arXiv subjects

Leonid Sigal

Publications and source records attributed to Leonid Sigal.

At least 127 records · Page 7Linked to original sources

arXiv2018

Visual Reference Resolution using Attention Memory for Visual Dialog

Visual dialog is a task of answering a series of inter-dependent questions given an input image, and often requires to resolve visual references among the questions. This problem is different from visual question answering (VQA), which relies on spatial attention (a.k.a. visual grounding) estimated from an image and question pair. We propose a novel attention mechanism that exploits visual attentions in the past to resolve the current reference in the visual dialog scenario. The proposed model is equipped with an associative attention memory storing a sequence of previous (attention, key) pairs. From this memory, the model retrieves the previous attention, taking into account recency, which is most relevant for the current question, in order to resolve potentially ambiguous references. The model then merges the retrieved attention with a tentative one to obtain the final attention for the current question; specifically, we use dynamic parameter prediction to combine the two attentions conditioned on the question. Through extensive experiments on a new synthetic visual dialog dataset, we show that our model significantly outperforms the state-of-the-art (by ~16 % points) in situations, where visual reference resolution plays an important role. Moreover, the proposed model achieves superior performance (~ 2 % points improvement) in the Visual Dialog dataset, despite having significantly fewer parameters than the baselines.

cs.CV↗

arXiv2018

Modular Generative Adversarial Networks

Existing methods for multi-domain image-to-image translation (or generation) attempt to directly map an input image (or a random vector) to an image in one of the output domains. However, most existing methods have limited scalability and robustness, since they require building independent models for each pair of domains in question. This leads to two significant shortcomings: (1) the need to train exponential number of pairwise models, and (2) the inability to leverage data from other domains when training a particular pairwise mapping. Inspired by recent work on module networks, this paper proposes ModularGAN for multi-domain image generation and image-to-image translation. ModularGAN consists of several reusable and composable modules that carry on different functions (e.g., encoding, decoding, transformations). These modules can be trained simultaneously, leveraging data from all domains, and then combined to construct specific GAN networks at test time, according to the specific image translation task. This leads to ModularGAN's superior flexibility of generating (or translating to) an image in any desired domain. Experimental results demonstrate that our model not only presents compelling perceptual results but also outperforms state-of-the-art methods on multi-domain facial attribute transfer.

cs.CV↗

arXiv2018

A Neural Multi-sequence Alignment TeCHnique (NeuMATCH)

The alignment of heterogeneous sequential data (video to text) is an important and challenging problem. Standard techniques for this task, including Dynamic Time Warping (DTW) and Conditional Random Fields (CRFs), suffer from inherent drawbacks. Mainly, the Markov assumption implies that, given the immediate past, future alignment decisions are independent of further history. The separation between similarity computation and alignment decision also prevents end-to-end training. In this paper, we propose an end-to-end neural architecture where alignment actions are implemented as moving data between stacks of Long Short-term Memory (LSTM) blocks. This flexible architecture supports a large variety of alignment tasks, including one-to-one, one-to-many, skipping unmatched elements, and (with extensions) non-monotonic alignment. Extensive experiments on semi-synthetic and real datasets show that our algorithm outperforms state-of-the-art baselines.

cs.CV↗

arXiv2018

Probabilistic Video Generation using Holistic Attribute Control

Videos express highly structured spatio-temporal patterns of visual data. A video can be thought of as being governed by two factors: (i) temporally invariant (e.g., person identity), or slowly varying (e.g., activity), attribute-induced appearance, encoding the persistent content of each frame, and (ii) an inter-frame motion or scene dynamics (e.g., encoding evolution of the person ex-ecuting the action). Based on this intuition, we propose a generative framework for video generation and future prediction. The proposed framework generates a video (short clip) by decoding samples sequentially drawn from a latent space distribution into full video frames. Variational Autoencoders (VAEs) are used as a means of encoding/decoding frames into/from the latent space and RNN as a wayto model the dynamics in the latent space. We improve the video generation consistency through temporally-conditional sampling and quality by structuring the latent space with attribute controls; ensuring that attributes can be both inferred and conditioned on during learning/generation. As a result, given attributes and/orthe first frame, our model is able to generate diverse but highly consistent sets ofvideo sequences, accounting for the inherent uncertainty in the prediction task. Experimental results on Chair CAD, Weizmann Human Action, and MIT-Flickr datasets, along with detailed comparison to the state-of-the-art, verify effectiveness of the framework.

cs.CV↗

arXiv2018

Heterogeneous Knowledge Transfer in Video Emotion Recognition, Attribution and Summarization

Emotion is a key element in user-generated videos. However, it is difficult to understand emotions conveyed in such videos due to the complex and unstructured nature of user-generated content and the sparsity of video frames expressing emotion. In this paper, for the first time, we study the problem of transferring knowledge from heterogeneous external sources, including image and textual data, to facilitate three related tasks in understanding video emotion: emotion recognition, emotion attribution and emotion-oriented summarization. Specifically, our framework (1) learns a video encoding from an auxiliary emotional image dataset in order to improve supervised video emotion recognition, and (2) transfers knowledge from an auxiliary textual corpora for zero-shot recognition of emotion classes unseen during training. The proposed technique for knowledge transfer facilitates novel applications of emotion attribution and emotion-oriented summarization. A comprehensive set of experiments on multiple datasets demonstrate the effectiveness of our framework.

cs.CV↗

arXiv2017

Recent Advances in Zero-shot Recognition

With the recent renaissance of deep convolution neural networks, encouraging breakthroughs have been achieved on the supervised recognition tasks, where each class has sufficient training data and fully annotated training data. However, to scale the recognition to a large number of classes with few or now training samples for each class remains an unsolved problem. One approach to scaling up the recognition is to develop models capable of recognizing unseen categories without any training instances, or zero-shot recognition/ learning. This article provides a comprehensive review of existing zero-shot recognition techniques covering various aspects ranging from representations of models, and from datasets and evaluation settings. We also overview related recognition tasks including one-shot and open set recognition which can be used as natural extensions of zero-shot recognition when limited number of class samples become available or when zero-shot recognition is implemented in a real-world setting. Importantly, we highlight the limitations of existing approaches and point out future research directions in this existing new research area.

cs.CV↗

arXiv2017

Action Classification and Highlighting in Videos

Inspired by recent advances in neural machine translation, that jointly align and translate using encoder-decoder networks equipped with attention, we propose an attentionbased LSTM model for human activity recognition. Our model jointly learns to classify actions and highlight frames associated with the action, by attending to salient visual information through a jointly learned soft-attention networks. We explore attention informed by various forms of visual semantic features, including those encoding actions, objects and scenes. We qualitatively show that soft-attention can learn to effectively attend to important objects and scene information correlated with specific human actions. Further, we show that, quantitatively, our attention-based LSTM outperforms the vanilla LSTM and CNN models used by stateof-the-art methods. On a large-scale youtube video dataset, ActivityNet, our model outperforms competing methods in action classification.

cs.CV↗

arXiv2017

Predicting Personality from Book Preferences with User-Generated Content Labels

Psychological studies have shown that personality traits are associated with book preferences. However, past findings are based on questionnaires focusing on conventional book genres and are unrepresentative of niche content. For a more comprehensive measure of book content, this study harnesses a massive archive of content labels, also known as 'tags', created by users of an online book catalogue, Goodreads.com. Combined with data on preferences and personality scores collected from Facebook users, the tag labels achieve high accuracy in personality prediction by psychological standards. We also group tags into broader genres, to check their validity against past findings. Our results are robust across both tag and genre levels of analyses, and consistent with existing literature. Moreover, user-generated tag labels reveal unexpected insights, such as cultural differences, book reading behaviors, and other non-content factors affecting preferences. To our knowledge, this is currently the largest study that explores the relationship between personality and book content preferences.

cs.CY↗

arXiv2017

Weakly-supervised Visual Grounding of Phrases with Linguistic Structures

We propose a weakly-supervised approach that takes image-sentence pairs as input and learns to visually ground (i.e., localize) arbitrary linguistic phrases, in the form of spatial attention masks. Specifically, the model is trained with images and their associated image-level captions, without any explicit region-to-phrase correspondence annotations. To this end, we introduce an end-to-end model which learns visual groundings of phrases with two types of carefully designed loss functions. In addition to the standard discriminative loss, which enforces that attended image regions and phrases are consistently encoded, we propose a novel structural loss which makes use of the parse tree structures induced by the sentences. In particular, we ensure complementarity among the attention masks that correspond to sibling noun phrases, and compositionality of attention masks among the children and parent phrases, as defined by the sentence parse tree. We validate the effectiveness of our approach on the Microsoft COCO and Visual Genome datasets.

cs.CV↗

arXiv2017

Semi-Latent GAN: Learning to generate and modify facial images from attributes

Generating and manipulating human facial images using high-level attributal controls are important and interesting problems. The models proposed in previous work can solve one of these two problems (generation or manipulation), but not both coherently. This paper proposes a novel model that learns how to both generate and modify the facial image from high-level semantic attributes. Our key idea is to formulate a Semi-Latent Facial Attribute Space (SL-FAS) to systematically learn relationship between user-defined and latent attributes, as well as between those attributes and RGB imagery. As part of this newly formulated space, we propose a new model --- SL-GAN which is a specific form of Generative Adversarial Network. Finally, we present an iterative training algorithm for SL-GAN. The experiments on recent CelebA and CASIA-WebFace datasets validate the effectiveness of our proposed framework. We will also make data, pre-trained models and code available.

cs.CV↗

arXiv2017

Learning to Generate Posters of Scientific Papers by Probabilistic Graphical Models

Researchers often summarize their work in the form of scientific posters. Posters provide a coherent and efficient way to convey core ideas expressed in scientific papers. Generating a good scientific poster, however, is a complex and time consuming cognitive task, since such posters need to be readable, informative, and visually aesthetic. In this paper, for the first time, we study the challenging problem of learning to generate posters from scientific papers. To this end, a data-driven framework, that utilizes graphical models, is proposed. Specifically, given content to display, the key elements of a good poster, including attributes of each panel and arrangements of graphical elements are learned and inferred from data. During the inference stage, an MAP inference framework is employed to incorporate some design principles. In order to bridge the gap between panel attributes and the composition within each panel, we also propose a recursive page splitting algorithm to generate the panel layout for a poster. To learn and validate our model, we collect and release a new benchmark dataset, called NJU-Fudan Paper-Poster dataset, which consists of scientific papers and corresponding posters with exhaustively labelled panels and attributes. Qualitative and quantitative results indicate the effectiveness of our approach.

cs.CV↗

arXiv2016

Learning Language-Visual Embedding for Movie Understanding with Natural-Language

Learning a joint language-visual embedding has a number of very appealing properties and can result in variety of practical application, including natural language image/video annotation and search. In this work, we study three different joint language-visual neural network model architectures. We evaluate our models on large scale LSMDC16 movie dataset for two tasks: 1) Standard Ranking for video annotation and retrieval 2) Our proposed movie multiple-choice test. This test facilitate automatic evaluation of visual-language models for natural language video annotation based on human activities. In addition to original Audio Description (AD) captions, provided as part of LSMDC16, we collected and will make available a) manually generated re-phrasings of those captions obtained using Amazon MTurk b) automatically generated human activity elements in "Predicate + Object" (PO) phrases based on "Knowlywood", an activity knowledge mining model. Our best model archives Recall@10 of 19.2% on annotation and 18.9% on video retrieval tasks for subset of 1000 samples. For multiple-choice test, our best model achieve accuracy 58.11% over whole LSMDC16 public test-set.

cs.CV↗

arXiv2016

Semi-supervised Vocabulary-informed Learning

Despite significant progress in object categorization, in recent years, a number of important challenges remain, mainly, ability to learn from limited labeled data and ability to recognize object classes within large, potentially open, set of labels. Zero-shot learning is one way of addressing these challenges, but it has only been shown to work with limited sized class vocabularies and typically requires separation between supervised and unsupervised classes, allowing former to inform the latter but not vice versa. We propose the notion of semi-supervised vocabulary-informed learning to alleviate the above mentioned challenges and address problems of supervised, zero-shot and open set recognition using a unified framework. Specifically, we propose a maximum margin framework for semantic manifold-based recognition that incorporates distance constraints from (both supervised and unsupervised) vocabulary atoms, ensuring that labeled samples are projected closest to their correct prototypes, in the embedding space, than to others. We show that resulting model shows improvements in supervised, zero-shot, and large open set recognition, with up to 310K class vocabulary on AwA and ImageNet datasets.

cs.CV↗

arXiv2016

Learning to Generate Posters of Scientific Papers

Researchers often summarize their work in the form of posters. Posters provide a coherent and efficient way to convey core ideas from scientific papers. Generating a good scientific poster, however, is a complex and time consuming cognitive task, since such posters need to be readable, informative, and visually aesthetic. In this paper, for the first time, we study the challenging problem of learning to generate posters from scientific papers. To this end, a data-driven framework, that utilizes graphical models, is proposed. Specifically, given content to display, the key elements of a good poster, including panel layout and attributes of each panel, are learned and inferred from data. Then, given inferred layout and attributes, composition of graphical elements within each panel is synthesized. To learn and validate our model, we collect and make public a Poster-Paper dataset, which consists of scientific papers and corresponding posters with exhaustively labelled panels and attributes. Qualitative and quantitative results indicate the effectiveness of our approach.

cs.AI↗

arXiv2015

Do Less and Achieve More: Training CNNs for Action Recognition Utilizing Action Images from the Web

Recently, attempts have been made to collect millions of videos to train CNN models for action recognition in videos. However, curating such large-scale video datasets requires immense human labor, and training CNNs on millions of videos demands huge computational resources. In contrast, collecting action images from the Web is much easier and training on images requires much less computation. In addition, labeled web images tend to contain discriminative action poses, which highlight discriminative portions of a video's temporal progression. We explore the question of whether we can utilize web action images to train better CNN models for action recognition in videos. We collect 23.8K manually filtered images from the Web that depict the 101 actions in the UCF101 action video dataset. We show that by utilizing web action images along with videos in training, significant performance boosts of CNN models can be achieved. We then investigate the scalability of the process by leveraging crawled web images (unfiltered) for UCF101 and ActivityNet. We replace 16.2M video frames by 393K unfiltered images and get comparable performance.

cs.CV↗

arXiv2015

Learning from Synthetic Data Using a Stacked Multichannel Autoencoder

Learning from synthetic data has many important and practical applications. An example of application is photo-sketch recognition. Using synthetic data is challenging due to the differences in feature distributions between synthetic and real data, a phenomenon we term synthetic gap. In this paper, we investigate and formalize a general framework-Stacked Multichannel Autoencoder (SMCAE) that enables bridging the synthetic gap and learning from synthetic data more efficiently. In particular, we show that our SMCAE can not only transform and use synthetic data on the challenging face-sketch recognition task, but that it can also help simulate real images, which can be used for training classifiers for recognition. Preliminary experiments validate the effectiveness of the framework.

cs.CV↗

arXiv2015

Learning Classifiers from Synthetic Data Using a Multichannel Autoencoder

We propose a method for using synthetic data to help learning classifiers. Synthetic data, even is generated based on real data, normally results in a shift from the distribution of real data in feature space. To bridge the gap between the real and synthetic data, and jointly learn from synthetic and real data, this paper proposes a Multichannel Autoencoder(MCAE). We show that by suing MCAE, it is possible to learn a better feature representation for classification. To evaluate the proposed approach, we conduct experiments on two types of datasets. Experimental results on two datasets validate the efficiency of our MCAE model and our methodology of generating synthetic data.

cs.CV↗

arXiv2015

Hierarchical Maximum-Margin Clustering

We present a hierarchical maximum-margin clustering method for unsupervised data analysis. Our method extends beyond flat maximum-margin clustering, and performs clustering recursively in a top-down manner. We propose an effective greedy splitting criteria for selecting which cluster to split next, and employ regularizers that enforce feature sharing/competition for capturing data semantics. Experimental results obtained on four standard datasets show that our method outperforms flat and hierarchical clustering baselines, while forming clean and semantically meaningful cluster hierarchies.

cs.LG↗