Related papers: Commonly Uncommon: Semantic Sparsity in Situation …

Unsupervised methods have proven effective for discriminative tasks in a single-modality scenario. In this paper, we present a multimodal framework for learning sparse representations that can capture semantic correlation between…

In sparse coding, we attempt to extract features of input vectors, assuming that the data is inherently structured as a sparse superposition of basic building blocks. Similarly, neural networks perform a given task by learning features of…

Abnormal event detection in videos is a challenging problem, partly due to the multiplicity of abnormal patterns and the lack of their corresponding annotations. In this paper, we propose new constrained pretext tasks to learn object level…

In this paper we propose and carefully evaluate a sequence labeling framework which solely utilizes sparse indicator features derived from dense distributed word representations. The proposed model obtains (near) state-of-the art…

Grounded Situation Recognition (GSR) aims to generate structured semantic summaries of images for "human-like" event understanding. Specifically, GSR task not only detects the salient activity verb (e.g. buying), but also predicts all…

We propose a computationally efficient and high-performance classification algorithm by incorporating class structural information in analysis dictionary learning. To achieve more consistent classification, we associate a class…

The recurring context in which objects appear holds valuable information that can be employed to predict their existence. This intuitive observation indeed led many researchers to endow appearance-based detectors with explicit reasoning…

Segmentation and Rhetorical Role Labeling of legal judgements play a crucial role in retrieval and adjacent tasks, including case summarization, semantic search, argument mining etc. Previous approaches have formulated this task either as…

Neural network-based language models deal with data sparsity problems by mapping the large discrete space of words into a smaller continuous space of real-valued vectors. By learning distributed vector representations for words, each…

The ability to accurately detect and classify objects at varying pixel sizes in cluttered scenes is crucial to many Navy applications. However, detection performance of existing state-of the-art approaches such as convolutional neural…

Given the features of a video, recurrent neural networks can be used to automatically generate a caption for the video. Existing methods for video captioning have at least three limitations. First, semantic information has been widely…

Automatic speech recognition (ASR) system is becoming a ubiquitous technology. Although its accuracy is closing the gap with that of human level under certain settings, one area that can further improve is to incorporate user-specific…

A major goal of computer vision is to enable computers to interpret visual situations---abstract concepts (e.g., "a person walking a dog," "a crowd waiting for a bus," "a picnic") whose image instantiations are linked more by their common…

Object detection is one of the most active areas in computer vision, which has made significant improvement in recent years. Current state-of-the-art object detection methods mostly adhere to the framework of regions with convolutional…

We develop a representation suitable for the unconstrained recognition of words in natural images: the general case of no fixed lexicon and unknown length. To this end we propose a convolutional neural network (CNN) based architecture which…

This paper describes a fast and accurate semantic image segmentation approach that encodes not only the discriminative features from deep neural networks, but also the high-order context compatibility among adjacent objects as well as low…

Numerous embedding models have been recently explored to incorporate semantic knowledge into visual recognition. Existing methods typically focus on minimizing the distance between the corresponding images and texts in the embedding space…

Referring expression comprehension aims to localize objects identified by natural language descriptions. This is a challenging task as it requires understanding of both visual and language domains. One nature is that each object can be…

Constructing an organized dataset comprised of a large number of images and several captions for each image is a laborious task, which requires vast human effort. On the other hand, collecting a large number of images and sentences…

This study addresses an image-matching problem in challenging cases, such as large scene variations or textureless scenes. To gain robustness to such situations, most previous studies have attempted to encode the global contexts of a scene…