activity
20162021
most citedSigNet: Convolutional Siamese Network for Writer Independent Offline Signature Verification

179 citations · 182 across the 4 of their papers we have counts for

collaborators
Showing cs.CVShow all

10 papers · 1 filter

cs.CV20213 cited

Localizing Infinity-shaped fishes: Sketch-guided object localization in the wild

Pau Riba, Sounak Dey, Ali Furkan Biten +1

This work investigates the problem of sketch-guided object localization (SGOL), where human sketches are used as queries to conduct the object localization in natural images. In th…

cs.CV2021

One-shot Compositional Data Generation for Low Resource Handwritten Text Recognition

Mohamed Ali Souibgui, Ali Furkan Biten, Sounak Dey +5

Low resource Handwritten Text Recognition (HTR) is a hard problem due to the scarce annotated data and the very limited linguistic information (dictionaries and language models). F…

cs.CV2020

Multi-Modal Reasoning Graph for Scene-Text Based Fine-Grained Image Classification and Retrieval

Andres Mafla, Sounak Dey, Ali Furkan Biten +2

Scene text instances found in natural images carry explicit semantic information that can provide important cues to solve a wide array of computer vision problems. In this paper, w…

cs.CV2020

Fine-grained Image Classification and Retrieval by Combining Visual and Locally Pooled Textual Features

Andres Mafla, Sounak Dey, Ali Furkan Biten +2

Text contained in an image carries high-level semantics that can be exploited to achieve richer image understanding. In particular, the mere presence of text provides strong guidin…

cs.CV2019

Doodle to Search: Practical Zero-Shot Sketch-based Image Retrieval

Sounak Dey, Pau Riba, Anjan Dutta +2

In this paper, we investigate the problem of zero-shot sketch-based image retrieval (ZS-SBIR), where human sketches are used as queries to conduct retrieval of photos from unseen c…

cs.CV2018

Non-deterministic Behavior of Ranking-based Metrics when Evaluating Embeddings

Anguelos Nicolaou, Sounak Dey, Vincent Christlein +2

Embedding data into vector spaces is a very popular strategy of pattern recognition methods. When distances between embeddings are quantized, performance metrics become ambiguous.…