C. V. Jawahar

Kristen Grauman, Andrew Westbury, Lorenzo Torresani et al. · cmu, gatech

We present Ego-Exo4D, a diverse, large-scale multimodal multiview video dataset and benchmark challenge. Ego-Exo4D centers around simultaneously-captured egocentric and exocentric video of skilled human activities (e.g., sports, music, dance, bike repair). 740 participants from 13 cities worldwide performed these activities in 123 different natural scene contexts, yielding long-form captures from 1 to 42 minutes each and 1,286 hours of video combined. The multimodal nature of the dataset is unprecedented: the video is accompanied by multichannel audio, eye gaze, 3D point clouds, camera poses, IMU, and multiple paired language descriptions -- including a novel "expert commentary" done by coaches and teachers and tailored to the skilled-activity domain. To push the frontier of first-person video understanding of skilled human activity, we also present a suite of benchmark tasks and their annotations, including fine-grained activity understanding, proficiency estimation, cross-view translation, and 3D hand/body pose. All resources are open sourced to fuel new research in the community. Project page: http://ego-exo4d-data.org/

Shubham Dokania, A. H. Abdul Hafez, Anbumani Subramanian et al.

Autonomous driving and assistance systems rely on annotated data from traffic and road scenarios to model and learn the various object relations in complex real-world scenarios. Preparation and training of deploy-able deep learning architectures require the models to be suited to different traffic scenarios and adapt to different situations. Currently, existing datasets, while large-scale, lack such diversities and are geographically biased towards mainly developed cities. An unstructured and complex driving layout found in several developing countries such as India poses a challenge to these models due to the sheer degree of variations in the object types, densities, and locations. To facilitate better research toward accommodating such scenarios, we build a new dataset, IDD-3D, which consists of multi-modal data from multiple cameras and LiDAR sensors with 12k annotated driving LiDAR frames across various traffic scenarios. We discuss the need for this dataset through statistical comparisons with existing datasets and highlight benchmarks on standard 3D object detection and tracking tasks in complex layouts. Code and data available at https://github.com/shubham1810/idd3d_kit.git

Shubham Dokania, Anbumani Subramanian, Manmohan Chandraker et al.

High-quality structured data with rich annotations are critical components in intelligent vehicle systems dealing with road scenes. However, data curation and annotation require intensive investments and yield low-diversity scenarios. The recently growing interest in synthetic data raises questions about the scope of improvement in such systems and the amount of manual work still required to produce high volumes and variations of simulated data. This work proposes a synthetic data generation pipeline that utilizes existing datasets, like nuScenes, to address the difficulties and domain-gaps present in simulated datasets. We show that using annotations and visual cues from existing datasets, we can facilitate automated multi-modal data generation, mimicking real scene properties with high-fidelity, along with mechanisms to diversify samples in a physically meaningful way. We demonstrate improvements in mIoU metrics by presenting qualitative and quantitative experiments with real and synthetic data for semantic segmentation on the Cityscapes and KITTI-STEP datasets. All relevant code and data is released on github (https://github.com/shubham1810/trove_toolkit).

Megha Mariam K. M, Vineeth N. Balasubramanian, C. V. Jawahar

The communication of scientific knowledge has become increasingly multimodal, spanning text, visuals, and speech through materials such as research papers, slides, and recorded presentations. These different representations collectively convey a study's reasoning, results, and insights, offering complementary perspectives that enrich understanding. However, despite their shared purpose, such materials are rarely connected in a structured way. The absence of explicit links across formats makes it difficult to trace how concepts, visuals, and explanations correspond, limiting unified exploration and analysis of research content. To address this gap, we introduce the Multimodal Conference Dataset (MCD), the first benchmark that integrates research papers, presentation videos, explanatory videos, and slides from the same works. We evaluate a range of embedding-based and vision-language models to assess their ability to discover fine-grained cross-format correspondences, establishing the first systematic benchmark for this task. Our results show that vision-language models are robust but struggle with fine-grained alignment, while embedding-based models capture text-visual correspondences well but equations and symbolic content form distinct clusters in the embedding space. These findings highlight both the strengths and limitations of current approaches and point to key directions for future research in multimodal scientific understanding. To ensure reproducibility, we release the resources for MCD at https://github.com/meghamariamkm2002/MCD

Bipasha Sen, Aditya Agarwal, Vinay P Namboodiri et al. · mila, mit

Generating videos is a complex task that is accomplished by generating a set of temporally coherent images frame-by-frame. This limits the expressivity of videos to only image-based operations on the individual video frames needing network designs to obtain temporally coherent trajectories in the underlying image space. We propose INR-V, a video representation network that learns a continuous space for video-based generative tasks. INR-V parameterizes videos using implicit neural representations (INRs), a multi-layered perceptron that predicts an RGB value for each input pixel location of the video. The INR is predicted using a meta-network which is a hypernetwork trained on neural representations of multiple video instances. Later, the meta-network can be sampled to generate diverse novel videos enabling many downstream video-based generative tasks. Interestingly, we find that conditional regularization and progressive weight initialization play a crucial role in obtaining INR-V. The representation space learned by INR-V is more expressive than an image space showcasing many interesting properties not possible with the existing works. For instance, INR-V can smoothly interpolate intermediate videos between known video instances (such as intermediate identities, expressions, and poses in face videos). It can also in-paint missing portions in videos to recover temporally coherent full videos. In this work, we evaluate the space learned by INR-V on diverse generative tasks such as video interpolation, novel video generation, video inversion, and video inpainting against the existing baselines. INR-V significantly outperforms the baselines on several of these demonstrated tasks, clearly showcasing the potential of the proposed representation space.

Sindhu B Hegde, K R Prajwal, Rudrabha Mukhopadhyay et al. · oxford

In this work, we address the problem of generating speech from silent lip videos for any speaker in the wild. In stark contrast to previous works, our method (i) is not restricted to a fixed number of speakers, (ii) does not explicitly impose constraints on the domain or the vocabulary and (iii) deals with videos that are recorded in the wild as opposed to within laboratory settings. The task presents a host of challenges, with the key one being that many features of the desired target speech, like voice, pitch and linguistic content, cannot be entirely inferred from the silent face video. In order to handle these stochastic variations, we propose a new VAE-GAN architecture that learns to associate the lip and speech sequences amidst the variations. With the help of multiple powerful discriminators that guide the training process, our generator learns to synthesize speech sequences in any voice for the lip movements of any person. Extensive experiments on multiple datasets show that we outperform all baselines by a large margin. Further, our network can be fine-tuned on videos of specific identities to achieve a performance comparable to single-speaker models that are trained on $4\times$ more data. We conduct numerous ablation studies to analyze the effect of different modules of our architecture. We also provide a demo video that demonstrates several qualitative results along with the code and trained models on our website: \url{http://cvit.iiit.ac.in/research/projects/cvit-projects/lip-to-speech-synthesis}}

Aditya Agarwal, Bipasha Sen, Rudrabha Mukhopadhyay et al. · mila, mit

Doubles play an indispensable role in the movie industry. They take the place of the actors in dangerous stunt scenes or scenes where the same actor plays multiple characters. The double's face is later replaced with the actor's face and expressions manually using expensive CGI technology, costing millions of dollars and taking months to complete. An automated, inexpensive, and fast way can be to use face-swapping techniques that aim to swap an identity from a source face video (or an image) to a target face video. However, such methods cannot preserve the source expressions of the actor important for the scene's context. To tackle this challenge, we introduce video-to-video (V2V) face-swapping, a novel task of face-swapping that can preserve (1) the identity and expressions of the source (actor) face video and (2) the background and pose of the target (double) video. We propose FaceOff, a V2V face-swapping system that operates by learning a robust blending operation to merge two face videos following the constraints above. It reduces the videos to a quantized latent space and then blends them in the reduced space. FaceOff is trained in a self-supervised manner and robustly tackles the non-trivial challenges of V2V face-swapping. As shown in the experimental section, FaceOff significantly outperforms alternate approaches qualitatively and quantitatively.

Varun A. Paturkar, Shankar Gangisetty, C. V. Jawahar

Two-wheelers account for a disproportionately high share of road fatalities in the Global South. Research on two-wheeler rider behavior, however, lags far behind four-wheelers, where multimodal datasets have driven major advances in Advanced Driver Assistance Systems (ADAS). To address this gap, we present the MOtorized TwO-wheeler Rider (MOTOR) dataset, the first large-scale, multi-view, multimodal resource dedicated to two-wheelers in dense, unstructured traffic. MOTOR comprises 1,629 sequences (25+ hours of video data) collected from 16 riders and integrates synchronized front, rear, and helmet videos, rider eye-gaze from wearable trackers, on-road audio, and telemetry (GPS, accelerometer, gyroscope). Rich annotations capture traffic context, rider state, 12 riding maneuvers spanning conventional and unconventional behaviors, and legality labels (Legal, Illegal, Unspecified). We benchmark rider behavior recognition and maneuver legality classification using state-of-the-art video action recognition backbones (CNN and Transformer-based), extended with multimodal fusion, and find that combining RGB, gaze, and telemetry consistently yields the best performance. MOTOR thus provides a unique foundation for advancing safety-critical understanding of two-wheeler riding. It offers the research community a benchmark to develop and evaluate models for behavior analysis, legality-aware prediction, and intelligent transportation systems. Dataset and code is available at https: //varuniiith.github.io/MOTOR-Dataset/

Soumya Jahagirdar, Minesh Mathew, Dimosthenis Karatzas et al.

Video Question Answering methods focus on commonsense reasoning and visual cognition of objects or persons and their interactions over time. Current VideoQA approaches ignore the textual information present in the video. Instead, we argue that textual information is complementary to the action and provides essential contextualisation cues to the reasoning process. To this end, we propose a novel VideoQA task that requires reading and understanding the text in the video. To explore this direction, we focus on news videos and require QA systems to comprehend and answer questions about the topics presented by combining visual and textual cues in the video. We introduce the ``NewsVideoQA'' dataset that comprises more than $8,600$ QA pairs on $3,000+$ news videos obtained from diverse news channels from around the world. We demonstrate the limitations of current Scene Text VQA and VideoQA methods and propose ways to incorporate scene text information into VideoQA methods.

George Tom, Minesh Mathew, Sergi Garcia et al.

Text and signs around roads provide crucial information for drivers, vital for safe navigation and situational awareness. Scene text recognition in motion is a challenging problem, while textual cues typically appear for a short time span, and early detection at a distance is necessary. Systems that exploit such information to assist the driver should not only extract and incorporate visual and textual cues from the video stream but also reason over time. To address this issue, we introduce RoadTextVQA, a new dataset for the task of video question answering (VideoQA) in the context of driver assistance. RoadTextVQA consists of $3,222$ driving videos collected from multiple countries, annotated with $10,500$ questions, all based on text or road signs present in the driving videos. We assess the performance of state-of-the-art video question answering models on our RoadTextVQA dataset, highlighting the significant potential for improvement in this domain and the usefulness of the dataset in advancing research on in-vehicle support systems and text-aware multimodal question answering. The dataset is available at http://cvit.iiit.ac.in/research/projects/cvit-projects/roadtextvqa

Ajoy Mondal, C. V. Jawahar

Handwritten Text Recognition (HTR) is more interesting and challenging than printed text due to uneven variations in the handwriting style of the writers, content, and time. HTR becomes more challenging for the Indic languages because of (i) multiple characters combined to form conjuncts which increase the number of characters of respective languages, and (ii) near to 100 unique basic Unicode characters in each Indic script. Recently, many recognition methods based on the encoder-decoder framework have been proposed to handle such problems. They still face many challenges, such as image blur and incomplete characters due to varying writing styles and ink density. We argue that most encoder-decoder methods are based on local visual features without explicit global semantic information. In this work, we enhance the performance of Indic handwritten text recognizers using global semantic information. We use a semantic module in an encoder-decoder framework for extracting global semantic information to recognize the Indic handwritten texts. The semantic information is used in both the encoder for supervision and the decoder for initialization. The semantic information is predicted from the word embedding of a pre-trained language model. Extensive experiments demonstrate that the proposed framework achieves state-of-the-art results on handwritten texts of ten Indic languages.

Devdoot Chatterjee, Zakaria Laskar, C. V. Jawahar

We present a generalizable feed-forward Gaussian splatting framework for human 3D reconstruction and real-time animation that operates directly on multi-view RGB images and their associated SMPL-X poses. Unlike prior methods that rely on depth supervision, fixed input views, UV map, or repeated feed-forward inference for each target view or pose, our approach predicts, in a canonical pose, a set of 3D Gaussian primitives associated with each SMPL-X vertex. One Gaussian is regularized to remain close to the SMPL-X surface, providing a strong geometric prior and stable correspondence to the parametric body model, while an additional small set of unconstrained Gaussians per vertex allows the representation to capture geometric structures that deviate from the parametric surface, such as clothing and hair. In contrast to recent approaches such as HumanRAM, which require repeated network inference to synthesize novel poses, our method produces an animatable human representation from a single forward pass; by explicitly associating Gaussian primitives with SMPL-X vertices, the reconstructed model can be efficiently animated via linear blend skinning without further network evaluation. We evaluate our method on the THuman 2.1, AvatarReX and THuman 4.0 datasets, where it achieves reconstruction quality comparable to state-of-the-art methods while uniquely supporting real-time animation and interactive applications. Code and pre-trained models are available at https://github.com/Devdoot57/HumanGS .

Zeeshan Khan, C. V. Jawahar, Makarand Tapaswi

Dense video understanding requires answering several questions such as who is doing what to whom, with what, how, why, and where. Recently, Video Situation Recognition (VidSitu) is framed as a task for structured prediction of multiple events, their relationships, and actions and various verb-role pairs attached to descriptive entities. This task poses several challenges in identifying, disambiguating, and co-referencing entities across multiple verb-role pairs, but also faces some challenges of evaluation. In this work, we propose the addition of spatio-temporal grounding as an essential component of the structured prediction task in a weakly supervised setting, and present a novel three stage Transformer model, VideoWhisperer, that is empowered to make joint predictions. In stage one, we learn contextualised embeddings for video features in parallel with key objects that appear in the video clips to enable fine-grained spatio-temporal reasoning. The second stage sees verb-role queries attend and pool information from object embeddings, localising answers to questions posed about the action. The final stage generates these answers as captions to describe each verb-role pair present in the video. Our model operates on a group of events (clips) simultaneously and predicts verbs, verb-role pairs, their nouns, and their grounding on-the-fly. When evaluated on a grounding-augmented version of the VidSitu dataset, we observe a large improvement in entity captioning accuracy, as well as the ability to localize verb-roles without grounding annotations at training time.

Megha Mariam K. M, Aditya Arun, Zakaria Laskar et al.

Generative AI models, particularly Text-to-Video (T2V) systems, offer a promising avenue for transforming science education by automating the creation of engaging and intuitive visual explanations. In this work, we take a first step toward evaluating their potential in physics education by introducing a dedicated benchmark for explanatory video generation. The benchmark is designed to assess how well T2V models can convey core physics concepts through visual illustrations. Each physics concept in our benchmark is decomposed into granular teaching points, with each point accompanied by a carefully crafted prompt intended for visual explanation of the teaching point. T2V models are evaluated on their ability to generate accurate videos in response to these prompts. Our aim is to systematically explore the feasibility of using T2V models to generate high-quality, curriculum-aligned educational content-paving the way toward scalable, accessible, and personalized learning experiences powered by AI. Our evaluation reveals that current models produce visually coherent videos with smooth motion and minimal flickering, yet their conceptual accuracy is less reliable. Performance in areas such as mechanics, fluids, and optics is encouraging, but models struggle with electromagnetism and thermodynamics, where abstract interactions are harder to depict. These findings underscore the gap between visual quality and conceptual correctness in educational video generation. We hope this benchmark helps the community close that gap and move toward T2V systems that can deliver accurate, curriculum-aligned physics content at scale. The benchmark and accompanying codebase are publicly available at https://github.com/meghamariamkm/PhyEduVideo.

Aman Goyal, Dev Agarwal, Anbumani Subramanian et al.

In many Asian countries with unconstrained road traffic conditions, driving violations such as not wearing helmets and triple-riding are a significant source of fatalities involving motorcycles. Identifying and penalizing such riders is vital in curbing road accidents and improving citizens' safety. With this motivation, we propose an approach for detecting, tracking, and counting motorcycle riding violations in videos taken from a vehicle-mounted dashboard camera. We employ a curriculum learning-based object detector to better tackle challenging scenarios such as occlusions. We introduce a novel trapezium-shaped object boundary representation to increase robustness and tackle the rider-motorcycle association. We also introduce an amodal regressor that generates bounding boxes for the occluded riders. Experimental results on a large-scale unconstrained driving dataset demonstrate the superiority of our approach compared to existing approaches and other ablative variants.

Avijit Dasgupta, C. V. Jawahar, Karteek Alahari

Despite the progress seen in classification methods, current approaches for handling videos with distribution shifts in source and target domains remain source-dependent as they require access to the source data during the adaptation stage. In this paper, we present a self-training based source-free video domain adaptation approach to address this challenge by bridging the gap between the source and the target domains. We use the source pre-trained model to generate pseudo-labels for the target domain samples, which are inevitably noisy. Thus, we treat the problem of source-free video domain adaptation as learning from noisy labels and argue that the samples with correct pseudo-labels can help us in adaptation. To this end, we leverage the cross-entropy loss as an indicator of the correctness of the pseudo-labels and use the resulting small-loss samples from the target domain for fine-tuning the model. We further enhance the adaptation performance by implementing a teacher-student (TS) framework, in which the teacher, which is updated gradually, produces reliable pseudo-labels. Meanwhile, the student undergoes fine-tuning on the target domain videos using these generated pseudo-labels to improve its performance. Extensive experimental evaluations show that our methods, termed as CleanAdapt, CleanAdapt + TS, achieve state-of-the-art results, outperforming the existing approaches on various open datasets. Our source code is publicly available at https://avijit9.github.io/CleanAdapt.

Siddhant Bansal, Chetan Arora, C. V. Jawahar

Procedure learning involves identifying the key-steps and determining their logical order to perform a task. Existing approaches commonly use third-person videos for learning the procedure, making the manipulated object small in appearance and often occluded by the actor, leading to significant errors. In contrast, we observe that videos obtained from first-person (egocentric) wearable cameras provide an unobstructed and clear view of the action. However, procedure learning from egocentric videos is challenging because (a) the camera view undergoes extreme changes due to the wearer's head motion, and (b) the presence of unrelated frames due to the unconstrained nature of the videos. Due to this, current state-of-the-art methods' assumptions that the actions occur at approximately the same time and are of the same duration, do not hold. Instead, we propose to use the signal provided by the temporal correspondences between key-steps across videos. To this end, we present a novel self-supervised Correspond and Cut (CnC) framework for procedure learning. CnC identifies and utilizes the temporal correspondences between the key-steps across multiple videos to learn the procedure. Our experiments show that CnC outperforms the state-of-the-art on the benchmark ProceL and CrossTask datasets by 5.2% and 6.3%, respectively. Furthermore, for procedure learning using egocentric videos, we propose the EgoProceL dataset consisting of 62 hours of videos captured by 130 subjects performing 16 tasks. The source code and the dataset are available on the project page https://sid2697.github.io/egoprocel/.

Sindhu B Hegde, Rudrabha Mukhopadhyay, Vinay P Namboodiri et al.

In this paper, we explore an interesting question of what can be obtained from an $8\times8$ pixel video sequence. Surprisingly, it turns out to be quite a lot. We show that when we process this $8\times8$ video with the right set of audio and image priors, we can obtain a full-length, $256\times256$ video. We achieve this $32\times$ scaling of an extremely low-resolution input using our novel audio-visual upsampling network. The audio prior helps to recover the elemental facial details and precise lip shapes and a single high-resolution target identity image prior provides us with rich appearance details. Our approach is an end-to-end multi-stage framework. The first stage produces a coarse intermediate output video that can be then used to animate single target identity image and generate realistic, accurate and high-quality outputs. Our approach is simple and performs exceedingly well (an $8\times$ improvement in FID score) compared to previous super-resolution methods. We also extend our model to talking-face video compression, and show that we obtain a $3.5\times$ improvement in terms of bits/pixel over the previous state-of-the-art. The results from our network are thoroughly analyzed through extensive ablation experiments (in the paper and supplementary material). We also provide the demo video along with code and models on our website: \url{http://cvit.iiit.ac.in/research/projects/cvit-projects/talking-face-video-upsampling}.

Naman Mishra, Shankar Gangisetty, C. V. Jawahar

Pedestrian intention and trajectory prediction are critical for the safe deployment of autonomous driving systems, directly influencing navigation decisions in complex traffic environments. Recent advances in large vision-language models offer a powerful new paradigm for these tasks by combining high-capacity visual understanding with flexible natural language reasoning. In this work, we introduce PedestrianQA, a large-scale video-based dataset that formulates pedestrian intention and trajectory prediction as question-answering tasks augmented with structured rationales. PedestrianQA expresses richly annotated pedestrian sequences, in natural language, enabling VLMs to learn from visual dynamics, contextual cues, and interactions among traffic agents while generating concise explanations of their predictions without needing specialized architectures tailored for each task. Empirical evaluations across PIE, JAAD, TITAN, and IDD-PeD show that finetuning state-of-the-art VLMs on PedestrianQA significantly improves intention classification, trajectory forecasting accuracy, and the quality of explanatory rationales, demonstrating the strong potential of VLMs as a unified and explainable framework for safety-critical pedestrian behavior modeling.

Prafful Kumar Khoba, Chirag Parikh, Rohit Saluja et al.

The previous fine-grained datasets mainly focus on classification and are often captured in a controlled setup, with the camera focusing on the objects. We introduce the first Fine-Grained Vehicle Detection (FGVD) dataset in the wild, captured from a moving camera mounted on a car. It contains 5502 scene images with 210 unique fine-grained labels of multiple vehicle types organized in a three-level hierarchy. While previous classification datasets also include makes for different kinds of cars, the FGVD dataset introduces new class labels for categorizing two-wheelers, autorickshaws, and trucks. The FGVD dataset is challenging as it has vehicles in complex traffic scenarios with intra-class and inter-class variations in types, scale, pose, occlusion, and lighting conditions. The current object detectors like yolov5 and faster RCNN perform poorly on our dataset due to a lack of hierarchical modeling. Along with providing baseline results for existing object detectors on FGVD Dataset, we also present the results of a combination of an existing detector and the recent Hierarchical Residual Network (HRN) classifier for the FGVD task. Finally, we show that FGVD vehicle images are the most challenging to classify among the fine-grained datasets.

Megha Mariam K M, C. V. Jawahar

Imagine sitting in a presentation, trying to follow the speaker while simultaneously scanning the slides for relevant information. While the entire slide is visible, identifying the relevant regions can be challenging. As you focus on one part of the slide, the speaker moves on to a new sentence, leaving you scrambling to catch up visually. This constant back-and-forth creates a disconnect between what is being said and the most important visual elements, making it hard to absorb key details, especially in fast-paced or content-heavy presentations such as conference talks. This requires an understanding of slides, including text, graphics, and layout. We introduce a method that automatically identifies and highlights the most relevant slide regions based on the speaker's narrative. By analyzing spoken content and matching it with textual or graphical elements in the slides, our approach ensures better synchronization between what listeners hear and what they need to attend to. We explore different ways of solving this problem and assess their success and failure cases. Analyzing multimedia documents is emerging as a key requirement for seamless understanding of content-rich videos, such as educational videos and conference talks, by reducing cognitive strain and improving comprehension. Code and dataset are available at: https://github.com/meghamariamkm2002/Slide_Highlight

Siddhant Bansal, Chetan Arora, C. V. Jawahar

Given multiple videos of the same task, procedure learning addresses identifying the key-steps and determining their order to perform the task. For this purpose, existing approaches use the signal generated from a pair of videos. This makes key-steps discovery challenging as the algorithms lack inter-videos perspective. Instead, we propose an unsupervised Graph-based Procedure Learning (GPL) framework. GPL consists of the novel UnityGraph that represents all the videos of a task as a graph to obtain both intra-video and inter-videos context. Further, to obtain similar embeddings for the same key-steps, the embeddings of UnityGraph are updated in an unsupervised manner using the Node2Vec algorithm. Finally, to identify the key-steps, we cluster the embeddings using KMeans. We test GPL on benchmark ProceL, CrossTask, and EgoProceL datasets and achieve an average improvement of 2% on third-person datasets and 3.6% on EgoProceL over the state-of-the-art.

Nitin Nilesh, Tushar Sharma, Anurag Ghosh et al.

Analysis of player movements is a crucial subset of sports analysis. Existing player movement analysis methods use recorded videos after the match is over. In this work, we propose an end-to-end framework for player movement analysis for badminton matches on live broadcast match videos. We only use the visual inputs from the match and, unlike other approaches which use multi-modal sensor data, our approach uses only visual cues. We propose a method to calculate the on-court distance covered by both the players from the video feed of a live broadcast badminton match. To perform this analysis, we focus on the gameplay by removing replays and other redundant parts of the broadcast match. We then perform player tracking to identify and track the movements of both players in each frame. Finally, we calculate the distance covered by each player and the average speed with which they move on the court. We further show a heatmap of the areas covered by the player on the court which is useful for analyzing the gameplay of the player. Our proposed framework was successfully used to analyze live broadcast matches in real-time during the Premier Badminton League 2019 (PBL 2019), with commentators and broadcasters appreciating the utility.

Varun Gupta, Anbumani Subramanian, C. V. Jawahar et al.

Unconstrained Asian roads often involve poor infrastructure, affecting overall road safety. Missing traffic signs are a regular part of such roads. Missing or non-existing object detection has been studied for locating missing curbs and estimating reasonable regions for pedestrians on road scene images. Such methods involve analyzing task-specific single object cues. In this paper, we present the first and most challenging video dataset for missing objects, with multiple types of traffic signs for which the cues are visible without the signs in the scenes. We refer to it as the Missing Traffic Signs Video Dataset (MTSVD). MTSVD is challenging compared to the previous works in two aspects i) The traffic signs are generally not present in the vicinity of their cues, ii) The traffic signs cues are diverse and unique. Also, MTSVD is the first publicly available missing object dataset. To train the models for identifying missing signs, we complement our dataset with 10K traffic sign tracks, with 40 percent of the traffic signs having cues visible in the scenes. For identifying missing signs, we propose the Cue-driven Contextual Attention units (CueCAn), which we incorporate in our model encoder. We first train the encoder to classify the presence of traffic sign cues and then train the entire segmentation model end-to-end to localize missing traffic signs. Quantitative and qualitative analysis shows that CueCAn significantly improves the performance of base models.

Ajoy Mondal, Rohit saluja, C. V. Jawahar

Long-term OCR services aim to provide high-quality output to their users at competitive costs. It is essential to upgrade the models because of the complex data loaded by the users. The service providers encourage the users who provide data where the OCR model fails by rewarding them based on data complexity, readability, and available budget. Hitherto, the OCR works include preparing the models on standard datasets without considering the end-users. We propose a strategy of consistently upgrading an existing Handwritten Hindi OCR model three times on the dataset of 15 users. We fix the budget of 4 users for each iteration. For the first iteration, the model directly trains on the dataset from the first four users. For the rest iteration, all remaining users write a page each, which service providers later analyze to select the 4 (new) best users based on the quality of predictions on the human-readable words. Selected users write 23 more pages for upgrading the model. We upgrade the model with Curriculum Learning (CL) on the data available in the current iteration and compare the subset from previous iterations. The upgraded model is tested on a held-out set of one page each from all 23 users. We provide insights into our investigations on the effect of CL, user selection, and especially the data from unseen writing styles. Our work can be used for long-term OCR services in crowd-sourcing scenarios for the service providers and end users.

Thrupthi Ann John, Vineeth N Balasubramanian, C. V. Jawahar

Although current deep models for face tasks surpass human performance on some benchmarks, we do not understand how they work. Thus, we cannot predict how it will react to novel inputs, resulting in catastrophic failures and unwanted biases in the algorithms. Explainable AI helps bridge the gap, but currently, there are very few visualization algorithms designed for faces. This work undertakes a first-of-its-kind meta-analysis of explainability algorithms in the face domain. We explore the nuances and caveats of adapting general-purpose visualization algorithms to the face domain, illustrated by computing visualizations on popular face models. We review existing face explainability works and reveal valuable insights into the structure and hierarchy of face networks. We also determine the design considerations for practical face visualizations accessible to AI practitioners by conducting a user study on the utility of various explainability algorithms.

Sainithin Artham, Shankar Gangisetty, Avijit Dasgupta et al.

Comprehensive situational awareness is essential for autonomous vehicles operating in safety-critical environments, as it enables the identification and mitigation of potential risks. Although recent Multimodal Large Language Models (MLLMs) have shown promise on general vision-language tasks, our findings indicate that zero-shot MLLMs still underperform compared to domain-specific methods in fine-grained, spatially grounded risk assessment. To address this gap, we propose DriveSafe, a framework for risk-aware scene understanding that leverages structured natural language descriptions. Specifically, our method first generates spatially grounded captions enriched with multimodal context, including motion, spatial, and depth cues. These captions are then used for downstream risk assessment, explicitly identifying hazardous objects, their locations, and the unsafe behaviors they imply, followed by actionable safety suggestions. To further improve performance, we employ caption-risk pairings to fine-tune a lightweight adapter module, efficiently injecting domain-specific knowledge into the base LLM. By conditioning risk assessment on explicit language-based scene representations, DriveSafe achieves significant gains over both zero-shot MLLMs and prior domain-specific baselines. Exhaustive experiments on the DRAMA benchmark demonstrate state-of-the-art performance, while ablation studies validate the effectiveness of our key design choices. Project page: https://cvit.iiit.ac.in/ research/projects/cvit-projects/drivesafe

Purbayan Kar, Ayush Ghadiya, Vishal Chudasama et al.

Face aging, an ill-posed problem shaped by environmental and genetic factors, is vital in entertainment, forensics, and digital archiving, where realistic age transformations must preserve both identity and visual realism. However, existing works relying on numerical age representations overlook the interplay of biological and contextual cues. Despite progress in recent face aging models, they struggle with identity preservation in wide age transformations, also static attention and optimization-heavy inversion in diffusion limit adaptability, fine-grained control and background consistency. To address these challenges, we propose Face Time Traveller (FaceTT), a diffusion-based framework that achieves high-fidelity, identity-consistent age transformation. Here, we introduce a Face-Attribute-Aware Prompt Refinement strategy that encodes intrinsic (biological) and extrinsic (environmental) aging cues for context-aware conditioning. A tuning-free Angular Inversion method is proposed that efficiently maps real faces into the diffusion latent space for fast and accurate reconstruction. Moreover, an Adaptive Attention Control mechanism is introduced that dynamically balances cross-attention for semantic aging cues and self-attention for structural and identity preservation. Extensive experiments on benchmark datasets and in-the-wild testset demonstrate that FaceTT achieves superior identity retention, background preservation and aging realism over state-of-the-art (SOTA) methods.

Munish Monga, Vishal Chudasama, Pankaj Wasnik et al.

Real-world object detection must operate in evolving environments where new classes emerge, domains shift, and unseen objects must be identified as "unknown": all without accessing prior data. We introduce Evolving World Object Detection (EWOD), a paradigm coupling incremental learning, domain adaptation, and unknown detection under exemplar-free constraints. To tackle EWOD, we propose EW-DETR framework that augments DETR-based detectors with three synergistic modules: Incremental LoRA Adapters for exemplar-free incremental learning under evolving domains; a Query-Norm Objectness Adapter that decouples objectness-aware features from DETR decoder queries; and Entropy-Aware Unknown Mixing for calibrated unknown detection. This framework generalises across DETR-based detectors, enabling state-of-the-art RF-DETR to operate effectively in evolving-world settings. We also introduce FOGS (Forgetting, Openness, Generalisation Score) to holistically evaluate performance across these dimensions. Extensive experiments on Pascal Series and Diverse Weather benchmarks show EW-DETR outperforms other methods, improving FOGS by 57.24%.

Aniket Pal, Ajoy Mondal, Minesh Mathew et al.

The proliferation of MultiLingual Visual Question Answering (MLVQA) benchmarks augments the capabilities of large language models (LLMs) and multi-modal LLMs, thereby enabling them to adeptly capture the intricate linguistic subtleties and visual complexities inherent across diverse languages. Despite its potential, the current MLVQA model struggles to fully utilize its capabilities when dealing with the extensive variety of handwritten documents. This article delineates HW-MLVQA, an avant-garde VQA benchmark meticulously crafted to mitigate the dearth of authentic Multilingual Handwritten document comprehension. HW-MLVQA encompasses an extensive collection of 1,600 handwritten Pages complemented by 2,400 question-answers. Furthermore, it provides a robust benchmark evaluation framework spanning three distinct modalities: text, image, and an integrated image & text modality. To simulate authentic real-world contexts devoid of ground truth textual transcriptions, we facilitates a rigorous assessment of proprietary and open-source OCR models. The benchmark aspires to facilitate pivotal advancements in multilingual handwritten document interpretation, fostering innovation and scholarly inquiry within this specialized domain.

Arpit Bahety, Rohit Saluja, Ravi Kiran Sarvadevabhatla et al.

Assessing the number of street trees is essential for evaluating urban greenery and can help municipalities employ solutions to identify tree-starved streets. It can also help identify roads with different levels of deforestation and afforestation over time. Yet, there has been little work in the area of street trees quantification. This work first explains a data collection setup carefully designed for counting roadside trees. We then describe a unique annotation procedure aimed at robustly detecting and quantifying trees. We work on a dataset of around 1300 Indian road scenes annotated with over 2500 street trees. We additionally use the five held-out videos covering 25 km of roads for counting trees. We finally propose a street tree detection, counting, and visualization framework using current object detectors and a novel yet simple counting algorithm owing to the thoughtful collection setup. We find that the high-level visualizations based on the density of trees on the routes and Kernel Density Ranking (KDR) provide a quick, accurate, and inexpensive way to recognize tree-starved streets. We obtain a tree detection mAP of 83.74% on the test images, which is a 2.73% improvement over our baseline. We propose Tree Count Density Classification Accuracy (TCDCA) as an evaluation metric to measure tree density. We obtain TCDCA of 96.77% on the test videos, with a remarkable improvement of 22.58% over baseline, and demonstrate that our counting module's performance is close to human level. Source code: https://github.com/iHubData-Mobility/public-tree-counting.

Sindhu B Hegde, K R Prajwal, Rudrabha Mukhopadhyay et al.

In this work, we re-think the task of speech enhancement in unconstrained real-world environments. Current state-of-the-art methods use only the audio stream and are limited in their performance in a wide range of real-world noises. Recent works using lip movements as additional cues improve the quality of generated speech over "audio-only" methods. But, these methods cannot be used for several applications where the visual stream is unreliable or completely absent. We propose a new paradigm for speech enhancement by exploiting recent breakthroughs in speech-driven lip synthesis. Using one such model as a teacher network, we train a robust student network to produce accurate lip movements that mask away the noise, thus acting as a "visual noise filter". The intelligibility of the speech enhanced by our pseudo-lip approach is comparable (< 3% difference) to the case of using real lips. This implies that we can exploit the advantages of using lip movements even in the absence of a real video stream. We rigorously evaluate our model using quantitative metrics as well as human evaluations. Additional ablation studies and a demo video on our website containing qualitative comparisons and results clearly illustrate the effectiveness of our approach. We provide a demo video which clearly illustrates the effectiveness of our proposed approach on our website: \url{http://cvit.iiit.ac.in/research/projects/cvit-projects/visual-speech-enhancement-without-a-real-visual-stream}. The code and models are also released for future research: \url{https://github.com/Sindhu-Hegde/pseudo-visual-speech-denoising}.

Prajwal K R, Rudrabha Mukhopadhyay, Jerin Philip et al.

In light of the recent breakthroughs in automatic machine translation systems, we propose a novel approach that we term as "Face-to-Face Translation". As today's digital communication becomes increasingly visual, we argue that there is a need for systems that can automatically translate a video of a person speaking in language A into a target language B with realistic lip synchronization. In this work, we create an automatic pipeline for this problem and demonstrate its impact on multiple real-world applications. First, we build a working speech-to-speech translation system by bringing together multiple existing modules from speech and language. We then move towards "Face-to-Face Translation" by incorporating a novel visual module, LipGAN for generating realistic talking faces from the translated audio. Quantitative evaluation of LipGAN on the standard LRW test set shows that it significantly outperforms existing approaches across all standard metrics. We also subject our Face-to-Face Translation pipeline, to multiple human evaluations and show that it can significantly improve the overall user experience for consuming and interacting with multimodal content across languages. Code, models and demo video are made publicly available. Demo video: https://www.youtube.com/watch?v=aHG6Oei8jF0 Code and models: https://github.com/Rudrabha/LipGAN

Praveen Krishnan, C. V. Jawahar

Generating synthetic images is an art which emulates the natural process of image generation in a closest possible manner. In this work, we exploit such a framework for data generation in handwritten domain. We render synthetic data using open source fonts and incorporate data augmentation schemes. As part of this work, we release 9M synthetic handwritten word image corpus which could be useful for training deep network architectures and advancing the performance in handwritten word spotting and recognition tasks.

Darshan Singh S, Anchit Gupta, C. V. Jawahar et al.

Over the last decade, online lecture videos have become increasingly popular and have experienced a meteoric rise during the pandemic. However, video-language research has primarily focused on instructional videos or movies, and tools to help students navigate the growing online lectures are lacking. Our first contribution is to facilitate research in the educational domain, by introducing AVLectures, a large-scale dataset consisting of 86 courses with over 2,350 lectures covering various STEM subjects. Each course contains video lectures, transcripts, OCR outputs for lecture frames, and optionally lecture notes, slides, assignments, and related educational content that can inspire a variety of tasks. Our second contribution is introducing video lecture segmentation that splits lectures into bite-sized topics that show promise in improving learner engagement. We formulate lecture segmentation as an unsupervised task that leverages visual, textual, and OCR cues from the lecture, while clip representations are fine-tuned on a pretext self-supervised task of matching the narration with the temporally aligned visual content. We use these representations to generate segments using a temporally consistent 1-nearest neighbor algorithm, TW-FINCH. We evaluate our method on 15 courses and compare it against various visual and textual baselines, outperforming all of them. Our comprehensive ablation studies also identify the key factors driving the success of our approach.

Sindhu Hegde, Rudrabha Mukhopadhyay, C. V. Jawahar et al.

In this paper, we introduce a novel approach to address the task of synthesizing speech from silent videos of any in-the-wild speaker solely based on lip movements. The traditional approach of directly generating speech from lip videos faces the challenge of not being able to learn a robust language model from speech alone, resulting in unsatisfactory outcomes. To overcome this issue, we propose incorporating noisy text supervision using a state-of-the-art lip-to-text network that instills language information into our model. The noisy text is generated using a pre-trained lip-to-text model, enabling our approach to work without text annotations during inference. We design a visual text-to-speech network that utilizes the visual stream to generate accurate speech, which is in-sync with the silent input video. We perform extensive experiments and ablation studies, demonstrating our approach's superiority over the current state-of-the-art methods on various benchmark datasets. Further, we demonstrate an essential practical application of our method in assistive technology by generating speech for an ALS patient who has lost the voice but can make mouth movements. Our demo video, code, and additional details can be found at \url{http://cvit.iiit.ac.in/research/projects/cvit-projects/ms-l2s-itw}.

Chirag Parikh, Rohit Saluja, C. V. Jawahar et al.

Intelligent vehicle systems require a deep understanding of the interplay between road conditions, surrounding entities, and the ego vehicle's driving behavior for safe and efficient navigation. This is particularly critical in developing countries where traffic situations are often dense and unstructured with heterogeneous road occupants. Existing datasets, predominantly geared towards structured and sparse traffic scenarios, fall short of capturing the complexity of driving in such environments. To fill this gap, we present IDD-X, a large-scale dual-view driving video dataset. With 697K bounding boxes, 9K important object tracks, and 1-12 objects per video, IDD-X offers comprehensive ego-relative annotations for multiple important road objects covering 10 categories and 19 explanation label categories. The dataset also incorporates rearview information to provide a more complete representation of the driving environment. We also introduce custom-designed deep networks aimed at multiple important object localization and per-object explanation prediction. Overall, our dataset and introduced prediction models form the foundation for studying how road conditions and surrounding entities affect driving behavior in complex traffic situations.

Ekansh Chauhan, Amit Sharma, Megha S Uppin et al.

The effective management of brain tumors relies on precise typing, subtyping, and grading. This study advances patient care with findings from rigorous multiple instance learning experimentations across various feature extractors and aggregators in brain tumor histopathology. It establishes new performance benchmarks in glioma subtype classification across multiple datasets, including a novel dataset focused on the Indian demographic (IPD- Brain), providing a valuable resource for existing research. Using a ResNet-50, pretrained on histopathology datasets for feature extraction, combined with the Double-Tier Feature Distillation (DTFD) feature aggregator, our approach achieves state-of-the-art AUCs of 88.08 on IPD-Brain and 95.81 on the TCGA-Brain dataset, respectively, for three-way glioma subtype classification. Moreover, it establishes new benchmarks in grading and detecting IHC molecular biomarkers (IDH1R132H, TP53, ATRX, Ki-67) through H&E stained whole slide images for the IPD-Brain dataset. The work also highlights a significant correlation between the model decision-making processes and the diagnostic reasoning of pathologists, underscoring its capability to mimic professional diagnostic procedures.

Ekansh Chauhan, Anila Sharma, Amit Sharma et al.

Breast cancer, the most common malignancy among women, requires precise detection and classification for effective treatment. Immunohistochemistry (IHC) biomarkers like HER2, ER, and PR are critical for identifying breast cancer subtypes. However, traditional IHC classification relies on pathologists' expertise, making it labor-intensive and subject to significant inter-observer variability. To address these challenges, this study introduces the India Pathology Breast Cancer Dataset (IPD-Breast), comprising of 1,272 IHC slides (HER2, ER, and PR) aimed at automating receptor status classification. The primary focus is on developing predictive models for HER2 3-way classification (0, Low, High) to enhance prognosis. Evaluation of multiple deep learning models revealed that an end-to-end ConvNeXt network utilizing low-resolution IHC images achieved an AUC, F1, and accuracy of 91.79%, 83.52%, and 83.56%, respectively, for 3-way classification, outperforming patch-based methods by over 5.35% in F1 score. This study highlights the potential of simple yet effective deep learning techniques to significantly improve accuracy and reproducibility in breast cancer classification, supporting their integration into clinical workflows for better patient outcomes.

Suyash Maniyar, Vishvesh Trivedi, Ajoy Mondal et al.

Lecture slide element detection and retrieval are key problems in slide understanding. Training effective models for these tasks often depends on extensive manual annotation. However, annotating large volumes of lecture slides for supervised training is labor intensive and requires domain expertise. To address this, we propose a large language model (LLM)-guided synthetic lecture slide generation pipeline, SynLecSlideGen, which produces high-quality, coherent and realistic slides. We also create an evaluation benchmark, namely RealSlide by manually annotating 1,050 real lecture slides. To assess the utility of our synthetic slides, we perform few-shot transfer learning on real data using models pre-trained on them. Experimental results show that few-shot transfer learning with pretraining on synthetic slides significantly improves performance compared to training only on real data. This demonstrates that synthetic data can effectively compensate for limited labeled lecture slides. The code and resources of our work are publicly available on our project website: https://synslidegen.github.io/.

Ruthvik Bokkasam, Shankar Gangisetty, A. H. Abdul Hafez et al.

With the rapid advancements in autonomous driving, accurately predicting pedestrian behavior has become essential for ensuring safety in complex and unpredictable traffic conditions. The growing interest in this challenge highlights the need for comprehensive datasets that capture unstructured environments, enabling the development of more robust prediction models to enhance pedestrian safety and vehicle navigation. In this paper, we introduce an Indian driving pedestrian dataset designed to address the complexities of modeling pedestrian behavior in unstructured environments, such as illumination changes, occlusion of pedestrians, unsignalized scene types and vehicle-pedestrian interactions. The dataset provides high-level and detailed low-level comprehensive annotations focused on pedestrians requiring the ego-vehicle's attention. Evaluation of the state-of-the-art intention prediction methods on our dataset shows a significant performance drop of up to $\mathbf{15\%}$, while trajectory prediction methods underperform with an increase of up to $\mathbf{1208}$ MSE, defeating standard pedestrian datasets. Additionally, we present exhaustive quantitative and qualitative analysis of intention and trajectory baselines. We believe that our dataset will open new challenges for the pedestrian behavior research community to build robust models. Project Page: https://cvit.iiit.ac.in/research/projects/cvit-projects/iddped

Aniket Pal, Sanket Biswas, Alloy Das et al.

Understanding and reasoning over academic handwritten notes remains a challenge in document AI, particularly for mathematical equations, diagrams, and scientific notations. Existing visual question answering (VQA) benchmarks focus on printed or structured handwritten text, limiting generalization to real-world note-taking. To address this, we introduce NoTeS-Bank, an evaluation benchmark for Neural Transcription and Search in note-based question answering. NoTeS-Bank comprises complex notes across multiple domains, requiring models to process unstructured and multimodal content. The benchmark defines two tasks: (1) Evidence-Based VQA, where models retrieve localized answers with bounding-box evidence, and (2) Open-Domain VQA, where models classify the domain before retrieving relevant documents and answers. Unlike classical Document VQA datasets relying on optical character recognition (OCR) and structured data, NoTeS-BANK demands vision-language fusion, retrieval, and multimodal reasoning. We benchmark state-of-the-art Vision-Language Models (VLMs) and retrieval frameworks, exposing structured transcription and reasoning limitations. NoTeS-Bank provides a rigorous evaluation with NDCG@5, MRR, Recall@K, IoU, and ANLS, establishing a new standard for visual document understanding and reasoning.

Zakaria Laskar, Tomas Vojir, Matej Grcic et al.

Before deployment in the real-world deep neural networks require thorough evaluation of how they handle both knowns, inputs represented in the training data, and unknowns (anomalies). This is especially important for scene understanding tasks with safety critical applications, such as in autonomous driving. Existing datasets allow evaluation of only knowns or unknowns - but not both, which is required to establish "in the wild" suitability of deep neural network models. To bridge this gap, we propose a novel anomaly segmentation dataset, ISSU, that features a diverse set of anomaly inputs from cluttered real-world environments. The dataset is twice larger than existing anomaly segmentation datasets, and provides a training, validation and test set for controlled in-domain evaluation. The test set consists of a static and temporal part, with the latter comprised of videos. The dataset provides annotations for both closed-set (knowns) and anomalies, enabling closed-set and open-set evaluation. The dataset covers diverse conditions, such as domain and cross-sensor shift, illumination variation and allows ablation of anomaly detection methods with respect to these variations. Evaluation results of current state-of-the-art methods confirm the need for improvements especially in domain-generalization, small and large object segmentation.

Shankar Gangisetty, Abdul Wasi, Shyam Nandan Rai et al.

The recent surge in the vehicle market has led to an alarming increase in road accidents. This underscores the critical importance of enhancing road safety measures, particularly for vulnerable road users like motorcyclists. Hence, we introduce the rider intention prediction (RIP) competition that aims to address challenges in rider safety by proactively predicting maneuvers before they occur, thereby strengthening rider safety. This capability enables the riders to react to the potential incorrect maneuvers flagged by advanced driver assistance systems (ADAS). We collect a new dataset, namely, rider action anticipation dataset (RAAD) for the competition consisting of two tasks: single-view RIP and multi-view RIP. The dataset incorporates a spectrum of traffic conditions and challenging navigational maneuvers on roads with varying lighting conditions. For the competition, we received seventy-five registrations and five team submissions for inference of which we compared the methods of the top three performing teams on both the RIP tasks: one state-space model (Mamba2) and two learning-based approaches (SVM and CNN-LSTM). The results indicate that the state-space model outperformed the other methods across the entire dataset, providing a balanced performance across maneuver classes. The SVM-based RIP method showed the second-best performance when using random sampling and SMOTE. However, the CNN-LSTM method underperformed, primarily due to class imbalance issues, particularly struggling with minority classes. This paper details the proposed RAAD dataset and provides a summary of the submissions for the RIP 2024 competition.

Vaishnavi Khindkar, Vineeth Balasubramanian, Chetan Arora et al.

With the increased importance of autonomous navigation systems has come an increasing need to protect the safety of Vulnerable Road Users (VRUs) such as pedestrians. Predicting pedestrian intent is one such challenging task, where prior work predicts the binary cross/no-cross intention with a fusion of visual and motion features. However, there has been no effort so far to hedge such predictions with human-understandable reasons. We address this issue by introducing a novel problem setting of exploring the intuitive reasoning behind a pedestrian's intent. In particular, we show that predicting the 'WHY' can be very useful in understanding the 'WHAT'. To this end, we propose a novel, reason-enriched PIE++ dataset consisting of multi-label textual explanations/reasons for pedestrian intent. We also introduce a novel multi-task learning framework called MINDREAD, which leverages a cross-modal representation learning framework for predicting pedestrian intent as well as the reason behind the intent. Our comprehensive experiments show significant improvement of 5.6% and 7% in accuracy and F1-score for the task of intent prediction on the PIE++ dataset using MINDREAD. We also achieved a 4.4% improvement in accuracy on a commonly used JAAD dataset. Extensive evaluation using quantitative/qualitative metrics and user studies shows the effectiveness of our approach.

Aniket Pal, Ajoy Mondal, C. V. Jawahar

Question-answering handwritten documents is a challenging task with numerous real-world applications. This paper proposes a novel recognition-based approach that improves upon the previous state-of-the-art on the HW-SQuAD and BenthamQA datasets. Our model incorporates transformer-based document retrieval and ensemble methods at the model level, achieving an Exact Match score of 82.02% and 69% in HW-SQuAD and BenthamQA datasets, respectively, surpassing the previous best recognition-based approach by 10.89% and 3%. We also enhance the document retrieval component, boosting the top-5 retrieval accuracy from 90% to 95.30%. Our results demonstrate the significance of our proposed approach in advancing question answering on handwritten documents. The code and trained models will be publicly available to facilitate future research in this critical area of natural language.

Soumya Jahagirdar, Minesh Mathew, Dimosthenis Karatzas et al.

Researchers have extensively studied the field of vision and language, discovering that both visual and textual content is crucial for understanding scenes effectively. Particularly, comprehending text in videos holds great significance, requiring both scene text understanding and temporal reasoning. This paper focuses on exploring two recently introduced datasets, NewsVideoQA and M4-ViteVQA, which aim to address video question answering based on textual content. The NewsVideoQA dataset contains question-answer pairs related to the text in news videos, while M4-ViteVQA comprises question-answer pairs from diverse categories like vlogging, traveling, and shopping. We provide an analysis of the formulation of these datasets on various levels, exploring the degree of visual understanding and multi-frame comprehension required for answering the questions. Additionally, the study includes experimentation with BERT-QA, a text-only model, which demonstrates comparable performance to the original methods on both datasets, indicating the shortcomings in the formulation of these datasets. Furthermore, we also look into the domain adaptation aspect by examining the effectiveness of training on M4-ViteVQA and evaluating on NewsVideoQA and vice-versa, thereby shedding light on the challenges and potential benefits of out-of-domain training.

Jobin K. V., Ajoy Mondal, C. V. Jawahar

Slide presentations are an effective and efficient tool used by the teaching community for classroom communication. However, this teaching model can be challenging for blind and visually impaired (VI) students. The VI student required personal human assistance for understand the presented slide. This shortcoming motivates us to design a Classroom Slide Narration System (CSNS) that generates audio descriptions corresponding to the slide content. This problem poses as an image-to-markup language generation task. The initial step is to extract logical regions such as title, text, equation, figure, and table from the slide image. In the classroom slide images, the logical regions are distributed based on the location of the image. To utilize the location of the logical regions for slide image segmentation, we propose the architecture, Classroom Slide Segmentation Network (CSSN). The unique attributes of this architecture differs from most other semantic segmentation networks. Publicly available benchmark datasets such as WiSe and SPaSe are used to validate the performance of our segmentation architecture. We obtained 9.54 segmentation accuracy improvement in WiSe dataset. We extract content (information) from the slide using four well-established modules such as optical character recognition (OCR), figure classification, equation description, and table structure recognizer. With this information, we build a Classroom Slide Narration System (CSNS) to help VI students understand the slide content. The users have given better feedback on the quality output of the proposed CSNS in comparison to existing systems like Facebooks Automatic Alt-Text (AAT) and Tesseract.

Sanjana Gunna, Rohit Saluja, C. V. Jawahar

Scene-text recognition is remarkably better in Latin languages than the non-Latin languages due to several factors like multiple fonts, simplistic vocabulary statistics, updated data generation tools, and writing systems. This paper examines the possible reasons for low accuracy by comparing English datasets with non-Latin languages. We compare various features like the size (width and height) of the word images and word length statistics. Over the last decade, generating synthetic datasets with powerful deep learning techniques has tremendously improved scene-text recognition. Several controlled experiments are performed on English, by varying the number of (i) fonts to create the synthetic data and (ii) created word images. We discover that these factors are critical for the scene-text recognition systems. The English synthetic datasets utilize over 1400 fonts while Arabic and other non-Latin datasets utilize less than 100 fonts for data generation. Since some of these languages are a part of different regions, we garner additional fonts through a region-based search to improve the scene-text recognition models in Arabic and Devanagari. We improve the Word Recognition Rates (WRRs) on Arabic MLT-17 and MLT-19 datasets by 24.54% and 2.32% compared to previous works or baselines. We achieve WRR gains of 7.88% and 3.72% for IIIT-ILST and MLT-19 Devanagari datasets.

Sanjana Gunna, Rohit Saluja, C. V. Jawahar

Scene text recognition in low-resource Indian languages is challenging because of complexities like multiple scripts, fonts, text size, and orientations. In this work, we investigate the power of transfer learning for all the layers of deep scene text recognition networks from English to two common Indian languages. We perform experiments on the conventional CRNN model and STAR-Net to ensure generalisability. To study the effect of change in different scripts, we initially run our experiments on synthetic word images rendered using Unicode fonts. We show that the transfer of English models to simple synthetic datasets of Indian languages is not practical. Instead, we propose to apply transfer learning techniques among Indian languages due to similarity in their n-gram distributions and visual features like the vowels and conjunct characters. We then study the transfer learning among six Indian languages with varying complexities in fonts and word length statistics. We also demonstrate that the learned features of the models transferred from other Indian languages are visually closer (and sometimes even better) to the individual model features than those transferred from English. We finally set new benchmarks for scene-text recognition on Hindi, Telugu, and Malayalam datasets from IIIT-ILST and Bangla dataset from MLT-17 by achieving 6%, 5%, 2%, and 23% gains in Word Recognition Rates (WRRs) compared to previous works. We further improve the MLT-17 Bangla results by plugging in a novel correction BiLSTM into our model. We additionally release a dataset of around 440 scene images containing 500 Gujarati and 2535 Tamil words. WRRs improve over the baselines by 8%, 4%, 5%, and 3% on the MLT-19 Hindi and Bangla datasets and the Gujarati and Tamil datasets.