Search Results - "Shagan Sah"

Understanding temporal structure for video captioning by Sah, Shagan, Nguyen, Thang, Ptucha, Ray

“…Recent research in convolutional and recurrent neural networks has fueled incredible advances in video understanding. We propose a video captioning framework…”
Get full text

Semantic Text Summarization of Long Videos by Shagan Sah, Kulhare, Sourabh, Gray, Allison, Venugopalan, Subhashini, Prud'Hommeaux, Emily, Ptucha, Raymond

“…Long videos captured by consumers are typically tied to some of the most important moments of their lives, yet ironically are often the least frequently…”
Get full text

Robust Spatial Filtering With Graph Convolutional Neural Networks by Such, Felipe Petroski, Sah, Shagan, Dominguez, Miguel Alexander, Pillai, Suhas, Chao Zhang, Michael, Andrew, Cahill, Nathan D., Ptucha, Raymond

“…Convolutional neural networks (CNNs) have recently led to incredible breakthroughs on a variety of pattern recognition problems. Banks of finite-impulse…”
Get full text

Show, Translate and Tell by Peri, Dheeraj, Sah, Shagan, Ptucha, Raymond

“…Humans have an incredible ability to process and understand information from multiple sources such as images, video, text, and speech. Recent success of deep…”
Get full text

Key frame extraction for salient activity recognition by Kulhare, Sourabh, Sah, Shagan, Pillai, Suhas, Ptucha, Raymond

“…Surveillance cameras have become big business, with most metropolitan cities spending millions of dollars to watch residents, both from street corners, public…”
Get full text

Towards 3D convolutional neural networks with meshes by Dominguez, Miguel, Such, Felipe Petroski, Sah, Shagan, Ptucha, Raymond

“…Voxels are an effective approach to 3D mesh and point cloud classification because they build upon mature Convolutional Neural Network concepts. We show…”
Get full text

Multi-Modal Deep Learning to Understand Vision and Language by Sah, Shagan

“…Developing intelligent agents that can perceive and understand the rich visual world around us has been a long-standing goal in the field of artificial…”
Get full text

Multi Stage Common Vector Space for Multimodal Embeddings by Gopalakrishnan, Sabarish, Udaiyar, Premkumar, Sah, Shagan, Ptucha, Raymond

“…Deep learning frameworks have proven to be very effective at tasks like classification, segmentation, detection, and translation. Before being processed by a…”
Get full text

Image description through fusion based recurrent multi-modal learning by Oruganti, Ram Manohar, Sah, Shagan, Pillai, Suhas, Ptucha, Raymond

“…Current research in computer vision and machine learning has demonstrated some great abilities at detecting and recognizing objects in natural images. The…”
Get full text

Semantically Invariant Text-to-Image Generation by Sah, Shagan, Peri, Dheeraj, Shringi, Ameya, Zhang, Chi, Dominguez, Miguez, Savakis, Andreas, Ptucha, Rav

“…Image captioning has demonstrated models that are capable of generating plausible text given input images or videos. Further, recent work in image generation…”
Get full text

Multimodal Reconstruction Using Vector Representation by Sah, Shagan, Shringi, Ameya, Peri, Dheeraj, Hamilton, John, Savakis, Andreas, Ptucha, Ray

“…Recent work has demonstrated that neural embedding from multiple modalities can be utilized to focus the results of generative adversarial networks. However,…”
Get full text

Batch-normalized recurrent highway networks by Zhang, Chi, Nguyen, Thang, Sah, Shagan, Ptucha, Raymond, Loui, Alexander, Salvaggio, Carl

“…Gradient control plays an important role in feed-forward networks applied to various computer vision tasks. Previous work has shown that Recurrent Highway…”
Get full text

Vector Learning for Cross Domain Representations by Sah, Shagan, Zhang, Chi, Nguyen, Thang, Peri, Dheeraj Kumar, Shringi, Ameya, Ptucha, Raymond

“…Recently, generative adversarial networks have gained a lot of popularity for image generation tasks. However, such models are associated with complex learning…”
Get full text

Adaptive hierarchical classification networks by Nooka, Sai Prasad, Chennupati, Sumanth, Veerabhadra, Karthik, Sah, Shagan, Ptucha, Raymond

“…Hierarchical decomposition enables increased number of classes in a classification problem. Class similarities guide the creation of a family of course to fine…”
Get full text

A multi-temporal fusion-based approach for land cover mapping in support of nuclear incident response by Sah, Shagan

“…An increasingly important application of remote sensing is to provide decision support during emergency response and disaster management efforts. Land cover…”
Get full text

General-Purpose Deep Point Cloud Feature Extractor by Dominguez, Miguel, Dhamdhere, Rohan, Petkar, Atir, Jain, Saloni, Sah, Shagan, Ptucha, Raymond

“…Depth sensors used in autonomous driving and gaming systems often report back 3D point clouds. The lack of structure from these sensors does not allow these…”
Get full text

Show, Translate and Tell by Peri, Dheeraj, Sah, Shagan, Ptucha, Raymond

“…Humans have an incredible ability to process and understand information from multiple sources such as images, video, text, and speech. Recent success of deep…”
Get full text

Adaptive Hierarchical Decomposition of Large Deep Networks by Chennupati, Sumanth, Nooka, Sai, Sah, Shagan, Ptucha, Raymond W

“…Deep learning has recently demonstrated its ability to rival the human brain for visual object recognition. As datasets get larger, a natural question to ask…”
Get full text

Semantic sentence embeddings for paraphrasing and text summarization by Zhang, Chi, Sah, Shagan, Nguyen, Thang, Peri, Dheeraj, Loui, Alexander, Salvaggio, Carl, Ptucha, Raymond

“…This paper introduces a sentence to vector encoding framework suitable for advanced natural language processing. Our latent representation is shown to encode…”
Get full text

Multistream hierarchical boundary network for video captioning by Nguyen, Thang, Sah, Shagan, Ptucha, Raymond

“…Video understanding has become increasingly important as surveillance, social, and informational videos weave themselves into our everyday lives. Video…”
Get full text