Get our free extension to see links to code for papers anywhere online!

 Add to Chrome

 Add to Firefox

CatalyzeX Code Finder - Browser extension linking code for ML papers across the web! | Product Hunt Embed
Utilizing Every Image Object for Semi-supervised Phrase Grounding

Nov 05, 2020
Haidong Zhu, Arka Sadhu, Zhaoheng Zheng, Ram Nevatia


  Access Paper or Ask Questions

SPAN: Spatial Pyramid Attention Network forImage Manipulation Localization

Sep 01, 2020
Xuefeng Hu, Zhihan Zhang, Zhenye Jiang, Syomantak Chaudhuri, Zhenheng Yang, Ram Nevatia

* ECCV 2020 

  Access Paper or Ask Questions

CPARR: Category-based Proposal Analysis for Referring Relationships

Apr 17, 2020
Chuanzi He, Haidong Zhu, Jiyang Gao, Kan Chen, Ram Nevatia

* CVPR 2020 Workshop on Multimodal Learning 

  Access Paper or Ask Questions

Video Object Grounding using Semantic Roles in Language Description

Mar 24, 2020
Arka Sadhu, Kan Chen, Ram Nevatia

* CVPR20 camera-ready including appendix 

  Access Paper or Ask Questions

Curriculum DeepSDF

Mar 19, 2020
Yueqi Duan, Haidong Zhu, He Wang, Li Yi, Ram Nevatia, Leonidas J. Guibas


  Access Paper or Ask Questions

Zero-Shot Grounding of Objects from Natural Language Queries

Aug 20, 2019
Arka Sadhu, Kan Chen, Ram Nevatia

* ICCV19 oral, camera-ready version 

  Access Paper or Ask Questions

Pose-variant 3D Facial Attribute Generation

Jul 24, 2019
Feng-Ju Chang, Xiang Yu, Ram Nevatia, Manmohan Chandraker


  Access Paper or Ask Questions

Activity Driven Weakly Supervised Object Detection

Apr 02, 2019
Zhenheng Yang, Dhruv Mahajan, Deepti Ghadiyaram, Ram Nevatia, Vignesh Ramanathan

* CVPR'19 camera ready 

  Access Paper or Ask Questions

PIRC Net : Using Proposal Indexing, Relationships and Context for Phrase Grounding

Dec 07, 2018
Rama Kovvuri, Ram Nevatia

* Accepted in ACCV 2018 

  Access Paper or Ask Questions

NOTE-RCNN: NOise Tolerant Ensemble RCNN for Semi-Supervised Object Detection

Dec 01, 2018
JIyang Gao, Jiang Wang, Shengyang Dai, Li-Jia Li, Ram Nevatia

* 8 pages 

  Access Paper or Ask Questions

MAC: Mining Activity Concepts for Language-based Temporal Localization

Nov 21, 2018
Runzhou Ge, Jiyang Gao, Kan Chen, Ram Nevatia

* WACV 2019 

  Access Paper or Ask Questions

Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding

Oct 14, 2018
Chenxu Luo, Zhenheng Yang, Peng Wang, Yang Wang, Wei Xu, Ram Nevatia, Alan Yuille

* Chenxu Luo, Zhenheng Yang, and Peng Wang contributed equally, TPAMI submission. arXiv admin note: text overlap with arXiv:1806.10556 

  Access Paper or Ask Questions

Every Pixel Counts: Unsupervised Geometry Learning with Holistic 3D Motion Understanding

Aug 15, 2018
Zhenheng Yang, Peng Wang, Yang Wang, Wei Xu, Ram Nevatia

* ECCV18' submission 

  Access Paper or Ask Questions

CTAP: Complementary Temporal Action Proposal Generation

Jul 18, 2018
Jiyang Gao, Kan Chen, Ram Nevatia

* ECCV 2018 main conference paper (camera ready version). Code is available in http://www.github.com/jiyanggao/CTAP 

  Access Paper or Ask Questions

Revisiting Temporal Modeling for Video-based Person ReID

May 08, 2018
Jiyang Gao, Ram Nevatia

* codes available at https://github.com/jiyanggao/Video-Person-ReID 

  Access Paper or Ask Questions

Motion-Appearance Co-Memory Networks for Video Question Answering

Mar 29, 2018
Jiyang Gao, Runzhou Ge, Kan Chen, Ram Nevatia

* CVPR 2018 

  Access Paper or Ask Questions

LEGO: Learning Edge with Geometry all at Once by Watching Videos

Mar 24, 2018
Zhenheng Yang, Peng Wang, Yang Wang, Wei Xu, Ram Nevatia

* Accepted to CVPR 2018 as spotlight; Camera ready plus supplementary material. Code will come 

  Access Paper or Ask Questions

Knowledge Aided Consistency for Weakly Supervised Phrase Grounding

Mar 11, 2018
Kan Chen, Jiyang Gao, Ram Nevatia

* CVPR 2018 conference paper 

  Access Paper or Ask Questions

ExpNet: Landmark-Free, Deep, 3D Facial Expressions

Feb 02, 2018
Feng-Ju Chang, Anh Tuan Tran, Tal Hassner, Iacopo Masi, Ram Nevatia, Gerard Medioni

* Accepted to the IEEE International Conference on Automatic Face and Gesture Recognition, 2018 

  Access Paper or Ask Questions

Knowledge Concentration: Learning 100K Object Classifiers in a Single CNN

Nov 23, 2017
Jiyang Gao, Zijian, Guo, Zhen Li, Ram Nevatia


  Access Paper or Ask Questions

FacePoseNet: Making a Case for Landmark-Free Face Alignment

Aug 31, 2017
Fengju Chang, Anh Tuan Tran, Tal Hassner, Iacopo Masi, Ram Nevatia, Gerard Medioni


  Access Paper or Ask Questions

Query-guided Regression Network with Context Policy for Phrase Grounding

Aug 04, 2017
Kan Chen, Rama Kovvuri, Ram Nevatia

* Spotlight in ICCV 2017 

  Access Paper or Ask Questions

TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals

Aug 04, 2017
Jiyang Gao, Zhenheng Yang, Chen Sun, Kan Chen, Ram Nevatia

* ICCV 2017 camera ready 

  Access Paper or Ask Questions

TALL: Temporal Activity Localization via Language Query

Aug 03, 2017
Jiyang Gao, Chen Sun, Zhenheng Yang, Ram Nevatia

* ICCV 2017 camera ready (with supplemental material) 

  Access Paper or Ask Questions

Spatio-Temporal Action Detection with Cascade Proposal and Location Anticipation

Jul 31, 2017
Zhenheng Yang, Jiyang Gao, Ram Nevatia

* Accepted at BMVC 2017 (oral) 

  Access Paper or Ask Questions

RED: Reinforced Encoder-Decoder Networks for Action Anticipation

Jul 16, 2017
Jiyang Gao, Zhenheng Yang, Ram Nevatia


  Access Paper or Ask Questions

Cascaded Boundary Regression for Temporal Action Detection

May 02, 2017
Jiyang Gao, Zhenheng Yang, Ram Nevatia


  Access Paper or Ask Questions

AMC: Attention guided Multi-modal Correlation Learning for Image Search

Apr 03, 2017
Kan Chen, Trung Bui, Fang Chen, Zhaowen Wang, Ram Nevatia

* CVPR 2017 

  Access Paper or Ask Questions

A Multi-Scale Cascade Fully Convolutional Network Face Detector

Sep 12, 2016
Zhenheng Yang, Ram Nevatia

* Accepted to ICPR 16' 

  Access Paper or Ask Questions

Learning Action Concept Trees and Semantic Alignment Networks from Image-Description Data

Sep 08, 2016
Jiyang Gao, Ram Nevatia

* 16 pages, 5 figures 

  Access Paper or Ask Questions