Explanipedia

Copy‐Paste Augmentation Improves Automatic Species Identification in Camera Trap Images Open

Cédric Mesnage, Anne Corbett, Jake Curry, Sareh Rowlands, Anjan Dutta , et al. · 2025

Effective conservation requires effective biodiversity monitoring. The pace of global biodiversity change far outstrips the ability of manual fieldwork to monitor it. Therefore, technological solutions, like camera traps, have emerged as a…

DreamPet: Text Driven Controllable 3D Animal Generation using Gaussian Splatting Open

Vysakh Ramakrishnan, Sauradip Nag, Amal Dev Parakkat, Xiatian Zhu, Anjan Dutta · 2025

Realistic 3D animal generation from text prompts is a significant yet challenging task. Traditional approaches, which use score distillation sampling to optimize 3D formats like meshes or neural fields, often suffer from a lack of detail a…

A Closer Look at Multimodal Representation Collapse Open

Abhra Chaudhuri, Anjan Dutta, Tu Bui, S Georgescu · 2025

We aim to develop a fundamental understanding of modality collapse, a recently observed empirical phenomenon wherein models trained for multimodal fusion tend to rely only on a subset of the modalities, ignoring the rest. We show that moda…

Skin Disease Detector using CNN Open

Apoorv Ranjan, Anjan Dutta, Jabbar Salman Hussain, Aryaan Ved -, Vinod Kumar · 2025

Skin conditions are common and frequently need for a quick and precise diagnosis in order to be treated. In this paper, we propose a Convolutional Neural Network (CNN) based skin disease detection system. CNNs are ideally suited for the id…

OmniCount: Multi-label Object Counting with Semantic-Geometric Priors Open

Anindya Mondal, Sauradip Nag, Xiatian Zhu, Anjan Dutta · 2025

Object counting is pivotal for understanding the composition of scenes. Previously, this task was dominated by class-specific methods, which have gradually evolved into more adaptable class-agnostic strategies. However, these strategies co…

Copy-paste augmentation improves automatic species identification in camera trap images Open

Cédric Mesnage, Anne Corbett, Jake Curry, Sareh Rowlands, Anjan Dutta , et al. · 2024

1. Effective conservation requires effective biodiversity monitoring. The pace of global biodiversity change far outstrips the ability of manual fieldwork to monitor it. Therefore, technological solutions, like camera traps, have emerged a…

CraftSVG: Multi-Object Text-to-SVG Synthesis via Layout Guided Diffusion Open

Ayan Banerjee, Nityanand Mathur, Josep Lladós, Umapada Pal, Anjan Dutta · 2024

Generating VectorArt from text prompts is a challenging vision task, requiring diverse yet realistic depictions of the seen as well as unseen entities. However, existing research has been mostly limited to the generation of single objects,…

OmniCount: Multi-label Object Counting with Semantic-Geometric Priors Open

Anindya Mondal, Sauradip Nag, Xiatian Zhu, Anjan Dutta · 2024

Object counting is pivotal for understanding the composition of scenes. Previously, this task was dominated by class-specific methods, which have gradually evolved into more adaptable class-agnostic strategies. However, these strategies co…

Learning Conditional Invariances through Non-Commutativity Open

Abhra Chaudhuri, S Georgescu, Anjan Dutta · 2024

Invariance learning algorithms that conditionally filter out domain-specific random variables as distractors, do so based only on the data semantics, and not the target domain under evaluation. We show that a provably optimal and sample-ef…

CLIPDraw++: Text-to-Sketch Synthesis with Simple Primitives Open

Nityanand Mathur, Shyam Marjit, Abhra Chaudhuri, Anjan Dutta · 2023

With the goal of understanding the visual concepts that CLIP associates with text prompts, we show that the latent space of CLIP can be visualized solely in terms of linear transformations on simple geometric primitives like straight lines…

Transitivity Recovering Decompositions: Interpretable and Robust Fine-Grained Relationships Open

Abhra Chaudhuri, Massimiliano Mancini, Zeynep Akata, Anjan Dutta · 2023

Recent advances in fine-grained representation learning leverage local-to-global (emergent) relationships for achieving state-of-the-art results. The relational representations relied upon by such methods, however, are abstract. We aim to …

In-shop Clothes Retrieval Open

Anjan Dutta · 2023

In-shop Clothes Retrieval

In-shop Clothes Retrieval Open

Anjan Dutta · 2023

In-shop Clothes Retrieval

Actor-agnostic Multi-label Action Recognition with Multi-modal Query Open

Anindya Mondal, Sauradip Nag, Joaquín M. Prada, Xiatian Zhu, Anjan Dutta · 2023

Existing action recognition methods are typically actor-specific due to the intrinsic topological and apparent differences among the actors. This requires actor-specific pose estimation (e.g., humans vs. animals), leading to cumbersome mod…

Animal Kingdom AR Open

Anjan Dutta · 2023

Animal Kingdom

Animal Kingdom AR Open

Anjan Dutta · 2023

Animal Kingdom

Torque reversal and cyclotron absorption feature in HMXB 4U 1538-522 Open

Prince Sharma, Chetana Jain, Anjan Dutta · 2023

We present a comprehensive timing and spectral analysis of the HMXB 4U 1538-522 by using the Nuclear Spectroscopic Telescope Array (NuSTAR) observatory data. Using three archived observations made between 2019 and 2021, we have detected $\…

Data-Free Sketch-Based Image Retrieval Open

Abhra Chaudhuri, Ayan Kumar Bhunia, Yi-Zhe Song, Anjan Dutta · 2023

Rising concerns about privacy and anonymity preservation of deep learning models have facilitated research in data-free learning (DFL). For the first time, we identify that for data-scarce tasks like Sketch-Based Image Retrieval (SBIR), wh…

Places2_simp Open

Anjan Dutta · 2023

Simplified version of Places2 dataset.

Places2_simp Open

Anjan Dutta · 2023

Simplified version of Places2 dataset.

HMDB_simp Open

Anjan Dutta · 2023

SImplified version of HMDB51 dataset

HMDB_simp Open

Anjan Dutta · 2023

SImplified version of HMDB51 dataset

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

Abhra Chaudhuri, Massimiliano Mancini, Yanbei Chen, Zeynep Akata, Anjan Dutta · 2022

Representation learning for sketch-based image retrieval has mostly been tackled by learning embeddings that discard modality-specific information. As instances from different modalities can often provide complementary information describi…

Relational Proxies: Emergent Relationships as Fine-Grained Discriminators Open

Abhra Chaudhuri, Massimiliano Mancini, Zeynep Akata, Anjan Dutta · 2022

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 the overall global structure of the object. We propose Rel…

Abstracting Sketches through Simple Primitives Open

Stephan Alaniz, Massimiliano Mancini, Anjan Dutta, Diego Marcos, Zeynep Akata · 2022

Humans show high-level of abstraction capabilities in games that require quickly communicating object information. They decompose the message content into multiple parts and communicate them in an interpretable protocol. Toward equipping m…

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

Ushasi Chaudhuri, Ruchika Chavan, Biplab Banerjee, Anjan Dutta, Zeynep Akata · 2022

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 proper domain alignment. Moreover, the fine-grained nature …

Abstracting Sketches Through Simple Primitives Open

Stephan Alaniz, Massimiliano Mancini, Anjan Dutta, Diego Marcos, Zeynep Akata · 2022

Concurrent Discrimination and Alignment for Self-Supervised Feature Learning Open

Anjan Dutta, Massimiliano Mancini, Zeynep Akata · 2021

Existing self-supervised learning methods learn representation by means of pretext tasks which are either (1) discriminating that explicitly specify which features should be separated or (2) aligning that precisely indicate which features …

Concurrent Discrimination and Alignment for Self-Supervised Feature\n Learning Open

Anjan Dutta, Massimiliano Mancini, Zeynep Akata · 2021

Existing self-supervised learning methods learn representation by means of\npretext tasks which are either (1) discriminating that explicitly specify which\nfeatures should be separated or (2) aligning that precisely indicate which\nfeatur…

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

Faisal Alamri, Anjan Dutta · 2021

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 visual features and lacks the explicit attribute localisation…

Anjan Dutta YOU? Author Swipe