Search Results for author: Bharat Singh

Found 24 papers, 8 papers with code

Scale Normalized Image Pyramids with AutoFocus for Object Detection

1 code implementation10 Feb 2021 Bharat Singh, Mahyar Najibi, Abhishek Sharma, Larry S. Davis

The resulting algorithm is referred to as AutoFocus and results in a 2. 5-5 times speed-up during inference when used with SNIP.

Object Detection

ASAP-NMS: Accelerating Non-Maximum Suppression Using Spatially Aware Priors

1 code implementation19 Jul 2020 Rohun Tripathi, Vasu Singla, Mahyar Najibi, Bharat Singh, Abhishek Sharma, Larry Davis

The widely adopted sequential variant of Non Maximum Suppression (or Greedy-NMS) is a crucial module for object-detection pipelines.

Object Detection Region Proposal

RSO: A Gradient Free Sampling Based Approach For Training Deep Neural Networks

no code implementations12 May 2020 Rohun Tripathi, Bharat Singh

To this end, RSO adds a perturbation to a weight in a deep neural network and tests if it reduces the loss on a mini-batch.

General Classification

Recognizing Instagram Filtered Images with Feature De-stylization

no code implementations30 Dec 2019 Zhe Wu, Zuxuan Wu, Bharat Singh, Larry S. Davis

Deep neural networks have been shown to suffer from poor generalization when small perturbations are added (like Gaussian noise), yet little work has been done to evaluate their robustness to more natural image transformations like photo filters.

Style Transfer

Automatic Long-Term Deception Detection in Group Interaction Videos

no code implementations15 May 2019 Chongyang Bai, Maksim Bolonkin, Judee Burgoon, Chao Chen, Norah Dunbar, Bharat Singh, V. S. Subrahmanian, Zhe Wu

Most work on automated deception detection (ADD) in video has two restrictions: (i) it focuses on a video of one person, and (ii) it focuses on a single act of deception in a one or two minute video.

Deception Detection

An Analysis of Pre-Training on Object Detection

no code implementations11 Apr 2019 Hengduo Li, Bharat Singh, Mahyar Najibi, Zuxuan Wu, Larry S. Davis

We analyze how well their features generalize to tasks like image classification, semantic segmentation and object detection on small datasets like PASCAL-VOC, Caltech-256, SUN-397, Flowers-102 etc.

Classification General Classification +3

TAN: Temporal Aggregation Network for Dense Multi-label Action Recognition

no code implementations14 Dec 2018 Xiyang Dai, Bharat Singh, Joe Yue-Hei Ng, Larry S. Davis

We present Temporal Aggregation Network (TAN) which decomposes 3D convolutions into spatial and temporal aggregation blocks.

Action Recognition

AutoFocus: Efficient Multi-Scale Inference

1 code implementation ICCV 2019 Mahyar Najibi, Bharat Singh, Larry S. Davis

Instead of processing an entire image pyramid, AutoFocus adopts a coarse to fine approach and only processes regions which are likely to contain small objects at finer scales.

Soft Sampling for Robust Object Detection

1 code implementation18 Jun 2018 Zhe Wu, Navaneeth Bodla, Bharat Singh, Mahyar Najibi, Rama Chellappa, Larry S. Davis

Interestingly, we observe that after dropping 30% of the annotations (and labeling them as background), the performance of CNN-based object detectors like Faster-RCNN only drops by 5% on the PASCAL VOC dataset.

Robust Object Detection

An Analysis of Scale Invariance in Object Detection ­ SNIP

no code implementations CVPR 2018 Bharat Singh, Larry S. Davis

On the COCO dataset, our single model performance is 45. 7% and an ensemble of 3 networks obtains an mAP of 48. 3%.

Object Detection

SNIPER: Efficient Multi-Scale Training

3 code implementations NeurIPS 2018 Bharat Singh, Mahyar Najibi, Larry S. Davis

Our implementation based on Faster-RCNN with a ResNet-101 backbone obtains an mAP of 47. 6% on the COCO dataset for bounding box detection and can process 5 images per second during inference with a single GPU.

Object Detection Region Proposal

Deception Detection in Videos

no code implementations12 Dec 2017 Zhe Wu, Bharat Singh, Larry S. Davis, V. S. Subrahmanian

We present a system for covert automated deception detection in real-life courtroom trial videos.

Action Recognition Deception Detection In Videos

R-FCN-3000 at 30fps: Decoupling Detection and Classification

2 code implementations CVPR 2018 Bharat Singh, Hengduo Li, Abhishek Sharma, Larry S. Davis

Our approach is a modification of the R-FCN architecture in which position-sensitive filters are shared across different object classes for performing localization.

Classification General Classification

An Analysis of Scale Invariance in Object Detection - SNIP

no code implementations22 Nov 2017 Bharat Singh, Larry S. Davis

On the COCO dataset, our single model performance is 45. 7% and an ensemble of 3 networks obtains an mAP of 48. 3%.

Object Detection

Temporal Context Network for Activity Localization in Videos

no code implementations ICCV 2017 Xiyang Dai, Bharat Singh, Guyue Zhang, Larry S. Davis, Yan Qiu Chen

For each temporal segment inside a proposal, features are uniformly sampled at a pair of scales and are input to a temporal convolutional neural network for classification.

Classification General Classification +1

Soft-NMS -- Improving Object Detection With One Line of Code

8 code implementations ICCV 2017 Navaneeth Bodla, Bharat Singh, Rama Chellappa, Larry S. Davis

To this end, we propose Soft-NMS, an algorithm which decays the detection scores of all other objects as a continuous function of their overlap with M. Hence, no object is eliminated in this process.

Object Detection

Fast-AT: Fast Automatic Thumbnail Generation using Deep Neural Networks

no code implementations CVPR 2017 Seyed A. Esmaeili, Bharat Singh, Larry S. Davis

It is a fully-convolutional deep neural network, which learns specific filters for thumbnails of different sizes and aspect ratios.

Training Neural Networks Without Gradients: A Scalable ADMM Approach

2 code implementations6 May 2016 Gavin Taylor, Ryan Burmeister, Zheng Xu, Bharat Singh, Ankit Patel, Tom Goldstein

With the growing importance of large network models and enormous training datasets, GPUs have become increasingly necessary to train neural networks.

VRFP: On-the-fly Video Retrieval using Web Images and Fast Fisher Vector Products

no code implementations10 Dec 2015 Xintong Han, Bharat Singh, Vlad I. Morariu, Larry S. Davis

VRFP is a real-time video retrieval framework based on short text input queries, which obtains weakly labeled training images from the web after the query is known.

Re-Ranking Video Retrieval +1

Layer-Specific Adaptive Learning Rates for Deep Networks

no code implementations15 Oct 2015 Bharat Singh, Soham De, Yangmuzi Zhang, Thomas Goldstein, Gavin Taylor

In this paper, we attempt to overcome the two above problems by proposing an optimization method for training deep neural networks which uses learning rates which are both specific to each layer in the network and adaptive to the curvature of the function, increasing the learning rate at low curvature points.

Image Classification

Selecting Relevant Web Trained Concepts for Automated Event Retrieval

no code implementations ICCV 2015 Bharat Singh, Xintong Han, Zhe Wu, Vlad I. Morariu, Larry S. Davis

Given a text description of an event, event retrieval is performed by selecting concepts linguistically related to the event description and fusing the concept responses on unseen videos.

Domain Adaptation

Cannot find the paper you are looking for? You can Submit a new open access paper.