Search Results for author: Anjan Dutta

Found 24 papers, 14 papers with code

Learning Conditional Invariances through Non-Commutativity

1 code implementation18 Feb 2024 Abhra Chaudhuri, Serban Georgescu, Anjan Dutta

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.

Domain Adaptation

CLIPDrawX: Primitive-based Explanations for Text Guided Sketch Synthesis

no code implementations4 Dec 2023 Nityanand Mathur, Shyam Marjit, Abhra Chaudhuri, Anjan Dutta

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 circles and straight lines.

Sarcasm in Sight and Sound: Benchmarking and Expansion to Improve Multimodal Sarcasm Detection

no code implementations29 Sep 2023 Swapnil Bhosale, Abhra Chaudhuri, Alex Lee Robert Williams, Divyank Tiwari, Anjan Dutta, Xiatian Zhu, Pushpak Bhattacharyya, Diptesh Kanojia

The introduction of the MUStARD dataset, and its emotion recognition extension MUStARD++, have identified sarcasm to be a multi-modal phenomenon -- expressed not only in natural language text, but also through manners of speech (like tonality and intonation) and visual cues (facial expression).

Benchmarking Emotion Recognition +1

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

1 code implementation20 Jul 2023 Anindya Mondal, Sauradip Nag, Joaquin M Prada, Xiatian Zhu, Anjan Dutta

Existing action recognition methods are typically actor-specific due to the intrinsic topological and apparent differences among the actors.

Action Classification Action Recognition In Videos +3

Data-Free Sketch-Based Image Retrieval

1 code implementation CVPR 2023 Abhra Chaudhuri, Ayan Kumar Bhunia, Yi-Zhe Song, Anjan Dutta

For the first time, we identify that for data-scarce tasks like Sketch-Based Image Retrieval (SBIR), where the difficulty in acquiring paired photos and hand-drawn sketches limits data-dependent cross-modal learning algorithms, DFL can prove to be a much more practical paradigm.

Retrieval Sketch-Based Image Retrieval

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

1 code implementation19 Oct 2022 Abhra Chaudhuri, Massimiliano Mancini, Yanbei Chen, Zeynep Akata, Anjan Dutta

Representation learning for sketch-based image retrieval has mostly been tackled by learning embeddings that discard modality-specific information.

Cross-Modal Retrieval Knowledge Distillation +3

Relational Proxies: Emergent Relationships as Fine-Grained Discriminators

1 code implementation5 Oct 2022 Abhra Chaudhuri, Massimiliano Mancini, Zeynep Akata, Anjan Dutta

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.

Abstracting Sketches through Simple Primitives

1 code implementation27 Jul 2022 Stephan Alaniz, Massimiliano Mancini, Anjan Dutta, Diego Marcos, Zeynep Akata

Toward equipping machines with such capabilities, we propose the Primitive-based Sketch Abstraction task where the goal is to represent sketches using a fixed set of drawing primitives under the influence of a budget.

Retrieval Sketch-Based Image Retrieval +1

Implicit and Explicit Attention for Zero-Shot Learning

1 code implementation2 Oct 2021 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.

Zero-Shot Learning

Concurrent Discrimination and Alignment for Self-Supervised Feature Learning

no code implementations19 Aug 2021 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 separated or (2) aligning that precisely indicate which features should be closed together, but ignore the fact how to jointly and principally define which features to be repelled and which ones to be attracted.

Self-Supervised Learning Semantic Segmentation +1

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

1 code implementation30 Jul 2021 Faisal Alamri, Anjan Dutta

Zero-Shot Learning (ZSL) aims to recognise unseen object classes, which are not observed during the training phase.

Attribute Zero-Shot Learning

Bookworm continual learning: beyond zero-shot learning and continual learning

no code implementations26 Jun 2020 Kai Wang, Luis Herranz, Anjan Dutta, Joost Van de Weijer

We propose bookworm continual learning(BCL), a flexible setting where unseen classes can be inferred via a semantic model, and the visual model can be updated continually.

Attribute Continual Learning +1

Semantically Tied Paired Cycle Consistency for Any-Shot Sketch-based Image Retrieval

no code implementations20 Jun 2020 Anjan Dutta, Zeynep Akata

Low-shot sketch-based image retrieval is an emerging task in computer vision, allowing to retrieve natural images relevant to hand-drawn sketch queries that are rarely seen during the training phase.

Generative Adversarial Network Retrieval +1

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

1 code implementation CVPR 2019 Sounak Dey, Pau Riba, Anjan Dutta, Josep Llados, Yi-Zhe Song

Highly abstract amateur human sketches are purposefully sourced to maximize the domain gap, instead of ones included in existing datasets that can often be semi-photorealistic.

Retrieval Sketch-Based Image Retrieval

Semantically Tied Paired Cycle Consistency for Zero-Shot Sketch-based Image Retrieval

1 code implementation CVPR 2019 Anjan Dutta, Zeynep Akata

Existing works either require aligned sketch-image pairs or inefficient memory fusion layer for mapping the visual information to a semantic space.

feature selection Retrieval +1

Hierarchical stochastic graphlet embedding for graph-based pattern recognition

1 code implementation8 Jul 2018 Anjan Dutta, Pau Riba, Josep Lladós, Alicia Fornés

Graph embedding, which maps graphs to a vectorial space, has been proposed as a way to tackle these difficulties enabling the use of standard machine learning techniques.

BIG-bench Machine Learning Clustering +1

Learning Cross-Modal Deep Embeddings for Multi-Object Image Retrieval using Text and Sketch

no code implementations28 Apr 2018 Sounak Dey, Anjan Dutta, Suman K. Ghosh, Ernest Valveny, Josep Lladós, Umapada Pal

In this work we introduce a cross modal image retrieval system that allows both text and sketch as input modalities for the query.

Image Retrieval Retrieval

Graph Kernels based on High Order Graphlet Parsing and Hashing

no code implementations28 Feb 2018 Anjan Dutta, Hichem Sahbi

In order to build our graph representation, we measure the distribution of these graphlets into a given graph, using particular hash functions that efficiently assign sampled graphlets into isomorphic sets with a very low probability of collision.

BIG-bench Machine Learning Vocal Bursts Intensity Prediction

Product Graph-based Higher Order Contextual Similarities for Inexact Subgraph Matching

no code implementations1 Feb 2017 Anjan Dutta, Josep Lladós, Horst Bunke, Umapada Pal

Many algorithms formulate graph matching as an optimization of an objective function of pairwise quantification of nodes and edges of two graphs to be matched.

Graph Matching

Stochastic Graphlet Embedding

1 code implementation1 Feb 2017 Anjan Dutta, Hichem Sahbi

In order to build our graph representation, we measure the distribution of these graphlets into a given graph, using particular hash functions that efficiently assign sampled graphlets into isomorphic sets with a very low probability of collision.

BIG-bench Machine Learning

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