Ravi Kiran Sarvadevabhatla

Neel Trivedi, Ravi Kiran Sarvadevabhatla

Pose-based action recognition is predominantly tackled by approaches which treat the input skeleton in a monolithic fashion, i.e. joints in the pose tree are processed as a whole. However, such approaches ignore the fact that action categories are often characterized by localized action dynamics involving only small subsets of part joint groups involving hands (e.g. `Thumbs up') or legs (e.g. `Kicking'). Although part-grouping based approaches exist, each part group is not considered within the global pose frame, causing such methods to fall short. Further, conventional approaches employ independent modality streams (e.g. joint, bone, joint velocity, bone velocity) and train their network multiple times on these streams, which massively increases the number of training parameters. To address these issues, we introduce PSUMNet, a novel approach for scalable and efficient pose-based action recognition. At the representation level, we propose a global frame based part stream approach as opposed to conventional modality based streams. Within each part stream, the associated data from multiple modalities is unified and consumed by the processing pipeline. Experimentally, PSUMNet achieves state of the art performance on the widely used NTURGB+D 60/120 dataset and dense joint skeleton dataset NTU 60-X/120-X. PSUMNet is highly efficient and outperforms competing methods which use 100%-400% more parameters. PSUMNet also generalizes to the SHREC hand gesture dataset with competitive performance. Overall, PSUMNet's scalability, performance and efficiency makes it an attractive choice for action recognition and for deployment on compute-restricted embedded and edge devices. Code and pretrained models can be accessed at https://github.com/skelemoa/psumnet

Sai Shashank Kalakonda, Shubh Maheshwari, Ravi Kiran Sarvadevabhatla

We introduce Action-GPT, a plug-and-play framework for incorporating Large Language Models (LLMs) into text-based action generation models. Action phrases in current motion capture datasets contain minimal and to-the-point information. By carefully crafting prompts for LLMs, we generate richer and fine-grained descriptions of the action. We show that utilizing these detailed descriptions instead of the original action phrases leads to better alignment of text and motion spaces. We introduce a generic approach compatible with stochastic (e.g. VAE-based) and deterministic (e.g. MotionCLIP) text-to-motion models. In addition, the approach enables multiple text descriptions to be utilized. Our experiments show (i) noticeable qualitative and quantitative improvement in the quality of synthesized motions, (ii) benefits of utilizing multiple LLM-generated descriptions, (iii) suitability of the prompt function, and (iv) zero-shot generation capabilities of the proposed approach. Project page: https://actiongpt.github.io

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.

Kushagra Srivastava, Dhruv Patel, Aditya Kumar Jha et al.

Unmanned Aerial Vehicle (UAV) based remote sensing system incorporated with computer vision has demonstrated potential for assisting building construction and in disaster management like damage assessment during earthquakes. The vulnerability of a building to earthquake can be assessed through inspection that takes into account the expected damage progression of the associated component and the component's contribution to structural system performance. Most of these inspections are done manually, leading to high utilization of manpower, time, and cost. This paper proposes a methodology to automate these inspections through UAV-based image data collection and a software library for post-processing that helps in estimating the seismic structural parameters. The key parameters considered here are the distances between adjacent buildings, building plan-shape, building plan area, objects on the rooftop and rooftop layout. The accuracy of the proposed methodology in estimating the above-mentioned parameters is verified through field measurements taken using a distance measuring sensor and also from the data obtained through Google Earth. Additional details and code can be accessed from https://uvrsabi.github.io/ .

Sai Shashank Kalakonda, Shubh Maheshwari, Ravi Kiran Sarvadevabhatla

We introduce MoRAG, a novel multi-part fusion based retrieval-augmented generation strategy for text-based human motion generation. The method enhances motion diffusion models by leveraging additional knowledge obtained through an improved motion retrieval process. By effectively prompting large language models (LLMs), we address spelling errors and rephrasing issues in motion retrieval. Our approach utilizes a multi-part retrieval strategy to improve the generalizability of motion retrieval across the language space. We create diverse samples through the spatial composition of the retrieved motions. Furthermore, by utilizing low-level, part-specific motion information, we can construct motion samples for unseen text descriptions. Our experiments demonstrate that our framework can serve as a plug-and-play module, improving the performance of motion diffusion models. Code, pretrained models and sample videos are available at: https://motion-rag.github.io/

Oikantik Nath, Sahithi Kukkala, Mitesh Khapra et al.

Document layout analysis is essential for downstream tasks such as information retrieval, extraction, OCR, and digitization. However, existing large-scale datasets like PubLayNet and DocBank lack fine-grained region labels and multilingual diversity, making them insufficient for representing complex document layouts. In contrast, human-annotated datasets such as M6Doc and D4LA offer richer labels and greater domain diversity, but are too small to train robust models and lack adequate multilingual coverage. This gap is especially pronounced for Indic documents, which encompass diverse scripts yet remain underrepresented in current datasets, further limiting progress in this space. To address these shortcomings, we introduce IndicDLP, a large-scale foundational document layout dataset spanning 11 representative Indic languages alongside English and 12 common document domains. Additionally, we curate UED-mini, a dataset derived from DocLayNet and M6Doc, to enhance pretraining and provide a solid foundation for Indic layout models. Our experiments demonstrate that fine-tuning existing English models on IndicDLP significantly boosts performance, validating its effectiveness. Moreover, models trained on IndicDLP generalize well beyond Indic layouts, making it a valuable resource for document digitization. This work bridges gaps in scale, diversity, and annotation granularity, driving inclusive and efficient document understanding.

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.

Abhinav Raundhal, Gaurav Behera, P J Narayanan et al.

Text as signs, labels, or instructions is a critical element of real-world scenes as they can convey important contextual information. 3D representations such as 3D Gaussian Splatting (3DGS) struggle to preserve fine-grained text details, while achieving high visual fidelity. Small errors in textual element reconstruction can lead to significant semantic loss. We propose STRinGS, a text-aware, selective refinement framework to address this issue for 3DGS reconstruction. Our method treats text and non-text regions separately, refining text regions first and merging them with non-text regions later for full-scene optimization. STRinGS produces sharp, readable text even in challenging configurations. We introduce a text readability measure OCR Character Error Rate (CER) to evaluate the efficacy on text regions. STRinGS results in a 63.6% relative improvement over 3DGS at just 7K iterations. We also introduce a curated dataset STRinGS-360 with diverse text scenarios to evaluate text readability in 3D reconstruction. Our method and dataset together push the boundaries of 3D scene understanding in text-rich environments, paving the way for more robust text-aware reconstruction methods.

Vaibhav Agrawal, Rishubh Parihar, Pradhaan Bhat et al.

We identify occlusion reasoning as a fundamental yet overlooked aspect for 3D layout-conditioned generation. It is essential for synthesizing partially occluded objects with depth-consistent geometry and scale. While existing methods can generate realistic scenes that follow input layouts, they often fail to model precise inter-object occlusions. We propose SeeThrough3D, a model for 3D layout conditioned generation that explicitly models occlusions. We introduce an occlusion-aware 3D scene representation (OSCR), where objects are depicted as translucent 3D boxes placed within a virtual environment and rendered from desired camera viewpoint. The transparency encodes hidden object regions, enabling the model to reason about occlusions, while the rendered viewpoint provides explicit camera control during generation. We condition a pretrained flow based text-to-image image generation model by introducing a set of visual tokens derived from our rendered 3D representation. Furthermore, we apply masked self-attention to accurately bind each object bounding box to its corresponding textual description, enabling accurate generation of multiple objects without object attribute mixing. To train the model, we construct a synthetic dataset with diverse multi-object scenes with strong inter-object occlusions. SeeThrough3D generalizes effectively to unseen object categories and enables precise 3D layout control with realistic occlusions and consistent camera control.

Pratyush Jena, Amal Joseph, Arnav Sharma et al.

Binarization is a popular first step towards text extraction in historical artifacts. Stone inscription images pose severe challenges for binarization due to poor contrast between etched characters and the stone background, non-uniform surface degradation, distracting artifacts, and highly variable text density and layouts. These conditions frequently cause existing binarization techniques to fail and struggle to isolate coherent character regions. Many approaches sub-divide the image into patches to improve text fragment resolution and improve binarization performance. With this in mind, we present a robust and adaptive patching strategy to binarize challenging Indic inscriptions. The patches from our approach are used to train an Attention U-Net for binarization. The attention mechanism allows the model to focus on subtle structural cues, while our dynamic sampling and patch selection method ensures that the model learns to overcome surface noise and layout irregularities. We also introduce a carefully annotated, pixel-precise dataset of Indic stone inscriptions at the character-fragment level. We demonstrate that our novel patching mechanism significantly boosts binarization performance across classical and deep learning baselines. Despite training only on single script Indic dataset, our model exhibits strong zero-shot generalization to other Indic and non-indic scripts, highlighting its robustness and script-agnostic generalization capabilities. By producing clean, structured representations of inscription content, our method lays the foundation for downstream tasks such as script identification, OCR, and historical text analysis. Project page: https://ihdia.iiit.ac.in/shilalekhya-binarization/

Chirag Parikh, Siddhi Pravin Lipare, Ravi Kiran Sarvadevabhatla

Existing video-language models can generate factual descriptions of road events but lack control over how these events are expressed: their tone, urgency, or style. This limits deployment in communication-critical settings where the effectiveness of a message depends on both content and presentation, not just factual accuracy. To mitigate this, we introduce a comprehensive dataset-model-evaluation suite for tone-controllable road video captioning. Our human-validated data generation pipeline expands road-video corpora with diverse tonal annotations and multi-tone captions, yielding the RoadTones-51K dataset. We propose RoadTones-VL-CoT, a controllable video-to-text model that also generates tone-conditioned Chain-of-Thought intermediate drafts for interpretability. We also introduce RoadTones-Eval, a new evaluation suite that jointly measures factual consistency and tone adherence. In addition, we conducted a user study whose results validate caption quality, tone control, and factual consistency. Together, these contributions lay the foundation for context-sensitive tone-controllable video captioning.

Sravya Vardhani Shivapuja, Ashwin Gopinath, Ayush Gupta et al.

The data distribution in popular crowd counting datasets is typically heavy tailed and discontinuous. This skew affects all stages within the pipelines of deep crowd counting approaches. Specifically, the approaches exhibit unacceptably large standard deviation wrt statistical measures (MSE, MAE). To address such concerns in a holistic manner, we make two fundamental contributions. Firstly, we modify the training pipeline to accommodate the knowledge of dataset skew. To enable principled and balanced minibatch sampling, we propose a novel smoothed Bayesian binning approach. More specifically, we propose a novel cost function which can be readily incorporated into existing crowd counting deep networks to encourage bin-aware optimization. As the second contribution, we introduce additional performance measures which are more inclusive and throw light on various comparative performance aspects of the deep networks. We also show that our binning-based modifications retain their superiority wrt the newly proposed performance measures. Overall, our contributions enable a practically useful and detail-oriented characterization of performance for crowd counting approaches.

Chirag Parikh, Deepti Rawat, Rakshitha R. T. et al.

We introduce RoadSocial, a large-scale, diverse VideoQA dataset tailored for generic road event understanding from social media narratives. Unlike existing datasets limited by regional bias, viewpoint bias and expert-driven annotations, RoadSocial captures the global complexity of road events with varied geographies, camera viewpoints (CCTV, handheld, drones) and rich social discourse. Our scalable semi-automatic annotation framework leverages Text LLMs and Video LLMs to generate comprehensive question-answer pairs across 12 challenging QA tasks, pushing the boundaries of road event understanding. RoadSocial is derived from social media videos spanning 14M frames and 414K social comments, resulting in a dataset with 13.2K videos, 674 tags and 260K high-quality QA pairs. We evaluate 18 Video LLMs (open-source and proprietary, driving-specific and general-purpose) on our road event understanding benchmark. We also demonstrate RoadSocial's utility in improving road event understanding capabilities of general-purpose Video LLMs.

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.

Anurag Bagchi, Jazib Mahmood, Dolton Fernandes et al.

State of the art architectures for untrimmed video Temporal Action Localization (TAL) have only considered RGB and Flow modalities, leaving the information-rich audio modality totally unexploited. Audio fusion has been explored for the related but arguably easier problem of trimmed (clip-level) action recognition. However, TAL poses a unique set of challenges. In this paper, we propose simple but effective fusion-based approaches for TAL. To the best of our knowledge, our work is the first to jointly consider audio and video modalities for supervised TAL. We experimentally show that our schemes consistently improve performance for state of the art video-only TAL approaches. Specifically, they help achieve new state of the art performance on large-scale benchmark datasets - ActivityNet-1.3 (54.34 mAP@0.5) and THUMOS14 (57.18 mAP@0.5). Our experiments include ablations involving multiple fusion schemes, modality combinations and TAL architectures. Our code, models and associated data are available at https://github.com/skelemoa/tal-hmo.

Pranay Gupta, Divyanshu Sharma, Ravi Kiran Sarvadevabhatla

We introduce SynSE, a novel syntactically guided generative approach for Zero-Shot Learning (ZSL). Our end-to-end approach learns progressively refined generative embedding spaces constrained within and across the involved modalities (visual, language). The inter-modal constraints are defined between action sequence embedding and embeddings of Parts of Speech (PoS) tagged words in the corresponding action description. We deploy SynSE for the task of skeleton-based action sequence recognition. Our design choices enable SynSE to generalize compositionally, i.e., recognize sequences whose action descriptions contain words not encountered during training. We also extend our approach to the more challenging Generalized Zero-Shot Learning (GZSL) problem via a confidence-based gating mechanism. We are the first to present zero-shot skeleton action recognition results on the large-scale NTU-60 and NTU-120 skeleton action datasets with multiple splits. Our results demonstrate SynSE's state of the art performance in both ZSL and GZSL settings compared to strong baselines on the NTU-60 and NTU-120 datasets. The code and pretrained models are available at https://github.com/skelemoa/synse-zsl

Neel Trivedi, Anirudh Thatipelli, Ravi Kiran Sarvadevabhatla

The lack of fine-grained joints (facial joints, hand fingers) is a fundamental performance bottleneck for state of the art skeleton action recognition models. Despite this bottleneck, community's efforts seem to be invested only in coming up with novel architectures. To specifically address this bottleneck, we introduce two new pose based human action datasets - NTU60-X and NTU120-X. Our datasets extend the largest existing action recognition dataset, NTU-RGBD. In addition to the 25 body joints for each skeleton as in NTU-RGBD, NTU60-X and NTU120-X dataset includes finger and facial joints, enabling a richer skeleton representation. We appropriately modify the state of the art approaches to enable training using the introduced datasets. Our results demonstrate the effectiveness of these NTU-X datasets in overcoming the aforementioned bottleneck and improve state of the art performance, overall and on previously worst performing action categories. Code and pretrained models can be found at https://github.com/skelemoa/ntu-x .

Ravi Kiran Sarvadevabhatla, R. Venkatesh Babu

With a view to provide a user-friendly interface for designing, training and developing deep learning frameworks, we have developed Expresso, a GUI tool written in Python. Expresso is built atop Caffe, the open-source, prize-winning framework popularly used to develop Convolutional Neural Networks. Expresso provides a convenient wizard-like graphical interface which guides the user through various common scenarios -- data import, construction and training of deep networks, performing various experiments, analyzing and visualizing the results of these experiments. The multi-threaded nature of Expresso enables concurrent execution and notification of events related to the aforementioned scenarios. The GUI sub-components and inter-component interfaces in Expresso have been designed with extensibility in mind. We believe Expresso's flexibility and ease of use will come in handy to researchers, newcomers and seasoned alike, in their explorations related to deep learning.

Nikhil Bansal, Kartik Gupta, Kiruthika Kannan et al.

Pictionary, the popular sketch-based guessing game, provides an opportunity to analyze shared goal cooperative game play in restricted communication settings. However, some players occasionally draw atypical sketch content. While such content is occasionally relevant in the game context, it sometimes represents a rule violation and impairs the game experience. To address such situations in a timely and scalable manner, we introduce DrawMon, a novel distributed framework for automatic detection of atypical sketch content in concurrently occurring Pictionary game sessions. We build specialized online interfaces to collect game session data and annotate atypical sketch content, resulting in AtyPict, the first ever atypical sketch content dataset. We use AtyPict to train CanvasNet, a deep neural atypical content detection network. We utilize CanvasNet as a core component of DrawMon. Our analysis of post deployment game session data indicates DrawMon's effectiveness for scalable monitoring and atypical sketch content detection. Beyond Pictionary, our contributions also serve as a design guide for customized atypical content response systems involving shared and interactive whiteboards. Code and datasets are available at https://drawm0n.github.io.

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.

Chirag Parikh, Ravi Shankar Mishra, Rohan Chandra et al.

Recognizing driving behaviors is important for downstream tasks such as reasoning, planning, and navigation. Existing video recognition approaches work well for common behaviors (e.g. "drive straight", "brake", "turn left/right"). However, the performance is sub-par for underrepresented/rare behaviors typically found in tail of the behavior class distribution. To address this shortcoming, we propose Transfer-LMR, a modular training routine for improving the recognition performance across all driving behavior classes. We extensively evaluate our approach on METEOR and HDD datasets that contain rich yet heavy-tailed distribution of driving behaviors and span diverse traffic scenarios. The experimental results demonstrate the efficacy of our approach, especially for recognizing underrepresented/rare driving behaviors.

Deepti Rawat, Keshav Gupta, Aryamaan Basu Roy et al.

Motorized two-wheelers are a prevalent and economical means of transportation, particularly in the Asia-Pacific region. However, hazardous driving practices such as triple riding and non-compliance with helmet regulations contribute significantly to accident rates. Addressing these violations through automated enforcement mechanisms can enhance traffic safety. In this paper, we propose DashCop, an end-to-end system for automated E-ticket generation. The system processes vehicle-mounted dashcam videos to detect two-wheeler traffic violations. Our contributions include: (1) a novel Segmentation and Cross-Association (SAC) module to accurately associate riders with their motorcycles, (2) a robust cross-association-based tracking algorithm optimized for the simultaneous presence of riders and motorcycles, and (3) the RideSafe-400 dataset, a comprehensive annotated dashcam video dataset for triple riding and helmet rule violations. Our system demonstrates significant improvements in violation detection, validated through extensive evaluations on the RideSafe-400 dataset.

Kushagra Srivastava, Damodar Datta Kancharla, Rizvi Tahereen et al.

Crack segmentation plays a crucial role in ensuring the structural integrity and seismic safety of civil structures. However, existing crack segmentation algorithms encounter challenges in maintaining accuracy with domain shifts across datasets. To address this issue, we propose a novel deep network that employs incremental training with unsupervised domain adaptation (UDA) using adversarial learning, without a significant drop in accuracy in the source domain. Our approach leverages an encoder-decoder architecture, consisting of both domain-invariant and domain-specific parameters. The encoder learns shared crack features across all domains, ensuring robustness to domain variations. Simultaneously, the decoder's domain-specific parameters capture domain-specific features unique to each domain. By combining these components, our model achieves improved crack segmentation performance. Furthermore, we introduce BuildCrack, a new crack dataset comparable to sub-datasets of the well-established CrackSeg9K dataset in terms of image count and crack percentage. We evaluate our proposed approach against state-of-the-art UDA methods using different sub-datasets of CrackSeg9K and our custom dataset. Our experimental results demonstrate a significant improvement in crack segmentation accuracy and generalization across target domains compared to other UDA methods - specifically, an improvement of 0.65 and 2.7 mIoU on source and target domains respectively.

Rohan Kumar, Jyothi Swaroopa Jinka, Ravi Kiran Sarvadevabhatla

Recognizing textual attributes such as bold, italic, underline and strikeout is essential for understanding text semantics, structure, and visual presentation. These attributes highlight key information, making them crucial for document analysis. Existing methods struggle with computational efficiency or adaptability in noisy, multilingual settings. To address this, we introduce TexTAR, a multi-task, context-aware Transformer for Textual Attribute Recognition (TAR). Our novel data selection pipeline enhances context awareness, and our architecture employs a 2D RoPE (Rotary Positional Embedding)-style mechanism to incorporate input context for more accurate attribute predictions. We also introduce MMTAD, a diverse, multilingual, multi-domain dataset annotated with text attributes across real-world documents such as legal records, notices, and textbooks. Extensive evaluations show TexTAR outperforms existing methods, demonstrating that contextual awareness contributes to state-of-the-art TAR performance.

Shubh Maheshwari, Debtanu Gupta, Ravi Kiran Sarvadevabhatla

We introduce MUGL, a novel deep neural model for large-scale, diverse generation of single and multi-person pose-based action sequences with locomotion. Our controllable approach enables variable-length generations customizable by action category, across more than 100 categories. To enable intra/inter-category diversity, we model the latent generative space using a Conditional Gaussian Mixture Variational Autoencoder. To enable realistic generation of actions involving locomotion, we decouple local pose and global trajectory components of the action sequence. We incorporate duration-aware feature representations to enable variable-length sequence generation. We use a hybrid pose sequence representation with 3D pose sequences sourced from videos and 3D Kinect-based sequences of NTU-RGBD-120. To enable principled comparison of generation quality, we employ suitably modified strong baselines during evaluation. Although smaller and simpler compared to baselines, MUGL provides better quality generations, paving the way for practical and controllable large-scale human action generation.

Rishabh Baghel, Abhishek Trivedi, Tejas Ravichandran et al.

We introduce MeronymNet, a novel hierarchical approach for controllable, part-based generation of multi-category objects using a single unified model. We adopt a guided coarse-to-fine strategy involving semantically conditioned generation of bounding box layouts, pixel-level part layouts and ultimately, the object depictions themselves. We use Graph Convolutional Networks, Deep Recurrent Networks along with custom-designed Conditional Variational Autoencoders to enable flexible, diverse and category-aware generation of 2-D objects in a controlled manner. The performance scores for generated objects reflect MeronymNet's superior performance compared to multiple strong baselines and ablative variants. We also showcase MeronymNet's suitability for controllable object generation and interactive object editing at various levels of structural and semantic granularity.

Samhita Kanaparthy, Manisha Padala, Sankarshan Damle et al.

Fairness across different demographic groups is an essential criterion for face-related tasks, Face Attribute Classification (FAC) being a prominent example. Apart from this trend, Federated Learning (FL) is increasingly gaining traction as a scalable paradigm for distributed training. Existing FL approaches require data homogeneity to ensure fairness. However, this assumption is too restrictive in real-world settings. We propose F3, a novel FL framework for fair FAC under data heterogeneity. F3 adopts multiple heuristics to improve fairness across different demographic groups without requiring data homogeneity assumption. We demonstrate the efficacy of F3 by reporting empirically observed fairness measures and accuracy guarantees on popular face datasets. Our results suggest that F3 strikes a practical balance between accuracy and fairness for FAC.

Prema Satish Sharan, Sowmya Aitha, Amandeep Kumar et al.

Handwritten documents are often characterized by dense and uneven layout. Despite advances, standard deep network based approaches for semantic layout segmentation are not robust to complex deformations seen across semantic regions. This phenomenon is especially pronounced for the low-resource Indic palm-leaf manuscript domain. To address the issue, we first introduce Indiscapes2, a new large-scale diverse dataset of Indic manuscripts with semantic layout annotations. Indiscapes2 contains documents from four different historical collections and is 150% larger than its predecessor, Indiscapes. We also propose a novel deep network Palmira for robust, deformation-aware instance segmentation of regions in handwritten manuscripts. We also report Hausdorff distance and its variants as a boundary-aware performance measure. Our experiments demonstrate that Palmira provides robust layouts, outperforms strong baseline approaches and ablative variants. We also include qualitative results on Arabic, South-East Asian and Hebrew historical manuscripts to showcase the generalization capability of Palmira.

Abhishek Trivedi, Ravi Kiran Sarvadevabhatla

Precise boundary annotations of image regions can be crucial for downstream applications which rely on region-class semantics. Some document collections contain densely laid out, highly irregular and overlapping multi-class region instances with large range in aspect ratio. Fully automatic boundary estimation approaches tend to be data intensive, cannot handle variable-sized images and produce sub-optimal results for aforementioned images. To address these issues, we propose BoundaryNet, a novel resizing-free approach for high-precision semi-automatic layout annotation. The variable-sized user selected region of interest is first processed by an attention-guided skip network. The network optimization is guided via Fast Marching distance maps to obtain a good quality initial boundary estimate and an associated feature representation. These outputs are processed by a Residual Graph Convolution Network optimized using Hausdorff loss to obtain the final region boundary. Results on a challenging image manuscript dataset demonstrate that BoundaryNet outperforms strong baselines and produces high-quality semantic region boundaries. Qualitatively, our approach generalizes across multiple document image datasets containing different script systems and layouts, all without additional fine-tuning. We integrate BoundaryNet into a document annotation system and show that it provides high annotation throughput compared to manual and fully automatic alternatives.

Sravya Vardhani Shivapuja, Mansi Pradeep Khamkar, Divij Bajaj et al.

Datasets for training crowd counting deep networks are typically heavy-tailed in count distribution and exhibit discontinuities across the count range. As a result, the de facto statistical measures (MSE, MAE) exhibit large variance and tend to be unreliable indicators of performance across the count range. To address these concerns in a holistic manner, we revise processes at various stages of the standard crowd counting pipeline. To enable principled and balanced minibatch sampling, we propose a novel smoothed Bayesian sample stratification approach. We propose a novel cost function which can be readily incorporated into existing crowd counting deep networks to encourage strata-aware optimization. We analyze the performance of representative crowd counting approaches across standard datasets at per strata level and in aggregate. We analyze the performance of crowd counting approaches across standard datasets and demonstrate that our proposed modifications noticeably reduce error standard deviation. Our contributions represent a nuanced, statistically balanced and fine-grained characterization of performance for crowd counting approaches. Code, pretrained models and interactive visualizations can be viewed at our project page https://deepcount.iiit.ac.in/

Meher Shashwat Nigam, Avinash Prabhu, Anurag Sahu et al.

Given a monocular colour image of a warehouse rack, we aim to predict the bird's-eye view layout for each shelf in the rack, which we term as multi-layer layout prediction. To this end, we present RackLay, a deep neural network for real-time shelf layout estimation from a single image. Unlike previous layout estimation methods, which provide a single layout for the dominant ground plane alone, RackLay estimates the top-view and front-view layout for each shelf in the considered rack populated with objects. RackLay's architecture and its variants are versatile and estimate accurate layouts for diverse scenes characterized by varying number of visible shelves in an image, large range in shelf occupancy factor and varied background clutter. Given the extreme paucity of datasets in this space and the difficulty involved in acquiring real data from warehouses, we additionally release a flexible synthetic dataset generation pipeline WareSynth which allows users to control the generation process and tailor the dataset according to contingent application. The ablations across architectural variants and comparison with strong prior baselines vindicate the efficacy of RackLay as an apt architecture for the novel problem of multi-layered layout estimation. We also show that fusing the top-view and front-view enables 3D reasoning applications such as metric free space estimation for the considered rack.

Satyajit Tourani, Dhagash Desai, Udit Singh Parihar et al.

Significant advances have been made recently in Visual Place Recognition (VPR), feature correspondence, and localization due to the proliferation of deep-learning-based methods. However, existing approaches tend to address, partially or fully, only one of two key challenges: viewpoint change and perceptual aliasing. In this paper, we present novel research that simultaneously addresses both challenges by combining deep-learned features with geometric transformations based on reasonable domain assumptions about navigation on a ground-plane, whilst also removing the requirement for specialized hardware setup (e.g. lighting, downwards facing cameras). In particular, our integration of VPR with SLAM by leveraging the robustness of deep-learned features and our homography-based extreme viewpoint invariance significantly boosts the performance of VPR, feature correspondence, and pose graph submodules of the SLAM pipeline. For the first time, we demonstrate a localization system capable of state-of-the-art performance despite perceptual aliasing and extreme 180-degree-rotated viewpoint change in a range of real-world and simulated experiments. Our system is able to achieve early loop closures that prevent significant drifts in SLAM trajectories. We also compare extensively several deep architectures for VPR and descriptor matching. We also show that superior place recognition and descriptor matching across opposite views results in a similar performance gain in back-end pose graph optimization.

Pranay Gupta, Anirudh Thatipelli, Aditya Aggarwal et al.

In this paper, we study current and upcoming frontiers across the landscape of skeleton-based human action recognition. To study skeleton-action recognition in the wild, we introduce Skeletics-152, a curated and 3-D pose-annotated subset of RGB videos sourced from Kinetics-700, a large-scale action dataset. We extend our study to include out-of-context actions by introducing Skeleton-Mimetics, a dataset derived from the recently introduced Mimetics dataset. We also introduce Metaphorics, a dataset with caption-style annotated YouTube videos of the popular social game Dumb Charades and interpretative dance performances. We benchmark state-of-the-art models on the NTU-120 dataset and provide multi-layered assessment of the results. The results from benchmarking the top performers of NTU-120 on the newly introduced datasets reveal the challenges and domain gap induced by actions in the wild. Overall, our work characterizes the strengths and limitations of existing approaches and datasets. Via the introduced datasets, our work enables new frontiers for human action recognition.

Rishabh Baghel, Ravi Kiran Sarvadevabhatla

We propose OPAL-Net, a novel hierarchical architecture for part-based layout generation of objects from multiple categories using a single unified model. We adopt a coarse-to-fine strategy involving semantically conditioned autoregressive generation of bounding box layouts and pixel-level part layouts for objects. We use Graph Convolutional Networks, Deep Recurrent Networks along with custom-designed Conditional Variational Autoencoders to enable flexible, diverse and category-aware generation of object layouts. We train OPAL-Net on PASCAL-Parts dataset. The generated samples and corresponding evaluation scores demonstrate the versatility of OPAL-Net compared to ablative variants and baselines.

Sai Shubodh Puligilla, Satyajit Tourani, Tushar Vaidya et al.

We showcase a topological mapping framework for a challenging indoor warehouse setting. At the most abstract level, the warehouse is represented as a Topological Graph where the nodes of the graph represent a particular warehouse topological construct (e.g. rackspace, corridor) and the edges denote the existence of a path between two neighbouring nodes or topologies. At the intermediate level, the map is represented as a Manhattan Graph where the nodes and edges are characterized by Manhattan properties and as a Pose Graph at the lower-most level of detail. The topological constructs are learned via a Deep Convolutional Network while the relational properties between topological instances are learnt via a Siamese-style Neural Network. In the paper, we show that maintaining abstractions such as Topological Graph and Manhattan Graph help in recovering an accurate Pose Graph starting from a highly erroneous and unoptimized Pose Graph. We show how this is achieved by embedding topological and Manhattan relations as well as Manhattan Graph aided loop closure relations as constraints in the backend Pose Graph optimization framework. The recovery of near ground-truth Pose Graph on real-world indoor warehouse scenes vindicate the efficacy of the proposed framework.

Abhishek Prusty, Sowmya Aitha, Abhishek Trivedi et al.

Historical palm-leaf manuscript and early paper documents from Indian subcontinent form an important part of the world's literary and cultural heritage. Despite their importance, large-scale annotated Indic manuscript image datasets do not exist. To address this deficiency, we introduce Indiscapes, the first ever dataset with multi-regional layout annotations for historical Indic manuscripts. To address the challenge of large diversity in scripts and presence of dense, irregular layout elements (e.g. text lines, pictures, multiple documents per image), we adapt a Fully Convolutional Deep Neural Network architecture for fully automatic, instance-level spatial layout parsing of manuscript images. We demonstrate the effectiveness of proposed architecture on images from the Indiscapes dataset. For annotation flexibility and keeping the non-technical nature of domain experts in mind, we also contribute a custom, web-based GUI annotation tool and a dashboard-style analytics portal. Overall, our contributions set the stage for enabling downstream applications such as OCR and word-spotting in historical Indic manuscripts at scale.

K L Navaneet, Ravi Kiran Sarvadevabhatla, Shashank Shekhar et al.

Given a target image as query, person re-identification systems retrieve a ranked list of candidate matches on a per-camera basis. In deployed systems, a human operator scans these lists and labels sighted targets by touch or mouse-based selection. However, classical re-id approaches generate per-camera lists independently. Therefore, target identifications by operator in a subset of cameras cannot be utilized to improve ranking of the target in remaining set of network cameras. To address this shortcoming, we propose a novel sequential multi-camera re-id approach. The proposed approach can accommodate human operator inputs and provides early gains via a monotonic improvement in target ranking. At the heart of our approach is a fusion function which operates on deep feature representations of query and candidate matches. We formulate an optimization procedure custom-designed to incrementally improve query representation. Since existing evaluation methods cannot be directly adopted to our setting, we also propose two novel evaluation protocols. The results on two large-scale re-id datasets (Market-1501, DukeMTMC-reID) demonstrate that our multi-camera method significantly outperforms baselines and other popular feature fusion schemes. Additionally, we conduct a comparative subject-based study of human operator performance. The superior operator performance enabled by our approach makes a compelling case for its integration into deployable video-surveillance systems.

Ravi Kiran Sarvadevabhatla, Shiv Surya, Trisha Mittal et al.

The ability of intelligent agents to play games in human-like fashion is popularly considered a benchmark of progress in Artificial Intelligence. Similarly, performance on multi-disciplinary tasks such as Visual Question Answering (VQA) is considered a marker for gauging progress in Computer Vision. In our work, we bring games and VQA together. Specifically, we introduce the first computational model aimed at Pictionary, the popular word-guessing social game. We first introduce Sketch-QA, an elementary version of Visual Question Answering task. Styled after Pictionary, Sketch-QA uses incrementally accumulated sketch stroke sequences as visual data. Notably, Sketch-QA involves asking a fixed question ("What object is being drawn?") and gathering open-ended guess-words from human guessers. We analyze the resulting dataset and present many interesting findings therein. To mimic Pictionary-style guessing, we subsequently propose a deep neural model which generates guess-words in response to temporally evolving human-drawn sketches. Our model even makes human-like mistakes while guessing, thus amplifying the human mimicry factor. We evaluate our model on the large-scale guess-word dataset generated via Sketch-QA task and compare with various baselines. We also conduct a Visual Turing Test to obtain human impressions of the guess-words generated by humans and our model. Experimental results demonstrate the promise of our approach for Pictionary and similarly themed games.

Ravi Kiran Sarvadevabhatla, Isht Dwivedi, Abhijat Biswas et al.

The ability to semantically interpret hand-drawn line sketches, although very challenging, can pave way for novel applications in multimedia. We propose SketchParse, the first deep-network architecture for fully automatic parsing of freehand object sketches. SketchParse is configured as a two-level fully convolutional network. The first level contains shared layers common to all object categories. The second level contains a number of expert sub-networks. Each expert specializes in parsing sketches from object categories which contain structurally similar parts. Effectively, the two-level configuration enables our architecture to scale up efficiently as additional categories are added. We introduce a router layer which (i) relays sketch features from shared layers to the correct expert (ii) eliminates the need to manually specify object category during inference. To bypass laborious part-level annotation, we sketchify photos from semantic object-part image datasets and use them for training. Our architecture also incorporates object pose prediction as a novel auxiliary task which boosts overall performance while providing supplementary information regarding the sketch. We demonstrate SketchParse's abilities (i) on two challenging large-scale sketch datasets (ii) in parsing unseen, semantically related object categories (iii) in improving fine-grained sketch-based image retrieval. As a novel application, we also outline how SketchParse's output can be used to generate caption-style descriptions for hand-drawn sketches.

Swaminathan Gurumurthy, Ravi Kiran Sarvadevabhatla, Venkatesh Babu Radhakrishnan

A class of recent approaches for generating images, called Generative Adversarial Networks (GAN), have been used to generate impressively realistic images of objects, bedrooms, handwritten digits and a variety of other image modalities. However, typical GAN-based approaches require large amounts of training data to capture the diversity across the image modality. In this paper, we propose DeLiGAN -- a novel GAN-based architecture for diverse and limited training data scenarios. In our approach, we reparameterize the latent generative space as a mixture model and learn the mixture model's parameters along with those of GAN. This seemingly simple modification to the GAN framework is surprisingly effective and results in models which enable diversity in generated samples although trained with limited data. In our work, we show that DeLiGAN can generate images of handwritten digits, objects and hand-drawn sketches, all using limited amounts of data. To quantitatively characterize intra-class diversity of generated samples, we also introduce a modified version of "inception-score", a measure which has been found to correlate well with human assessment of generated samples.

Ravi Kiran Sarvadevabhatla, Sudharshan Suresh, R. Venkatesh Babu

The study of eye gaze fixations on photographic images is an active research area. In contrast, the image subcategory of freehand sketches has not received as much attention for such studies. In this paper, we analyze the results of a free-viewing gaze fixation study conducted on 3904 freehand sketches distributed across 160 object categories. Our analysis shows that fixation sequences exhibit marked consistency within a sketch, across sketches of a category and even across suitably grouped sets of categories. This multi-level consistency is remarkable given the variability in depiction and extreme image content sparsity that characterizes hand-drawn object sketches. In our paper, we show that the multi-level consistency in the fixation data can be exploited to (a) predict a test sketch's category given only its fixation sequence and (b) build a computational model which predicts part-labels underlying fixations on objects. We hope that our findings motivate the community to deem sketch-like representations worthy of gaze-based studies vis-a-vis photographic images.

Ravi Kiran Sarvadevabhatla, Shanthakumar Venkatraman, R. Venkatesh Babu

An examination of object recognition challenge leaderboards (ILSVRC, PASCAL-VOC) reveals that the top-performing classifiers typically exhibit small differences amongst themselves in terms of error rate/mAP. To better differentiate the top performers, additional criteria are required. Moreover, the (test) images, on which the performance scores are based, predominantly contain fully visible objects. Therefore, `harder' test images, mimicking the challenging conditions (e.g. occlusion) in which humans routinely recognize objects, need to be utilized for benchmarking. To address the concerns mentioned above, we make two contributions. First, we systematically vary the level of local object-part content, global detail and spatial context in images from PASCAL VOC 2010 to create a new benchmarking dataset dubbed PPSS-12. Second, we propose an object-part based benchmarking procedure which quantifies classifiers' robustness to a range of visibility and contextual settings. The benchmarking procedure relies on a semantic similarity measure that naturally addresses potential semantic granularity differences between the category labels in training and test datasets, thus eliminating manual mapping. We use our procedure on the PPSS-12 dataset to benchmark top-performing classifiers trained on the ILSVRC-2012 dataset. Our results show that the proposed benchmarking procedure enables additional differentiation among state-of-the-art object classifiers in terms of their ability to handle missing content and insufficient object detail. Given this capability for additional differentiation, our approach can potentially supplement existing benchmarking procedures used in object recognition challenge leaderboards.

Ravi Kiran Sarvadevabhatla, Jogendra Kundu, Babu R. Venkatesh

Freehand sketching is an inherently sequential process. Yet, most approaches for hand-drawn sketch recognition either ignore this sequential aspect or exploit it in an ad-hoc manner. In our work, we propose a recurrent neural network architecture for sketch object recognition which exploits the long-term sequential and structural regularities in stroke data in a scalable manner. Specifically, we introduce a Gated Recurrent Unit based framework which leverages deep sketch features and weighted per-timestep loss to achieve state-of-the-art results on a large database of freehand object sketches across a large number of object categories. The inherently online nature of our framework is especially suited for on-the-fly recognition of objects as they are being drawn. Thus, our framework can enable interesting applications such as camera-equipped robots playing the popular party game Pictionary with human players and generating sparsified yet recognizable sketches of objects.

Ravi Kiran Sarvadevabhatla, Shiv Surya, Srinivas S S Kruthiventi et al.

Current state of the art object recognition architectures achieve impressive performance but are typically specialized for a single depictive style (e.g. photos only, sketches only). In this paper, we present SwiDeN : our Convolutional Neural Network (CNN) architecture which recognizes objects regardless of how they are visually depicted (line drawing, realistic shaded drawing, photograph etc.). In SwiDeN, we utilize a novel `deep' depictive style-based switching mechanism which appropriately addresses the depiction-specific and depiction-invariant aspects of the problem. We compare SwiDeN with alternative architectures and prior work on a 50-category Photo-Art dataset containing objects depicted in multiple styles. Experimental results show that SwiDeN outperforms other approaches for the depiction-invariant object recognition problem.

Suraj Srinivas, Ravi Kiran Sarvadevabhatla, Konda Reddy Mopuri et al.

Traditional architectures for solving computer vision problems and the degree of success they enjoyed have been heavily reliant on hand-crafted features. However, of late, deep learning techniques have offered a compelling alternative -- that of automatically learning problem-specific features. With this new paradigm, every problem in computer vision is now being re-examined from a deep learning perspective. Therefore, it has become important to understand what kind of deep networks are suitable for a given problem. Although general surveys of this fast-moving paradigm (i.e. deep-networks) exist, a survey specific to computer vision is missing. We specifically consider one form of deep networks widely used in computer vision - convolutional neural networks (CNNs). We start with "AlexNet" as our base CNN and then examine the broad variations proposed over time to suit different applications. We hope that our recipe-style survey will serve as a guide, particularly for novice practitioners intending to use deep-learning techniques for computer vision.

Ravi Kiran Sarvadevabhatla, Venkatesh Babu R

Studies from neuroscience show that part-mapping computations are employed by human visual system in the process of object recognition. In this work, we present an approach for analyzing semantic-part characteristics of object category representations. For our experiments, we use category-epitome, a recently proposed sketch-based spatial representation for objects. To enable part-importance analysis, we first obtain semantic-part annotations of hand-drawn sketches originally used to construct the corresponding epitomes. We then examine the extent to which the semantic-parts are present in the epitomes of a category and visualize the relative importance of parts as a word cloud. Finally, we show how such word cloud visualizations provide an intuitive understanding of category-level structural trends that exist in the category-epitome object representations.

Ravi Kiran Sarvadevabhatla, R. Venkatesh Babu

Freehand sketches often contain sparse visual detail. In spite of the sparsity, they are easily and consistently recognized by humans across cultures, languages and age groups. Therefore, analyzing such sparse sketches can aid our understanding of the neuro-cognitive processes involved in visual representation and recognition. In the recent past, Convolutional Neural Networks (CNNs) have emerged as a powerful framework for feature representation and recognition for a variety of image domains. However, the domain of sketch images has not been explored. This paper introduces a freehand sketch recognition framework based on "deep" features extracted from CNNs. We use two popular CNNs for our experiments -- Imagenet CNN and a modified version of LeNet CNN. We evaluate our recognition framework on a publicly available benchmark database containing thousands of freehand sketches depicting everyday objects. Our results are an improvement over the existing state-of-the-art accuracies by 3% - 11%. The effectiveness and relative compactness of our deep features also make them an ideal candidate for related problems such as sketch-based image retrieval. In addition, we provide a preliminary glimpse of how such features can help identify crucial attributes (e.g. object-parts) of the sketched objects.

Ravi Kiran Sarvadevabhatla, R. Venkatesh Babu

Freehand line sketches are an interesting and unique form of visual representation. Typically, such sketches are studied and utilized as an end product of the sketching process. However, we have found it instructive to study the sketches as sequentially accumulated composition of drawing strokes added over time. Studying sketches in this manner has enabled us to create novel sparse yet discriminative sketch-based representations for object categories which we term category-epitomes. Our procedure for obtaining these epitomes concurrently provides a natural measure for quantifying the sparseness underlying the original sketch, which we term epitome-score. We construct and analyze category-epitomes and epitome-scores for freehand sketches belonging to various object categories. Our analysis provides a novel viewpoint for studying the semantic nature of object categories.