Search Results for author: Sanath Narayan

Found 11 papers, 7 papers with code

Discriminative Region-based Multi-Label Zero-Shot Learning

1 code implementation20 Aug 2021 Sanath Narayan, Akshita Gupta, Salman Khan, Fahad Shahbaz Khan, Ling Shao, Mubarak Shah

We note that the best existing multi-label ZSL method takes a shared approach towards attending to region features with a common set of attention maps for all the classes.

Image Retrieval Multi-label zero-shot learning

Structured Latent Embeddings for Recognizing Unseen Classes in Unseen Domains

no code implementations12 Jul 2021 Shivam Chandhok, Sanath Narayan, Hisham Cholakkal, Rao Muhammad Anwer, Vineeth N Balasubramanian, Fahad Shahbaz Khan, Ling Shao

The need to address the scarcity of task-specific annotated data has resulted in concerted efforts in recent years for specific settings such as zero-shot learning (ZSL) and domain generalization (DG), to separately address the issues of semantic shift and domain shift, respectively.

Domain Generalization Zero-Shot Learning

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

1 code implementation ICCV 2019 Sanath Narayan, Hisham Cholakkal, Fahad Shahbaz Khan, Ling Shao

Our joint formulation has three terms: a classification term to ensure the separability of learned action features, an adapted multi-label center loss term to enhance the action feature discriminability and a counting loss term to delineate adjacent action sequences, leading to improved localization.

Action Classification Weakly Supervised Action Localization +2

A Large Dataset for Improving Patch Matching

1 code implementation4 Jan 2018 Rahul Mitra, Nehal Doiphode, Utkarsh Gautam, Sanath Narayan, Shuaib Ahmed, Sharat Chandran, Arjun Jain

Similarly on the Strecha dataset, we see an improvement of 3-5% for the matching task in non-planar scenes.

Patch Matching

Improved Descriptors for Patch Matching and Reconstruction

no code implementations24 Jan 2017 Rahul Mitra, Jiakai Zhang, Sanath Narayan, Shuaib Ahmed, Sharat Chandran, Arjun Jain

Scenes from the Oxford ACRD, MVS and Synthetic datasets are used for evaluating the patch matching performance of the learnt descriptors while the Strecha dataset is used to evaluate the 3D reconstruction task.

3D Reconstruction Patch Matching

Hyper-Fisher Vectors for Action Recognition

no code implementations28 Sep 2015 Sanath Narayan, Kalpathi R. Ramakrishnan

We also perform experiments to show that the performance of the Hyper-Fisher Vector is robust to the dictionary size of the BoW encoding.

Action Recognition

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