arXiv subjects

Ajay Divakaran

Publications and source records attributed to Ajay Divakaran.

48 records · Page 3Linked to original sources

arXiv2019

Integrating Text and Image: Determining Multimodal Document Intent in Instagram Posts

Computing author intent from multimodal data like Instagram posts requires modeling a complex relationship between text and image. For example, a caption might evoke an ironic contrast with the image, so neither caption nor image is a mere transcript of the other. Instead they combine -- via what has been called meaning multiplication -- to create a new meaning that has a more complex relation to the literal meanings of text and image. Here we introduce a multimodal dataset of 1299 Instagram posts labeled for three orthogonal taxonomies: the authorial intent behind the image-caption pair, the contextual relationship between the literal meanings of the image and caption, and the semiotic relationship between the signified meanings of the image and caption. We build a baseline deep multimodal classifier to validate the taxonomy, showing that employing both text and image improves intent detection by 9.6% compared to using only the image modality, demonstrating the commonality of non-intersective meaning multiplication. The gain with multimodality is greatest when the image and caption diverge semiotically. Our dataset offers a new resource for the study of the rich meanings that result from pairing text and image.

cs.CV↗

arXiv2019

Align2Ground: Weakly Supervised Phrase Grounding Guided by Image-Caption Alignment

We address the problem of grounding free-form textual phrases by using weak supervision from image-caption pairs. We propose a novel end-to-end model that uses caption-to-image retrieval as a `downstream' task to guide the process of phrase localization. Our method, as a first step, infers the latent correspondences between regions-of-interest (RoIs) and phrases in the caption and creates a discriminative image representation using these matched RoIs. In a subsequent step, this (learned) representation is aligned with the caption. Our key contribution lies in building this `caption-conditioned' image encoding which tightly couples both the tasks and allows the weak supervision to effectively guide visual grounding. We provide an extensive empirical and qualitative analysis to investigate the different components of our proposed model and compare it with competitive baselines. For phrase localization, we report an improvement of 4.9% (absolute) over the prior state-of-the-art on the VisualGenome dataset. We also report results that are at par with the state-of-the-art on the downstream caption-to-image retrieval task on COCO and Flickr30k datasets.

cs.CV↗

arXiv2019

Can You Explain That? Lucid Explanations Help Human-AI Collaborative Image Retrieval

While there have been many proposals on making AI algorithms explainable, few have attempted to evaluate the impact of AI-generated explanations on human performance in conducting human-AI collaborative tasks. To bridge the gap, we propose a Twenty-Questions style collaborative image retrieval game, Explanation-assisted Guess Which (ExAG), as a method of evaluating the efficacy of explanations (visual evidence or textual justification) in the context of Visual Question Answering (VQA). In our proposed ExAG, a human user needs to guess a secret image picked by the VQA agent by asking natural language questions to it. We show that overall, when AI explains its answers, users succeed more often in guessing the secret image correctly. Notably, a few correct explanations can readily improve human performance when VQA answers are mostly incorrect as compared to no-explanation games. Furthermore, we also show that while explanations rated as "helpful" significantly improve human performance, "incorrect" and "unhelpful" explanations can degrade performance as compared to no-explanation games. Our experiments, therefore, demonstrate that ExAG is an effective means to evaluate the efficacy of AI-generated explanations on a human-AI collaborative task.

cs.CY↗

arXiv2019

Sunny and Dark Outside?! Improving Answer Consistency in VQA through Entailed Question Generation

While models for Visual Question Answering (VQA) have steadily improved over the years, interacting with one quickly reveals that these models lack consistency. For instance, if a model answers "red" to "What color is the balloon?", it might answer "no" if asked, "Is the balloon red?". These responses violate simple notions of entailment and raise questions about how effectively VQA models ground language. In this work, we introduce a dataset, ConVQA, and metrics that enable quantitative evaluation of consistency in VQA. For a given observable fact in an image (e.g. the balloon's color), we generate a set of logically consistent question-answer (QA) pairs (e.g. Is the balloon red?) and also collect a human-annotated set of common-sense based consistent QA pairs (e.g. Is the balloon the same color as tomato sauce?). Further, we propose a consistency-improving data augmentation module, a Consistency Teacher Module (CTM). CTM automatically generates entailed (or similar-intent) questions for a source QA pair and fine-tunes the VQA model if the VQA's answer to the entailed question is consistent with the source QA pair. We demonstrate that our CTM-based training improves the consistency of VQA models on the ConVQA datasets and is a strong baseline for further research.

cs.CV↗

arXiv2019

FoodX-251: A Dataset for Fine-grained Food Classification

Food classification is a challenging problem due to the large number of categories, high visual similarity between different foods, as well as the lack of datasets for training state-of-the-art deep models. Solving this problem will require advances in both computer vision models as well as datasets for evaluating these models. In this paper we focus on the second aspect and introduce FoodX-251, a dataset of 251 fine-grained food categories with 158k images collected from the web. We use 118k images as a training set and provide human verified labels for 40k images that can be used for validation and testing. In this work, we outline the procedure of creating this dataset and provide relevant baselines with deep learning models. The FoodX-251 dataset has been used for organizing iFood-2019 challenge in the Fine-Grained Visual Categorization workshop (FGVC6 at CVPR 2019) and is available for download.

cs.CV↗

arXiv2019

Deep Unified Multimodal Embeddings for Understanding both Content and Users in Social Media Networks

There has been an explosion of multimodal content generated on social media networks in the last few years, which has necessitated a deeper understanding of social media content and user behavior. We present a novel content-independent content-user-reaction model for social multimedia content analysis. Compared to prior works that generally tackle semantic content understanding and user behavior modeling in isolation, we propose a generalized solution to these problems within a unified framework. We embed users, images and text drawn from open social media in a common multimodal geometric space, using a novel loss function designed to cope with distant and disparate modalities, and thereby enable seamless three-way retrieval. Our model not only outperforms unimodal embedding based methods on cross-modal retrieval tasks but also shows improvements stemming from jointly solving the two tasks on Twitter data. We also show that the user embeddings learned within our joint multimodal embedding model are better at predicting user interests compared to those learned with unimodal content on Instagram data. Our framework thus goes beyond the prior practice of using explicit leader-follower link information to establish affiliations by extracting implicit content-centric affiliations from isolated users. We provide qualitative results to show that the user clusters emerging from learned embeddings have consistent semantics and the ability of our model to discover fine-grained semantics from noisy and unstructured data. Our work reveals that social multimodal content is inherently multimodal and possesses a consistent structure because in social networks meaning is created through interactions between users and content.

cs.IR↗

arXiv2019

Stacked Spatio-Temporal Graph Convolutional Networks for Action Segmentation

We propose novel Stacked Spatio-Temporal Graph Convolutional Networks (Stacked-STGCN) for action segmentation, i.e., predicting and localizing a sequence of actions over long videos. We extend the Spatio-Temporal Graph Convolutional Network (STGCN) originally proposed for skeleton-based action recognition to enable nodes with different characteristics (e.g., scene, actor, object, action, etc.), feature descriptors with varied lengths, and arbitrary temporal edge connections to account for large graph deformation commonly associated with complex activities. We further introduce the stacked hourglass architecture to STGCN to leverage the advantages of an encoder-decoder design for improved generalization performance and localization accuracy. We explore various descriptors such as frame-level VGG, segment-level I3D, RCNN-based object, etc. as node descriptors to enable action segmentation based on joint inference over comprehensive contextual information. We show results on CAD120 (which provides pre-computed node features and edge weights for fair performance comparison across algorithms) as well as a more complex real-world activity dataset, Charades. Our Stacked-STGCN in general achieves 4.0% performance improvement over the best reported results in F1 score on CAD120 and 1.3% in mAP on Charades using VGG features.

cs.CV↗

arXiv2019

Data-Efficient Mutual Information Neural Estimator

Measuring Mutual Information (MI) between high-dimensional, continuous, random variables from observed samples has wide theoretical and practical applications. Recent work, MINE (Belghazi et al. 2018), focused on estimating tight variational lower bounds of MI using neural networks, but assumed unlimited supply of samples to prevent overfitting. In real world applications, data is not always available at a surplus. In this work, we focus on improving data efficiency and propose a Data-Efficient MINE Estimator (DEMINE), by developing a relaxed predictive MI lower bound that can be estimated at higher data efficiency by orders of magnitudes. The predictive MI lower bound also enables us to develop a new meta-learning approach using task augmentation, Meta-DEMINE, to improve generalization of the network and further boost estimation accuracy empirically. With improved data-efficiency, our estimators enables statistical testing of dependency at practical dataset sizes. We demonstrate the effectiveness of our estimators on synthetic benchmarks and a real world fMRI data, with application of inter-subject correlation analysis.

cs.LG↗

arXiv2018

Zero-Shot Object Detection

We introduce and tackle the problem of zero-shot object detection (ZSD), which aims to detect object classes which are not observed during training. We work with a challenging set of object classes, not restricting ourselves to similar and/or fine-grained categories as in prior works on zero-shot classification. We present a principled approach by first adapting visual-semantic embeddings for ZSD. We then discuss the problems associated with selecting a background class and motivate two background-aware approaches for learning robust detectors. One of these models uses a fixed background class and the other is based on iterative latent assignments. We also outline the challenge associated with using a limited number of training classes and propose a solution based on dense sampling of the semantic label space using auxiliary data with a large number of categories. We propose novel splits of two standard detection datasets - MSCOCO and VisualGenome, and present extensive empirical results in both the traditional and generalized zero-shot settings to highlight the benefits of the proposed methods. We provide useful insights into the algorithm and conclude by posing some open questions to encourage further research.

cs.CV↗

arXiv2018

Understanding Visual Ads by Aligning Symbols and Objects using Co-Attention

We tackle the problem of understanding visual ads where given an ad image, our goal is to rank appropriate human generated statements describing the purpose of the ad. This problem is generally addressed by jointly embedding images and candidate statements to establish correspondence. Decoding a visual ad requires inference of both semantic and symbolic nuances referenced in an image and prior methods may fail to capture such associations especially with weakly annotated symbols. In order to create better embeddings, we leverage an attention mechanism to associate image proposals with symbols and thus effectively aggregate information from aligned multimodal representations. We propose a multihop co-attention mechanism that iteratively refines the attention map to ensure accurate attention estimation. Our attention based embedding model is learned end-to-end guided by a max-margin loss function. We show that our model outperforms other baselines on the benchmark Ad dataset and also show qualitative results to highlight the advantages of using multihop co-attention.

cs.CV↗

arXiv2017

Combining Weakly and Webly Supervised Learning for Classifying Food Images

Food classification from images is a fine-grained classification problem. Manual curation of food images is cost, time and scalability prohibitive. On the other hand, web data is available freely but contains noise. In this paper, we address the problem of classifying food images with minimal data curation. We also tackle a key problems with food images from the web where they often have multiple cooccuring food types but are weakly labeled with a single label. We first demonstrate that by sequentially adding a few manually curated samples to a larger uncurated dataset from two web sources, the top-1 classification accuracy increases from 50.3% to 72.8%. To tackle the issue of weak labels, we augment the deep model with Weakly Supervised learning (WSL) that results in an increase in performance to 76.2%. Finally, we show some qualitative results to provide insights into the performance improvements using the proposed ideas.

cs.CV↗

arXiv2015

Human Social Interaction Modeling Using Temporal Deep Networks

We present a novel approach to computational modeling of social interactions based on modeling of essential social interaction predicates (ESIPs) such as joint attention and entrainment. Based on sound social psychological theory and methodology, we collect a new "Tower Game" dataset consisting of audio-visual capture of dyadic interactions labeled with the ESIPs. We expect this dataset to provide a new avenue for research in computational social interaction modeling. We propose a novel joint Discriminative Conditional Restricted Boltzmann Machine (DCRBM) model that combines a discriminative component with the generative power of CRBMs. Such a combination enables us to uncover actionable constituents of the ESIPs in two steps. First, we train the DCRBM model on the labeled data and get accurate (76\%-49\% across various ESIPs) detection of the predicates. Second, we exploit the generative capability of DCRBMs to activate the trained model so as to generate the lower-level data corresponding to the specific ESIP that closely matches the actual training data (with mean square error 0.01-0.1 for generating 100 frames). We are thus able to decompose the ESIPs into their constituent actionable behaviors. Such a purely computational determination of how to establish an ESIP such as engagement is unprecedented.

cs.CY↗