics. In this paper, we propose novel tensor representations for compactly capturing such higher-order relationships between visual features for the task of action recognition. We propose two tensor-based feature representations, viz. (i) sequence compatibility kernel (SCK) and (ii) dynamics compatibility kernel (DCK); the former building on the spatio-temporal correlations between features, while the latter explicitly modeling the action dynamics of a sequence. We also explore generalization of SCK, coined SCK(+), that operates on subsequences to capture the local-global interplay of correlations, which can incorporate multi-modal inputs e.g., skeleton 3D body-joints and per-frame classifier scores obtained from deep learning models trained on videos. We introduce linearization of these kernels that lead to compact and fast descriptors. We provide experiments on (i) 3D skeleton action sequences, (ii) fine-grained video sequences, and (iii) standard non-fine-grained videos. As our final representations are tensors that capture higher-order relationships of features, they relate to co-occurrences for robust fine-grained recognition. We use higher-order tensors and so-called Eigenvalue Power Normalization (EPN) which have been long speculated to perform spectral detection of higher-order occurrences, thus detecting fine-grained relationships of features rather than merely count features in action sequences. We prove that a tensor of order r, built from Z* dimensional features, coupled with EPN indeed detects if at least one higher-order occurrence is `projected' into one of its binom(Z*,r) subspaces of dim. r represented by the tensor, thus forming a Tensor Power Normalization metric endowed with binom(Z*,r) such `detectors'.
In this paper, we investigate in the context of deep neural networks, the performance of several discretization algorithms for two first-order finite-time optimization flows. These flows are, namely, the rescaled-gradient flow (RGF) and the signed-gradient flow (SGF), and consist of non-Lipscthiz or discontinuous dynamical systems that converge locally in finite time to the minima of gradient-dominated functions. We introduce three discretization methods for these first-order finite-time flows, and provide convergence guarantees. We then apply the proposed algorithms in training neural networks and empirically test their performances on three standard datasets, namely, CIFAR10, SVHN, and MNIST. Our results show that our schemes demonstrate faster convergences against standard optimization alternatives, while achieving equivalent or better accuracy.
Learning associations across modalities is critical for robust multimodal reasoning, especially when a modality may be missing during inference. In this paper, we study this problem in the context of audio-conditioned visual synthesis -- a task that is important, for example, in occlusion reasoning. Specifically, our goal is to generate future video frames and their motion dynamics conditioned on audio and a few past frames. To tackle this problem, we present Sound2Sight, a deep variational framework, that is trained to learn a per frame stochastic prior conditioned on a joint embedding of audio and past frames. This embedding is learned via a multi-head attention-based audio-visual transformer encoder. The learned prior is then sampled to further condition a video forecasting module to generate future frames. The stochastic prior allows the model to sample multiple plausible futures that are consistent with the provided audio and the past context. Moreover, to improve the quality and coherence of the generated frames, we propose a multimodal discriminator that differentiates between a synthesized and a real audio-visual clip. We empirically evaluate our approach, vis-\'a-vis closely-related prior methods, on two new datasets viz. (i) Multimodal Stochastic Moving MNIST with a Surprise Obstacle, (ii) Youtube Paintings; as well as on the existing Audio-Set Drums dataset. Our extensive experiments demonstrate that Sound2Sight significantly outperforms the state of the art in the generated video quality, while also producing diverse video content.
In this paper, we study the problem of learning compact (low-dimensional) representations for sequential data that captures its implicit spatio-temporal cues. To maximize extraction of such informative cues from the data, we set the problem within the context of contrastive representation learning and to that end propose a novel objective via optimal transport. Specifically, our formulation seeks a low-dimensional subspace representation of the data that jointly (i) maximizes the distance of the data (embedded in this subspace) from an adversarial data distribution under the optimal transport, a.k.a. the Wasserstein distance, (ii) captures the temporal order, and (iii) minimizes the data distortion. To generate the adversarial distribution, we propose a novel framework connecting Wasserstein GANs with a classifier, allowing a principled mechanism for producing good negative distributions for contrastive learning, which is currently a challenging problem. Our full objective is cast as a subspace learning problem on the Grassmann manifold and solved via Riemannian optimization. To empirically study our formulation, we provide experiments on the task of human action recognition in video sequences. Our results demonstrate competitive performance against challenging baselines.
The Audio-Visual Scene-aware Dialog (AVSD) task requires an agent to indulge in a natural conversation with a human about a given video. Specifically, apart from the video frames, the agent receives the audio, brief captions, and a dialog history, and the task is to produce the correct answer to a question about the video. Due to the diversity in the type of inputs, this task poses a very challenging multimodal reasoning problem. Current approaches to AVSD either use global video-level features or those from a few sampled frames, and thus lack the ability to explicitly capture relevant visual regions or their interactions for answer generation. To this end, we propose a novel spatio-temporal scene graph representation (STSGR) modeling fine-grained information flows within videos. Specifically, on an input video sequence, STSGR (i) creates a two-stream visual and semantic scene graph on every frame, (ii) conducts intra-graph reasoning using node and edge convolutions generating visual memories, and (iii) applies inter-graph aggregation to capture their temporal evolutions. These visual memories are then combined with other modalities and the question embeddings using a novel semantics-controlled multi-head shuffled transformer, which then produces the answer recursively. Our entire pipeline is trained end-to-end. We present experiments on the AVSD dataset and demonstrate state-of-the-art results. A human evaluation on the quality of our generated answers shows 12% relative improvement against prior methods.
Non-Rigid Structure-from-Motion (NRSfM) problem aims to recover 3D geometry of a deforming object from its 2D feature correspondences across multiple frames. Classical approaches to this problem assume a small number of feature points and, ignore the local non-linearities of the shape deformation, and therefore, struggles to reliably model non-linear deformations. Furthermore, available dense NRSfM algorithms are often hurdled by scalability, computations, noisy measurements and, restricted to model just global deformation. In this paper, we propose algorithms that can overcome these limitations with the previous methods and, at the same time, can recover a reliable dense 3D structure of a non-rigid object with higher accuracy. Assuming that a deforming shape is composed of a union of local linear subspace and, span a global low-rank space over multiple frames enables us to efficiently model complex non-rigid deformations. To that end, each local linear subspace is represented using Grassmannians and, the global 3D shape across multiple frames is represented using a low-rank representation. We show that our approach significantly improves accuracy, scalability, and robustness against noise. Also, our representation naturally allows for simultaneous reconstruction and clustering framework which in general is observed to be more suitable for NRSfM problems. Our method currently achieves leading performance on the standard benchmark datasets.
This paper presents a framework to recognize temporal compositions of atomic actions in videos. Specifically, we propose to express temporal compositions of actions as semantic regular expressions and derive an inference framework using probabilistic automata to recognize complex actions as satisfying these expressions on the input video features. Our approach is different from existing works that either predict long-range complex activities as unordered sets of atomic actions, or retrieve videos using natural language sentences. Instead, the proposed approach allows recognizing complex fine-grained activities using only pretrained action classifiers, without requiring any additional data, annotations or neural network training. To evaluate the potential of our approach, we provide experiments on synthetic datasets and challenging real action recognition datasets, such as MultiTHUMOS and Charades. We conclude that the proposed approach can extend state-of-the-art primitive action classifiers to vastly more complex activities without large performance degradation.
Modern face alignment methods have become quite accurate at predicting the locations of facial landmarks, but they do not typically estimate the uncertainty of their predicted locations nor predict whether landmarks are visible. In this paper, we present a novel framework for jointly predicting landmark locations, associated uncertainties of these predicted locations, and landmark visibilities. We model these as mixed random variables and estimate them using a deep network trained with our proposed Location, Uncertainty, and Visibility Likelihood (LUVLi) loss. In addition, we release an entirely new labeling of a large face alignment dataset with over 19,000 face images in a full range of head poses. Each face is manually labeled with the ground-truth locations of 68 landmarks, with the additional information of whether each landmark is unoccluded, self-occluded (due to extreme head poses), or externally occluded. Not only does our joint estimation yield accurate estimates of the uncertainty of predicted landmark locations, but it also yields state-of-the-art estimates for the landmark locations themselves on multiple standard face alignment datasets. Our method's estimates of the uncertainty of predicted landmark locations could be used to automatically identify input images on which face alignment fails, which can be critical for downstream tasks.
Generating video descriptions automatically is a challenging task that involves a complex interplay between spatio-temporal visual features and language models. Given that videos consist of spatial (frame-level) features and their temporal evolutions, an effective captioning model should be able to attend to these different cues selectively. To this end, we propose a Spatio-Temporal and Temporo-Spatial (STaTS) attention model which, conditioned on the language state, hierarchically combines spatial and temporal attention to videos in two different orders: (i) a spatio-temporal (ST) sub-model, which first attends to regions that have temporal evolution, then temporally pools the features from these regions; and (ii) a temporo-spatial (TS) sub-model, which first decides a single frame to attend to, then applies spatial attention within that frame. We propose a novel LSTM-based temporal ranking function, which we call ranked attention, for the ST model to capture action dynamics. Our entire framework is trained end-to-end. We provide experiments on two benchmark datasets: MSVD and MSR-VTT. Our results demonstrate the synergy between the ST and TS modules, outperforming recent state-of-the-art methods.