Few-shot Video Object Detection (FSVOD) addresses the challenge of detecting novel objects in videos with limited labeled examples, overcoming the constraints of traditional detection methods that require extensive training data. This task presents key challenges, including maintaining temporal consistency across frames affected by occlusion and appearance variations, and achieving novel object generalization without relying on complex region proposals, which are often computationally expensive and require task-specific training. Our novel object-aware temporal modeling approach addresses these challenges by incorporating a filtering mechanism that selectively propagates high-confidence object features across frames. This enables efficient feature progression, reduces noise accumulation, and enhances detection accuracy in a few-shot setting. By utilizing few-shot trained detection and classification heads with focused feature propagation, we achieve robust temporal consistency without depending on explicit object tube proposals. Our approach achieves performance gains, with AP improvements of 3.7% (FSVOD-500), 5.3% (FSYTV-40), 4.3% (VidOR), and 4.5% (VidVRD) in the 5-shot setting. Further results demonstrate improvements in 1-shot, 3-shot, and 10-shot configurations.

Traditionally, AI research in medical diagnosis has largely centered on image analysis. While this has led to notable advancements, the absence of patient-reported symptoms continues to hinder diagnostic accuracy. To address this, we propose a Pre-Consultation Dialogue Framework (PCDF) that mimics real-world diagnostic procedures, where doctors iteratively query patients before reaching a conclusion. Specifically, we simulate diagnostic dialogues between two vision–language models (VLMs): a DocVLM, which generates follow-up questions based on the image and dialogue history, and a PatientVLM, which responds using a symptom profile derived from the ground-truth diagnosis. We additionally conducted a small-scale clinical validation of the synthetic symptoms generated by our framework, with licensed clinicians confirming their clinical relevance, symptom coverage, and overall realism. These findings indicate that the resulting DocVLM–PatientVLM interactions form coherent, multi-turn consultations paired with images and diagnoses, which we then use to fine-tune the DocVLM. This dialogue-based supervision leads to substantial gains over image-only training, highlighting the value of realistic symptom elicitation for diagnosis.

Writing comprehensive and accurate descriptions of technical drawings in patent documents is crucial to effective knowledge sharing and enabling the replication and protection of intellectual property. However, automation of this task has been largely overlooked by the research community. To this end, we introduce PatentDesc-355K, a novel large-scale dataset containing ∼355K patent figures along with their brief and detailed textual descriptions extracted from more than 60K US patent documents. In addition, we propose PatentLMM – a novel large multimodal model specifically tailored to generate high-quality descriptions of patent figures. Our proposed PatentLMM comprises two key components: (i) PatentMME, a specialized multimodal vision encoder that captures the unique structural elements of patent figures, and (ii) PatentLLaMA, a domain-adapted version of LLaMA fine-tuned on a large collection of patents. Our extensive experiments demonstrate that training a vision encoder specifically designed for patent figures significantly boosts the performance, generating coherent descriptions compared to fine-tuning similar-sized off-the-shelf multimodal models. PatentDesc-355K and PatentLMM pave the way for automating the understanding of patent figures, enabling efficient knowledge sharing and faster drafting of patent documents.

Large Vision-Language Models (L-VLMs) have demonstrated remarkable performance in various vision and language tasks, including visual question answering (VQA).However, their high computational cost makes them impractical for resource-constrained settings and inference-heavy applications.In contrast, Small Vision-Language Models (S-VLMs) offer efficiency but suffer from a significant performance gap compared to their larger counterparts.In this work, we introduce the Model Parity Aligner (MPA), a novel framework designed to systematically improve S-VLMs by leveraging unlabeled images and effective knowledge transfer from L-VLMs.Instead of traditional knowledge distillation methods that rely on labeled training data, MPA employs a strategic parity-based approach that precisely identifies the knowledge disparities between S-VLMs and L-VLMs, and optimizes training by targeting only these disparities.We conduct extensive experiments on four diverse VQA benchmarks, namely TextVQA, ST-VQA, ChartQA, and OKVQA, each of which required specialized reasoning capabilities such as text recognition, chart interpretation, and commonsense and factual understanding.Our results demonstrate that MPA consistently enhances the performance of S-VLM on all benchmarks, reducing the performance gap while maintaining computational efficiency.We make our code publicly available.Q: What time is it on the clock?A: 5:00 Q: Which airline is represented by the blue and white plane

Video-to-video moment retrieval (Vid2VidMR) is the task of localizing unseen events or moments in a target video using a query video. This task poses several challenges, such as the need for semantic frame-level alignment and modeling complex dependencies between query and target videos. To tackle this challenging problem, we introduce MATR (Moment Alignment TRansformer), a transformer-based model designed to capture semantic context as well as the temporal details necessary for precise moment localization. MATR conditions target video representations on query video features using dual-stage sequence alignment that encodes the required correlations and dependencies. These representations are then used to guide foreground/background classification and boundary prediction heads, enabling the model to accurately identify moments in the target video that semantically match with the query video. Additionally, to provide a strong task-specific initialization for MATR, we propose a self-supervised pre-training technique that involves training the model to localize random clips within videos. Extensive experiments demonstrate that MATR achieves notable performance improvements of 13.1% in R@1 and 8.1% in mIoU on an absolute scale compared to state-of-the-art methods on the popular ActivityNet-VRL dataset. Additionally, on our newly proposed dataset, SportsMoments, MATR shows a 14.7% gain in R@1 and a 14.4% gain in mIoU on an absolute scale over strong baselines.

Non-native speakers with limited vocabulary often struggle to name specific objects despite being able to visualize them, e.g., people outside Australia searching for ‘numbats.’ Further, users may want to search for such elusive objects with difficult-to-sketch interactions, e.g., “numbat digging in the ground.” In such common but complex situations, users desire a search interface that accepts composite multimodal queries comprising hand-drawn sketches of “difficult-to-name but easy-to-draw” objects and text describing “difficult-to-sketch but easy-to-verbalize” object's attributes or interaction with the scene. This novel problem statement distinctly differs from the previously well-researched TBIR (text-based image retrieval) and SBIR (sketch-based image retrieval) problems. To study this under-explored task, we curate a dataset, CSTBIR (Composite Sketch+Text Based Image Retrieval), consisting of ~2M queries and 108K natural scene images. Further, as a solution to this problem, we propose a pretrained multimodal transformer-based baseline, STNet (Sketch+Text Network), that uses a hand-drawn sketch to localize relevant objects in the natural scene image, and encodes the text and image to perform image retrieval. In addition to contrastive learning, we propose multiple training objectives that improve the performance of our model. Extensive experiments show that our proposed method outperforms several state-of-the-art retrieval methods for text-only, sketch-only, and composite query modalities. We make the dataset and code available at: https://vl2g.github.io/projects/cstbir.

In this work, we study one-shot video object localization problem that aims to localize instances of unseen objects in the target video using a single query image of the object. Toward addressing this challenging problem, we extend a popular and successful object detection method, namely DETR (Detection Transformer), and introduce a novel approach –query-guided detection transformer for videos (QDETRv). A distinctive feature of QDETRv is its capacity to exploit information from the query image and spatio-temporal context of the target video, which significantly aids in precisely pinpointing the desired object in the video. We incorporate cross-attention mechanisms that capture temporal relationships across adjacent frames to handle the dynamic context in videos effectively. Further, to ensure strong initialization for QDETRv, we also introduce a novel unsupervised pretraining technique tailored to videos. This involves training our model on synthetic object trajectories with an analogous objective as the query-guided localization task. During this pretraining phase, we incorporate recurrent object queries and loss functions that encourage accurate patch feature reconstruction. These additions enable better temporal understanding and robust representation learning. Our experiments show that the proposed model significantly outperforms the competitive baselines on two public benchmarks, VidOR and ImageNet-VidVRD, extended for one-shot open-set localization tasks.

We revisit knowledge-aware text-based visual question answering, also known as Text-KVQA in the light of modern advancements in large multimodal models (LMMs), and make the following contributions: (i) We propose VisTEL -a principled approach to perform visual text entity linking.The proposed VisTEL module harnesses a state-of-the-art visual text recognition engine and the power of a large multimodal model to jointly reason using textual and visual context obtained using surrounding cues in the image to link the visual text entity to the correct knowledge base entity.(ii) We present KaLMA -knowledge-aware large multimodal assistant that augments an LMM with knowledge associated with visual text entity in the image to arrive at an accurate answer.Further, we provide a comprehensive experimental analysis and comparison of our approach with traditional visual question answering, pre-large multimodal models, and large multimodal models, as well as prior top-performing approaches.Averaging over three splits of Text-KVQA, our proposed approach surpasses the previous best approach by a substantial 23.3% on an absolute scale and establishes a new state of the art.We make our implementation publicly available.

Massive Open Online Courses (MOOCs) enable easy access to many educational materials, particularly lecture slides, on the web. Searching through them based on user queries becomes an essential problem due to the availability of such vast information. To address this, we present Lecture Slide Deck Search Engine – a model that supports natural language queries and hand-drawn sketches and performs searches on a large collection of slide images on computer science topics. This search engine is trained using a novel semantic label-aware transformer model that extracts the semantic labels in the slide images and seamlessly encodes them with the visual cues from the slide images and textual cues from the natural language query. Further, to study the problem in a challenging setting, we introduce a novel dataset, namely the Lecture Slide Deck (LecSD) Dataset containing 54K slide images from the Data Structure, Computer Networks, and Optimization courses and provide associated manual annotation for the query in the form of natural language or hand-drawn sketch. The proposed Lecture Slide Deck Search Engine outperforms the competitive baselines and achieves nearly 4% superior Recall@1 on an absolute scale compared to the state-of-the-art approach. We firmly believe that this work will open up promising directions for improving the accessibility and usability of educational resources, enabling students and educators to find and utilize lecture materials more effectively.

In this study, we explore sketch-based object localization on natural images. Given a crude hand-drawn object sketch, the task is to locate all instances of that object in the target image. This problem proves difficult due to the abstract nature of hand-drawn sketches, variations in the style and quality of sketches, and the large domain gap between the sketches and the natural images. Existing solutions address this using attention-based frameworks to merge query information into image features. Yet, these methods often integrate query features after independently learning image features, causing inadequate alignment and as a result incorrect localization. In contrast, we propose a novel sketch-guided vision transformer encoder that uses cross-attention after each block of the transformer-based image encoder to learn query-conditioned image features, leading to stronger alignment with the query sketch. Further, at the decoder’s output, object and sketch features are refined better to align the representation of objects with the sketch query, thereby improving localization. The proposed model also generalizes to the object categories not seen during training, as the target image features learned by the proposed model are query-aware. Our framework can utilize multiple sketch queries via a trainable novel sketch fusion strategy. The model is evaluated on the images from the public benchmark, MS-COCO, using the sketch queries from QuickDraw! and Sketchy datasets. Compared with existing localization methods, the proposed approach gives a 6.6% and 8.0% improvement in mAP for seen objects using sketch queries from QuickDraw! and Sketchy datasets, respectively, and a 12.2% improvement in AP@50 for large objects that are ‘unseen’ during training. The code is available at https://vcl-iisc.github.io/locformer/.

Interpreting visual relationships is a core aspect of comprehensive video understanding. Given a query visual relationship asand a test video, our objective is to localize the subject and object that are connected via the predicate. Given modern visio-lingual understanding capabilities, solving this problem is achievable, provided that there are large-scale annotated training examples available. However, annotating for every combination of subject, object, and predicate is cumbersome, expensive, and possibly infeasible. Therefore, there is a need for models that can learn to spatially and temporally localize subjects and objects that are connected via an unseen predicate using only a few support set videos sharing the common predicate. We address this challenging problem, referred to as few-shot referring relationships in videos for the first time. To this end, we pose the problem as a minimization of an objective function defined over a T-partite random field. Here, the vertices of the random field correspond to candidate bounding boxes for the subject and object, and T represents the number of frames in the test video. This objective function is composed of frame-level and visual relationship similarity potentials. To learn these potentials, we use a relation network that takes query-conditioned translational relationship embedding as inputs and is meta-trained using support set videos in an episodic manner. Further, the objective function is minimized using a belief propagation-based message passing on the random field to obtain the spatiotemporal localization or subject and object trajectories. We perform extensive experiments using two public benchmarks, namely ImageNet-VidVRD and VidOR, and compare the proposed approach with competitive baselines to assess its efficacy.

We study visual question answering in a setting where the answer has to be mined from a pool of relevant and irrelevant images given as a context. For such a setting, a model must first retrieve relevant images from the pool and answer the question from these retrieved images. We refer to this problem as retrieval-based visual question answering (or RETVQA in short). The RETVQA is distinctively different and more challenging than the traditionally-studied Visual Question Answering (VQA), where a given question has to be answered with a single relevant image in context. Towards solving the RETVQA task, we propose a unified Multi Image BART (MI-BART) that takes a question and retrieved images using our relevance encoder for free-form fluent answer generation. Further, we introduce the largest dataset in this space, namely RETVQA, which has the following salient features: multi-image and retrieval requirement for VQA, metadata-independent questions over a pool of heterogeneous images, expecting a mix of classification-oriented and open-ended generative answers. Our proposed framework achieves an accuracy of 76.5% and a fluency of 79.3% on the proposed dataset, namely RETVQA and also outperforms state-of-the-art methods by 4.9% and 11.8% on the image segment of the publicly available WebQA dataset on the accuracy and fluency metrics, respectively.

This paper presents a framework for jointly grounding objects that follow certain semantic relationship constraints given in a scene graph. A typical natural scene contains several objects, often exhibiting visual relationships of varied complexities between them. These inter-object relationships provide strong contextual cues towards improving grounding performance compared to a traditional object query-only-based localization task. A scene graph is an efficient and structured way to represent all the objects and their semantic relationships in the image. In an attempt towards bridging these two modalities representing scenes and utilizing contextual information for improving object localization, we rigorously study the problem of grounding scene graphs on natural images. To this end, we propose a novel graph neural network-based approach referred to as Visio-Lingual Message Passing Graph Neural Network (VL-MPAG Net). In VL-MPAG Net, we first construct a directed graph with object proposals as nodes and an edge between a pair of nodes representing a plausible relation between them. Then a three-step inter-graph and intra-graph message passing is performed to learn the context- dependent representation of the proposals and query objects. These object representations are used to score the proposals to generate object localization. The proposed method significantly outperforms the baselines on four public datasets.

Table -to-text generation has been widely studied in the Natural Language Processing community in the recent years.We give a new perspective to this problem by incorporating signals from both tables as well as associated images to generate relevant text.While tables contain a structured list of facts, images are a rich source of unstructured visual information.For example, in the tourism domain, images can be used to infer knowledge such as the type of landmark (e.g., church), its architecture (e.g., Ancient Roman), and composition (e.g., white marble).Therefore, in this paper, we introduce the novel task of Vision-augmented Table -To-Text Generation (VISTOT), defined as follows: given a table and an associated image, produce a descriptive sentence conditioned on the multimodal input.For the task, we present a novel multimodal table-to-text dataset, WIKILAND-MARKS, covering 73,084 unique world landmarks.Further, we also present a competitive architecture, namely, VT3 that generates accurate sentences conditioned on the image and table pairs.Through extensive analyses and experiments, we show that visual cues from images are helpful in (i) inferring missing information from incomplete or sparse tables, and (ii) strengthening the importance of useful information from noisy tables for natural language generation.We make the code and data publicly available 1 .

In this paper, given a small bag of images, each containing a common but latent predicate, we are interested in localizing visual subject-object pairs connected via the common predicate in each of the images. We refer to this novel problem as visual relationship co-localization or VRC as an abbreviation. VRC is a challenging task, even more so than the well-studied object co-localization task. This becomes further challenging when using just a few images, the model has to learn to co-localize visual subject-object pairs connected via unseen predicates. To solve VRC, we propose an optimization framework to select a common visual relationship in each image of the bag. The goal of the optimization framework is to find the optimal solution by learning visual relationship similarity across images in a few-shot setting. To obtain robust visual relationship representation, we utilize a simple yet effective technique that learns relationship embedding as a translation vector from visual subject to visual object in a shared space. Further, to learn visual relationship similarity, we utilize a proven meta-learning technique commonly used for few-shot classification tasks. Finally, to tackle the combinatorial complexity challenge arising from an exponential number of feasible solutions, we use a greedy approximation inference algorithm that selects approximately the best solution.We extensively evaluate our proposed framework on variations of bag sizes obtained from two challenging public datasets, namely VrR-VG and VG-150, and achieve impressive visual co-localization performance.

Visual Question Answering (VQA) has emerged as an important problem spanning Computer Vision, Natural Language Processing and Artificial Intelligence (AI). In conventional VQA, one may ask questions about an image which can be answered purely based on its content. For example, given an image with people in it, a typical VQA question may inquire about the number of people in the image. More recently, there is growing interest in answering questions which require commonsense knowledge involving common nouns (e.g., cats, dogs, microphones) present in the image. In spite of this progress, the important problem of answering questions requiring world knowledge about named entities (e.g., Barack Obama, White House, United Nations) in the image has not been addressed in prior research. We address this gap in this paper, and introduce KVQA – the first dataset for the task of (world) knowledge-aware VQA. KVQA consists of 183K question-answer pairs involving more than 18K named entities and 24K images. Questions in this dataset require multi-entity, multi-relation, and multi-hop reasoning over large Knowledge Graphs (KG) to arrive at an answer. To the best of our knowledge, KVQA is the largest dataset for exploring VQA over KG. Further, we also provide baseline performances using state-of-the-art methods on KVQA.

Text present in images are not merely strings, they provide useful cues about the image. Despite their utility in better image understanding, scene texts are not used in traditional visual question answering (VQA) models. In this work, we present a VQA model which can read scene texts and perform reasoning on a knowledge graph to arrive at an accurate answer. Our proposed model has three mutually interacting modules: i. proposal module to get word and visual content proposals from the image, ii. fusion module to fuse these proposals, question and knowledge base to mine relevant facts, and represent these facts as multi-relational graph, iii. reasoning module to perform a novel gated graph neural network based reasoning on this graph. The performance of our knowledge-enabled VQA model is evaluated on our newly introduced dataset, viz. text-KVQA. To the best of our knowledge, this is the first dataset which identifies the need for bridging text recognition with knowledge graph based reasoning. Through extensive experiments, we show that our proposed method outperforms traditional VQA as well as question-answering over knowledge base-based methods on text-KVQA.

The problem of answering questions about an image is popularly known as visual question answering (or VQA in short). It is a well-established problem in computer vision. However, none of the VQA methods currently utilize the text often present in the image. These "texts in images" provide additional useful cues and facilitate better understanding of the visual content. In this paper, we introduce a novel task of visual question answering by reading text in images, i.e., by optical character recognition or OCR. We refer to this problem as OCR-VQA. To facilitate a systematic way of studying this new problem, we introduce a large-scale dataset, namely OCRVQA-200K. This dataset comprises of 207,572 images of book covers and contains more than 1 million question-answer pairs about these images. We judiciously combine well-established techniques from OCR and VQA domains to present a novel baseline for OCR-VQA-200K. The experimental results and rigorous analysis demonstrate various challenges present in this dataset leaving ample scope for the future research. We are optimistic that this new task along with compiled dataset will open-up many exciting research avenues both for the document image analysis and the VQA communities.

We present an approach for automatically identifying the script of the text localized in the scene images. Our approach is inspired by the advancements in mid-level features. We represent the text images using mid-level features which are pooled from densely computed local features. Once text images are represented using the proposed mid-level feature representation, we use an off-the-shelf classifier to identify the script of the text image. Our approach is efficient and requires very less labeled data. We evaluate the performance of our method on a recently introduced CVSI dataset, demonstrating that the proposed approach can correctly identify script of 96.70% of the text images. In addition, we also introduce and benchmark a more challenging Indian Language Scene Text (ILST) dataset for evaluating the performance of our method.

We present an approach for the text-to-image retrieval problem based on textual content present in images. Given the recent developments in understanding text in images, an appealing approach to address this problem is to localize and recognize the text, and then query the database, as in a text retrieval problem. We show that such an approach, despite being based on state-of-the-art methods, is insufficient, and propose a method, where we do not rely on an exact localization and recognition pipeline. We take a query-driven search approach, where we find approximate locations of characters in the text query, and then impose spatial constraints to generate a ranked list of images in the database. The retrieval performance is evaluated on public scene text datasets as well as three large datasets, namely IIIT scene text retrieval, Sports-10K and TV series-1M, we introduce.

Recognizing text in images taken in the wild is a challenging problem that has received great attention in recent years. Previous methods addressed this problem by first detecting individual characters, and then forming them into words. Such approaches often suffer from weak character detections, due to large intra-class variations, even more so than characters from scanned documents. We take a different view of the problem and present a holistic word recognition framework. In this, we first represent the scene text image and synthetic images generated from lexicon words using gradient-based features. We then recognize the text in the image by matching the scene and synthetic image features with our novel weighted Dynamic Time Warping (wDTW) approach. We perform experimental analysis on challenging public datasets, such as Street View Text and ICDAR 2003. Our proposed method significantly outperforms our earlier work in Mishra et al. (CVPR 2012), as well as many other recent works, such as Novikova et al. (ECCV 2012), Wang et al. al.(ICPR 2012), Wang et al.(ICCV 2011).

Sparse representation based image restoration techniques have shown to be successful in solving various inverse problems such as denoising, in painting, and super-resolution, etc. on natural images and videos. In this paper, we explore the use of sparse representation based methods specifically to restore the degraded document images. While natural images form a very small subset of all possible images admitting the possibility of sparse representation, document images are significantly more restricted and are expected to be ideally suited for such a representation. However, the binary nature of textual document images makes dictionary learning and coding techniques unsuitable to be applied directly. We leverage the fact that different characters possess similar strokes, curves, and edges, and learn a dictionary that gives sparse decomposition for patches. Experimental results show significant improvement in image quality and OCR performance on documents collected from a variety of sources such as magazines and books. This method is therefore, ideally suited for restoring highly degraded images in repositories such as digital libraries.

International audience

Scene text recognition has gained significant attention from the computer vision community in recent years. Recognizing such text is a challenging problem, even more so than the recognition of scanned documents. In this work, we focus on the problem of recognizing text extracted from street images. We present a framework that exploits both bottom-up and top-down cues. The bottom-up cues are derived from individual character detections from the image. We build a Conditional Random Field model on these detections to jointly model the strength of the detections and the interactions between them. We impose top-down cues obtained from a lexicon-based prior, i.e. language statistics, on the model. The optimal word represented by the text image is obtained by minimizing the energy function corresponding to the random field model. We show significant improvements in accuracies on two challenging public datasets, namely Street View Text (over 15%) and ICDAR 2003 (nearly 10%).

Inspired by the success of MRF models for solving object segmentation problems, we formulate the binarization problem in this framework. We represent the pixels in a document image as random variables in an MRF, and introduce a new energy (or cost) function on these variables. Each variable takes a foreground or background label, and the quality of the binarization (or labelling) is determined by the value of the energy function. We minimize the energy function, i.e. find the optimal binarization, using an iterative graph cut scheme. Our model is robust to variations in foreground and background colours as we use a Gaussian Mixture Model in the energy function. In addition, our algorithm is efficient to compute, and adapts to a variety of document images. We show results on word images from the challenging ICDAR 2003 dataset, and compare our performance with previously reported methods. Our approach shows significant improvement in pixel level accuracy as well as OCR accuracy.