Captioning has attracted much attention in image and video understanding while a small amount of work examines audio captioning. This paper contributes a Mandarin-annotated dataset for audio captioning within a car scene. A sentence-level loss is proposed to be used in tandem with a GRU encoder-decoder model to generate captions with higher semantic similarity to human annotations. We evaluate the model on the newly-proposed Car dataset, a previously published Mandarin Hospital dataset and the Joint dataset, indicating its generalization capability across different scenes. An improvement in all metrics can be observed, including classical natural language generation (NLG) metrics, sentence richness and human evaluation ratings. However, though detailed audio captions can now be automatically generated, human annotations still outperform model captions on many aspects.
Learning to represent videos is a very challenging task both algorithmically and computationally. Standard video CNN architectures have been designed by directly extending architectures devised for image understanding to include the time dimension, using modules such as 3D convolutions, or by using two-stream design to capture both appearance and motion in videos. We interpret a video CNN as a collection of multi-stream convolutional blocks connected to each other, and propose the approach of automatically finding neural architectures with better connectivity and spatio-temporal interactions for video understanding. This is done by evolving a population of overly-connected architectures guided by connection weight learning. Architectures combining representations that abstract different input types (i.e., RGB and optical flow) at multiple temporal resolutions are searched for, allowing different types or sources of information to interact with each other. Our method, referred to as AssembleNet, outperforms prior approaches on public video datasets, in some cases by a great margin. We obtain 58.6% mAP on Charades and 34.27% accuracy on Moments-in-Time.
In this dissertation, I present my work towards exploring temporal information for better video understanding. Specifically, I have worked on two problems: action recognition and semantic segmentation. For action recognition, I have proposed a framework, termed hidden two-stream networks, to learn an optimal motion representation that does not require the computation of optical flow. My framework alleviates several challenges faced in video classification, such as learning motion representations, real-time inference, multi-framerate handling, generalizability to unseen actions, etc. For semantic segmentation, I have introduced a general framework that uses video prediction models to synthesize new training samples. By scaling up the training dataset, my trained models are more accurate and robust than previous models even without modifications to the network architectures or objective functions. I believe videos have much more potential to be mined, and temporal information is one of the most important cues for machines to perceive the visual world better.
In this work we present a new efficient approach to Human Action Recognition called Video Transformer Network (VTN). It leverages the latest advances in Computer Vision and Natural Language Processing and applies them to video understanding. The proposed method allows us to create lightweight CNN models that achieve high accuracy and real-time speed using just an RGB mono camera and general purpose CPU. Furthermore, we explain how to improve accuracy by distilling from multiple models with different modalities into a single model. We conduct a comparison with state-of-the-art methods and show that our approach performs on par with most of them on famous Action Recognition datasets. We benchmark the inference time of the models using the modern inference framework and argue that our approach compares favorably with other methods in terms of speed/accuracy trade-off, running at 56 FPS on CPU. The models and the training code are available.
Events in natural videos typically arise from spatio-temporal interactions between actors and objects and involve multiple co-occurring activities and object classes. To capture this rich visual and semantic context, we propose using two graphs: (1) an attributed spatio-temporal visual graph whose nodes correspond to actors and objects and whose edges encode different types of interactions, and (2) a symbolic graph that models semantic relationships. We further propose a graph neural network for refining the representations of actors, objects and their interactions on the resulting hybrid graph. Our model goes beyond current approaches that assume nodes and edges are of the same type, operate on graphs with fixed edge weights and do not use a symbolic graph. In particular, our framework: a) has specialized attention-based message functions for different node and edge types; b) uses visual edge features; c) integrates visual evidence with label relationships; and d) performs global reasoning in the semantic space. Experiments on challenging video understanding tasks, such as temporal action localization on the Charades dataset, show that the proposed method leads to state-of-the-art performance.
In this paper we present a new computer vision task, named video instance segmentation. The goal of this new task is simultaneous detection, segmentation and tracking of instances in videos. In words, it is the first time that the image instance segmentation problem is extended to the video domain. To facilitate research on this new task, we propose a large-scale benchmark called YouTube-VIS, which consists of 2883 high-resolution YouTube videos, a 40-category label set and 131k high-quality instance masks. In addition, we propose a novel algorithm called MaskTrack R-CNN for this task. Our new method introduces a new tracking branch to Mask R-CNN to jointly perform the detection, segmentation and tracking tasks simultaneously. Finally, we evaluate the proposed method and several strong baselines on our new dataset. Experimental results clearly demonstrate the advantages of the proposed algorithm and reveal insight for future improvement. We believe the video instance segmentation task will motivate the community along the line of research for video understanding.
Video recognition has been advanced in recent years by benchmarks with rich annotations. However, research is still mainly limited to human action or sports recognition - focusing on a highly specific video understanding task and thus leaving a significant gap towards describing the overall content of a video. We fill this gap by presenting a large-scale "Holistic Video Understanding Dataset"~(HVU). HVU is organized hierarchically in a semantic taxonomy that focuses on multi-label and multi-task video understanding as a comprehensive problem that encompasses the recognition of multiple semantic aspects in the dynamic scene. HVU contains approx.~572k videos in total with 9 million annotations for training, validation, and test set spanning over 3142 labels. HVU encompasses semantic aspects defined on categories of scenes, objects, actions, events, attributes, and concepts which naturally captures the real-world scenarios. We demonstrate the generalization capability of HVU on three challenging tasks: 1.) Video classification, 2.) Video captioning and 3.) Video clustering tasks. In particular for video classification, we introduce a new spatio-temporal deep neural network architecture called "Holistic Appearance and Temporal Network"~(HATNet) that builds on fusing 2D and 3D architectures into one by combining intermediate representations of appearance and temporal cues. HATNet focuses on the multi-label and multi-task learning problem and is trained in an end-to-end manner. Via our experiments, we validate the idea that holistic representation learning is complementary, and can play a key role in enabling many real-world applications.
Learning in the space-time domain remains a very challenging problem in machine learning and computer vision. Current computational models for understanding spatio-temporal visual data are heavily rooted in the classical single-image based paradigm. It is not yet well understood how to integrate information in space and time into a single, general model. We propose a neural graph model, recurrent in space and time, suitable for capturing both the local appearance and the complex higher-level interactions of different entities and objects within the changing world scene. Nodes and edges in our graph have dedicated neural networks for processing information. Nodes operate over features extracted from local parts in space and time and previous memory states. Edges process messages between connected nodes at different locations and spatial scales or between past and present time. Messages are passed iteratively in order to transmit information globally and establish long range interactions. Our model is general and could learn to recognize a variety of high level spatio-temporal concepts and be applied to different learning tasks. We demonstrate, through extensive experiments and ablation studies, that our model outperforms strong baselines and top published methods on recognizing complex activities in video. Moreover, we obtain state-of-the-art performance on the challenging Something-Something human-object interaction dataset.
Video understanding is emerging as a new paradigm for studying human-like AI. Question-and-Answering (Q&A) is used as a general benchmark to measure the level of intelligence for video understanding. While several previous studies have suggested datasets for video Q&A tasks, they did not really incorporate story-level understanding, resulting in highly-biased and lack of variance in degree of question difficulty. In this paper, we propose a hierarchical method for building Q&A datasets, i.e. hierarchical difficulty levels. We introduce three criteria for video story understanding, i.e. memory capacity, logical complexity, and DIKW (Data-Information-Knowledge-Wisdom) pyramid. We discuss how three-dimensional map constructed from these criteria can be used as a metric for evaluating the levels of intelligence relating to video story understanding.
Mutual information maximization has emerged as a powerful learning objective for unsupervised representation learning obtaining state-of-the-art performance in applications such as object recognition, speech recognition, and reinforcement learning. However, such approaches are fundamentally limited since a tight lower bound of mutual information requires sample size exponential in the mutual information. This limits the applicability of these approaches for prediction tasks with high mutual information, such as in video understanding or reinforcement learning. In these settings, such techniques are prone to overfit, both in theory and in practice, and capture only a few of the relevant factors of variation. This leads to incomplete representations that are not optimal for downstream tasks. In this work, we empirically demonstrate that mutual information-based representation learning approaches do fail to learn complete representations on a number of designed and real-world tasks. To mitigate these problems we introduce the Wasserstein dependency measure, which learns more complete representations by using the Wasserstein distance instead of the KL divergence in the mutual information estimator. We show that a practical approximation to this theoretically motivated solution, constructed using Lipschitz constraint techniques from the GAN literature, achieves substantially improved results on tasks where incomplete representations are a major challenge.
Many high-level video understanding methods require input in the form of object proposals. Currently, such proposals are predominantly generated with the help of networks that were trained for detecting and segmenting a set of known object classes, which limits their applicability to cases where all objects of interest are represented in the training set. This is a restriction for automotive scenarios, where unknown objects can frequently occur. We propose an approach that can reliably extract spatio-temporal object proposals for both known and unknown object categories from stereo video. Our 4D Generic Video Tubes (4D-GVT) method leverages motion cues, stereo data, and object instance segmentation to compute a compact set of video-object proposals that precisely localizes object candidates and their contours in 3D space and time. We show that given only a small amount of labeled data, our 4D-GVT proposal generator generalizes well to real-world scenarios, in which unknown categories appear. It outperforms other approaches that try to detect as many objects as possible by increasing the number of classes in the training set to several thousand.
Motion has shown to be useful for video understanding, where motion is typically represented by optical flow. However, computing flow from video frames is very time-consuming. Recent works directly leverage the motion vectors and residuals readily available in the compressed video to represent motion at no cost. While this avoids flow computation, it also hurts accuracy since the motion vector is noisy and has substantially reduced resolution, which makes it a less discriminative motion representation. To remedy these issues, we propose a lightweight generator network, which reduces noises in motion vectors and captures fine motion details, achieving a more Discriminative Motion Cue (DMC) representation. Since optical flow is a more accurate motion representation, we train the DMC generator to approximate flow using a reconstruction loss and a generative adversarial loss, jointly with the downstream action classification task. Extensive evaluations on three action recognition benchmarks (HMDB-51, UCF-101, and a subset of Kinetics) confirm the effectiveness of our method. Our full system, consisting of the generator and the classifier, is coined as DMC-Net which obtains high accuracy close to that of using flow and runs two orders of magnitude faster than using optical flow at inference time.
An important aspect of video understanding is the ability to predict the evolution of its content in the future. This paper presents a future frame semantic segmentation technique for predicting semantic masks of the current and future frames in a time-lapsed video. We specifically focus on time-lapsed videos with large temporal displacement to highlight the model's ability to capture large motions in time. We first introduce a unique semantic segmentation prediction dataset with over 120,000 time-lapsed sky-video frames and all corresponding semantic masks captured over a span of five years in North America region. The dataset has immense practical value for cloud cover analysis, which are treated as non-rigid objects of interest. %Here the model provides both semantic segmentation of cloud region and solar irradiance emitted from a region from the sky-videos. Next, our proposed recurrent network architecture departs from existing trend of using temporal convolutional networks (TCN) (or feed-forward networks), by explicitly learning an internal representations for the evolution of video content with time. Experimental evaluation shows an improvement of mean IoU over TCNs in the segmentation task by 10.8% for 10 mins (21% over 60 mins) ahead of time predictions. Further, our model simultaneously measures both the current and future solar irradiance from the same video frames with a normalized-MAE of 10.5% over two years. These results indicate that recurrent memory networks with attention mechanism are able to capture complex advective and diffused flow characteristic of dense fluids even with sparse temporal sampling and are more suitable for future frame prediction tasks for longer duration videos.
Video action recognition, a critical problem in video understanding, has been gaining increasing attention. To identify actions induced by complex object-object interactions, we need to consider not only spatial relations among objects in a single frame, but also temporal relations among different or the same objects across multiple frames. However, existing approaches that model video representations and non-local features are either incapable of explicitly modeling relations at the object-object level or unable to handle streaming videos. In this paper, we propose a novel dynamic hidden graph module to model complex object-object interactions in videos, of which two instantiations are considered: a visual graph that captures appearance/motion changes among objects and a location graph that captures relative spatiotemporal position changes among objects. Additionally, the proposed graph module allows us to process streaming videos, setting it apart from existing methods. Experimental results on benchmark datasets, Something-Something and ActivityNet, show the competitive performance of our method.
To understand the world, we humans constantly need to relate the present to the past, and put events in context. In this paper, we enable existing video models to do the same. We propose a long-term feature bank---supportive information extracted over the entire span of a video---to augment state-of-the-art video models that otherwise would only view short clips of 2-5 seconds. Our experiments demonstrate that augmenting 3D convolutional networks with a long-term feature bank yields state-of-the-art results on three challenging video datasets: AVA, EPIC-Kitchens, and Charades.
A dominant paradigm for learning-based approaches in computer vision is training generic models, such as ResNet for image recognition, or I3D for video understanding, on large datasets and allowing them to discover the optimal representation for the problem at hand. While this is an obviously attractive approach, it is not applicable in all scenarios. We claim that action detection is one such challenging problem - the models that need to be trained are large, and labeled data is expensive to obtain. To address this limitation, we propose to incorporate domain knowledge into the structure of the model, simplifying optimization. In particular, we augment a standard I3D network with a tracking module to aggregate long term motion patterns, and use a graph convolutional network to reason about interactions between actors and objects. Evaluated on the challenging AVA dataset, the proposed approach improves over the I3D baseline by 5.5% mAP and over the state-of-the-art by 4.8% mAP.
Automatically generating a natural language sentence to describe the content of an input video is a very challenging problem. It is an essential multimodal task in which auditory and visual contents are equally important. Although audio information has been exploited to improve video captioning in previous works, it is usually regarded as an additional feature fed into a black box fusion machine. How are the words in the generated sentences associated with the auditory and visual modalities? The problem is still not investigated. In this paper, we make the first attempt to design an interpretable audio-visual video captioning network to discover the association between words in sentences and audio-visual sequences. To achieve this, we propose a multimodal convolutional neural network-based audio-visual video captioning framework and introduce a modality-aware module for exploring modality selection during sentence generation. Besides, we collect new audio captioning and visual captioning datasets for further exploring the interactions between auditory and visual modalities for high-level video understanding. Extensive experiments demonstrate that the modality-aware module makes our model interpretable on modality selection during sentence generation. Even with the added interpretability, our video captioning network can still achieve comparable performance with recent state-of-the-art methods.
Understanding web instructional videos is an essential branch of video understanding in two aspects. First, most existing video methods focus on short-term actions for a-few-second-long video clips; these methods are not directly applicable to long videos. Second, unlike unconstrained long videos, e.g., movies, instructional videos are more structured in that they have step-by-step procedure constraining the understanding task. In this paper, we study reasoning on instructional videos via question-answering (QA). Surprisingly, it has not been an emphasis in the video community despite its rich applications. We thereby introduce YouQuek, an annotated QA dataset for instructional videos based on the recent YouCook2. The questions in YouQuek are not limited to cues on one frame but related to logical reasoning in the temporal dimension. Observing the lack of effective representations for modeling long videos, we propose a set of carefully designed models including a novel Recurrent Graph Convolutional Network (RGCN) that captures both temporal order and relation information. Furthermore, we study multiple modalities including description and transcripts for the purpose of boosting video understanding. Extensive experiments on YouQuek suggest that RGCN performs the best in terms of QA accuracy and a better performance is gained by introducing human annotated description.
True video understanding requires making sense of non-lambertian scenes where the color of light arriving at the camera sensor encodes information about not just the last object it collided with, but about multiple mediums -- colored windows, dirty mirrors, smoke or rain. Layered video representations have the potential of accurately modelling realistic scenes but have so far required stringent assumptions on motion, lighting and shape. Here we propose a learning-based approach for multi-layered video representation: we introduce novel uncertainty-capturing 3D convolutional architectures and train them to separate blended videos. We show that these models then generalize to single videos, where they exhibit interesting abilities: color constancy, factoring out shadows and separating reflections. We present quantitative and qualitative results on real world videos.
The success of deep neural networks generally requires a vast amount of training data to be labeled, which is expensive and unfeasible in scale, especially for video collections. To alleviate this problem, in this paper, we propose 3DRotNet: a fully self-supervised approach to learn spatiotemporal features from unlabeled videos. A set of rotations are applied to all videos, and a pretext task is defined as prediction of these rotations. When accomplishing this task, 3DRotNet is actually trained to understand the semantic concepts and motions in videos. In other words, it learns a spatiotemporal video representation, which can be transferred to improve video understanding tasks in small datasets. Our extensive experiments successfully demonstrate the effectiveness of the proposed framework on action recognition, leading to significant improvements over the state-of-the-art self-supervised methods. With the self-supervised pre-trained 3DRotNet from large datasets, the recognition accuracy is boosted up by 20.4% on UCF101 and 16.7% on HMDB51 respectively, compared to the models trained from scratch.