activity
20172021
most citedDynamic Distillation Network for Cross-Domain Few-Shot Recognition with Unlabeled Data

10 citations · 12 across the 5 of their papers we have counts for

collaborators

10 papers

cs.CV202110 cited

Dynamic Distillation Network for Cross-Domain Few-Shot Recognition with Unlabeled Data

Ashraful Islam, Chun-Fu Chen, Rameswar Panda +3

Most existing works in few-shot learning rely on meta-learning the network on a large base dataset which is typically from the same domain as the target dataset. We tackle the prob…

cs.CV2021

A Broad Study on the Transferability of Visual Representations with Contrastive Learning

Ashraful Islam, Chun-Fu Chen, Rameswar Panda +3

Tremendous progress has been made in visual representation learning, notably with the recent success of self-supervised contrastive learning methods. Supervised contrastive learnin…

cs.CV2021

A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action Localization

Ashraful Islam, Chengjiang Long, Richard Radke

Weakly supervised temporal action localization is a challenging vision task due to the absence of ground-truth temporal locations of actions in the training videos. With only video…

cs.CV2020

Towards Visually Explaining Similarity Models

Meng Zheng, Srikrishna Karanam, Terrence Chen +2

We consider the problem of visually explaining similarity models, i.e., explaining why a model predicts two images to be similar in addition to producing a scalar score. While much…

cs.CV2020

Weakly Supervised Temporal Action Localization Using Deep Metric Learning

Ashraful Islam, Richard J. Radke

Temporal action localization is an important step towards video understanding. Most current action localization methods depend on untrimmed videos with full temporal annotations of…

cs.CV2019

Multi-person Spatial Interaction in a Large Immersive Display Using Smartphones as Touchpads

Gyanendra Sharma, Richard J Radke

In this paper, we present a multi-user interaction interface for a large immersive space that supports simultaneous screen interactions by combining (1) user input via personal sma…