activity
20122022
most citedSigNet: Convolutional Siamese Network for Writer Independent Offline Signature Verification

179 citations · 326 across the 13 of their papers we have counts for

collaborators
Showing cs.CVShow all

15 papers · 1 filter

cs.CV20223 cited

Cross-Modal Fusion Distillation for Fine-Grained Sketch-Based Image Retrieval

Abhra Chaudhuri, Massimiliano Mancini, Yanbei Chen +2

Representation learning for sketch-based image retrieval has mostly been tackled by learning embeddings that discard modality-specific information. As instances from different moda…

cs.CV20222 cited

Relational Proxies: Emergent Relationships as Fine-Grained Discriminators

Abhra Chaudhuri, Massimiliano Mancini, Zeynep Akata +1

Fine-grained categories that largely share the same set of parts cannot be discriminated based on part information alone, as they mostly differ in the way the local parts relate to…

cs.CV2022

BDA-SketRet: Bi-Level Domain Adaptation for Zero-Shot SBIR

Ushasi Chaudhuri, Ruchika Chavan, Biplab Banerjee +2

The efficacy of zero-shot sketch-based image retrieval (ZS-SBIR) models is governed by two challenges. The immense distributions-gap between the sketches and the images requires a…

cs.CV2021

Implicit and Explicit Attention for Zero-Shot Learning

Faisal Alamri, Anjan Dutta

Most of the existing Zero-Shot Learning (ZSL) methods focus on learning a compatibility function between the image representation and class attributes. Few others concentrate on le…

cs.CV2021

Concurrent Discrimination and Alignment for Self-Supervised Feature Learning

Anjan Dutta, Massimiliano Mancini, Zeynep Akata

Existing self-supervised learning methods learn representation by means of pretext tasks which are either (1) discriminating that explicitly specify which features should be separa…

cs.CV202123 cited

Multi-Head Self-Attention via Vision Transformer for Zero-Shot Learning

Faisal Alamri, Anjan Dutta

Zero-Shot Learning (ZSL) aims to recognise unseen object classes, which are not observed during the training phase. The existing body of works on ZSL mostly relies on pretrained vi…