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

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Hisham Cholakkal

Hisham Cholakkal

equal contribution

Structured Latent Embeddings for Recognizing Unseen Classes in Unseen Domains


Jul 12, 2021
Shivam Chandhok, Sanath Narayan, Hisham Cholakkal, Rao Muhammad Anwer, Vineeth N Balasubramanian, Fahad Shahbaz Khan, Ling Shao

Figure 1 for Structured Latent Embeddings for Recognizing Unseen Classes in Unseen Domains
Figure 2 for Structured Latent Embeddings for Recognizing Unseen Classes in Unseen Domains
Figure 3 for Structured Latent Embeddings for Recognizing Unseen Classes in Unseen Domains
Figure 4 for Structured Latent Embeddings for Recognizing Unseen Classes in Unseen Domains

  Access Paper or Ask Questions

Handwriting Transformers


Apr 08, 2021
Ankan Kumar Bhunia, Salman Khan, Hisham Cholakkal, Rao Muhammad Anwer, Fahad Shahbaz Khan, Mubarak Shah

Figure 1 for Handwriting Transformers
Figure 2 for Handwriting Transformers
Figure 3 for Handwriting Transformers
Figure 4 for Handwriting Transformers

  Access Paper or Ask Questions

D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations


Dec 11, 2020
Sanath Narayan, Hisham Cholakkal, Munawar Hayat, Fahad Shahbaz Khan, Ming-Hsuan Yang, Ling Shao

Figure 1 for D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations
Figure 2 for D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations
Figure 3 for D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations
Figure 4 for D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations

  Access Paper or Ask Questions

SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation


Jul 29, 2020
Jiale Cao, Rao Muhammad Anwer, Hisham Cholakkal, Fahad Shahbaz Khan, Yanwei Pang, Ling Shao

Figure 1 for SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation
Figure 2 for SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation
Figure 3 for SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation
Figure 4 for SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation
* ECCV2020; Code: https://github.com/JialeCao001/SipMask 
  Access Paper or Ask Questions

PSC-Net: Learning Part Spatial Co-occurence for Occluded Pedestrian Detection


Jan 25, 2020
Jin Xie, Yanwei Pang, Hisham Cholakkal, Rao Muhammad Anwer, Fahad Shahbaz Khan, Ling Shao

Figure 1 for PSC-Net: Learning Part Spatial Co-occurence for Occluded Pedestrian Detection
Figure 2 for PSC-Net: Learning Part Spatial Co-occurence for Occluded Pedestrian Detection
Figure 3 for PSC-Net: Learning Part Spatial Co-occurence for Occluded Pedestrian Detection
Figure 4 for PSC-Net: Learning Part Spatial Co-occurence for Occluded Pedestrian Detection

  Access Paper or Ask Questions

Fine-grained Recognition: Accounting for Subtle Differences between Similar Classes


Dec 14, 2019
Guolei Sun, Hisham Cholakkal, Salman Khan, Fahad Shahbaz Khan, Ling Shao

Figure 1 for Fine-grained Recognition: Accounting for Subtle Differences between Similar Classes
Figure 2 for Fine-grained Recognition: Accounting for Subtle Differences between Similar Classes
Figure 3 for Fine-grained Recognition: Accounting for Subtle Differences between Similar Classes
Figure 4 for Fine-grained Recognition: Accounting for Subtle Differences between Similar Classes
* To appear in AAAI 2020 
  Access Paper or Ask Questions

Towards Partial Supervision for Generic Object Counting in Natural Scenes


Dec 13, 2019
Hisham Cholakkal, Guolei Sun, Salman Khan, Fahad Shahbaz Khan, Ling Shao, Luc Van Gool

Figure 1 for Towards Partial Supervision for Generic Object Counting in Natural Scenes
Figure 2 for Towards Partial Supervision for Generic Object Counting in Natural Scenes
Figure 3 for Towards Partial Supervision for Generic Object Counting in Natural Scenes
Figure 4 for Towards Partial Supervision for Generic Object Counting in Natural Scenes
* First two authors contributed equally. This work is a journal extension (TPAMI submission) of our CVPR 2019 paper arXiv:1903.02494 
  Access Paper or Ask Questions

3C-Net: Category Count and Center Loss for Weakly-Supervised Action Localization


Aug 22, 2019
Sanath Narayan, Hisham Cholakkal, Fahad Shabaz Khan, Ling Shao

Figure 1 for 3C-Net: Category Count and Center Loss for Weakly-Supervised Action Localization
Figure 2 for 3C-Net: Category Count and Center Loss for Weakly-Supervised Action Localization
Figure 3 for 3C-Net: Category Count and Center Loss for Weakly-Supervised Action Localization
Figure 4 for 3C-Net: Category Count and Center Loss for Weakly-Supervised Action Localization
* To appear in ICCV 2019 
  Access Paper or Ask Questions

Object Counting and Instance Segmentation with Image-level Supervision


Mar 06, 2019
Hisham Cholakkal, Guolei Sun, Fahad Shahbaz Khan, Ling Shao

Figure 1 for Object Counting and Instance Segmentation with Image-level Supervision
Figure 2 for Object Counting and Instance Segmentation with Image-level Supervision
Figure 3 for Object Counting and Instance Segmentation with Image-level Supervision
Figure 4 for Object Counting and Instance Segmentation with Image-level Supervision
* To appear in CVPR 2019 
  Access Paper or Ask Questions

Backtracking Spatial Pyramid Pooling (SPP)-based Image Classifier for Weakly Supervised Top-down Salient Object Detection


Aug 14, 2018
Hisham Cholakkal, Jubin Johnson, Deepu Rajan

Figure 1 for Backtracking Spatial Pyramid Pooling (SPP)-based Image Classifier for Weakly Supervised Top-down Salient Object Detection
Figure 2 for Backtracking Spatial Pyramid Pooling (SPP)-based Image Classifier for Weakly Supervised Top-down Salient Object Detection
Figure 3 for Backtracking Spatial Pyramid Pooling (SPP)-based Image Classifier for Weakly Supervised Top-down Salient Object Detection
Figure 4 for Backtracking Spatial Pyramid Pooling (SPP)-based Image Classifier for Weakly Supervised Top-down Salient Object Detection
* H. Cholakkal, J. Johnson, D. Rajan, "Backtracking Spatial Pyramid Pooling (SPP)-based Image Classifier for Weakly Supervised Top-down Salient Object Detection", in IEEE Transactions on Image processing, August 2018 
 * 14 pages, 7 figures 
  Access Paper or Ask Questions

L1-regularized Reconstruction Error as Alpha Matte


Feb 09, 2017
Jubin Johnson, Hisham Cholakkal, Deepu Rajan

Figure 1 for L1-regularized Reconstruction Error as Alpha Matte
Figure 2 for L1-regularized Reconstruction Error as Alpha Matte
Figure 3 for L1-regularized Reconstruction Error as Alpha Matte
Figure 4 for L1-regularized Reconstruction Error as Alpha Matte
* 5 pages, 5 figure, Accepted in IEEE Signal Processing Letters 
  Access Paper or Ask Questions

A Classifier-guided Approach for Top-down Salient Object Detection


Apr 22, 2016
Hisham Cholakkal, Jubin Johnson, Deepu Rajan

* To appear in Signal Processing: Image Communication, Elsevier. Available online from April 2016 
  Access Paper or Ask Questions

Sparse Coding for Alpha Matting


Apr 11, 2016
Jubin Johnson, Ehsan Shahrian Varnousfaderani, Hisham Cholakkal, Deepu Rajan

Figure 1 for Sparse Coding for Alpha Matting
Figure 2 for Sparse Coding for Alpha Matting
Figure 3 for Sparse Coding for Alpha Matting
Figure 4 for Sparse Coding for Alpha Matting
* To appear in IEEE Transactions on Image Processing 
  Access Paper or Ask Questions