Optical character recognition (OCR) for handwritten Indic manuscripts is essential for large-scale digitization and computational access to manuscript heritage. However, existing approaches are typically developed for one script at a time and require substantial script-specific customization. This limits scalability and practical deployment across diverse collections. We present UniLipi, a unified multi-script OCR model for handwritten Indic manuscripts trained jointly across 13 Indic scripts within a single framework. UniLipi directly handles realistic manuscript conditions, including extreme variation in line geometry, large variation in line length, and partial interruptions caused by non-textual manuscript entities such as holes, stains, or pictorial illustrations. To operate effectively under ultra low-resource conditions, the model leverages script-aware synthetic manuscript data generation, substantially reducing reliance on large volumes of real annotated data. Beyond historical manuscripts, we show that UniLipi serves as an effective foundational pretrained model. Specifically, its learned representations enable good OCR performance for contemporary Indic handwriting and extend to several non-Indic scripts, including Tibetan, Italian, Latin, and Chinese scripts. In addition to transcription, UniLipi predicts script identity and per-line native character counts, supporting practical manuscript cataloging workflows.

We present CURIO, an OCR system for low-resource historical manuscripts. In many challenging cases, manuscripts feature curved text lines, unsegmented lines with lack of spacing between words, and highly variable line lengths — conditions under which existing OCR methods fail. To tackle this challenge, we first extract lines and corresponding curvature profiles from manuscripts, then straighten them using a rectification procedure to reduce redundant background within each line. Because data is scarce, we compliment real data with synthetic data. To bridge the synthetic–real gap, we generate line images by warping rendered straight text along the rectified profiles, ensuring both real and synthetic lines align in their curvature characteristics. Our recognizer is a lightweight CNN–Transformer with padding-aware null activations, sparse attention and optimized with CTC loss for efficient training. We evaluate our method on challenging manuscript collections written in Sharada, a rare and endangered Indic script. CURIO outperforms strong CNN+RNN and Transformer baselines, with the largest gains on high-curvature lines and long lines. CURIO further transfers zero-shot to printed Sharada text, indicating robustness beyond manuscript domain.

We introduce Sketchtopia, a large-scale dataset and AI framework designed to explore goal-driven, multimodal communication through asynchronous interactions in a Pictionary-inspired setup. Sketchtopia captures natural human interactions, including freehand sketches, open-ended guesses, and iconic feedback gestures, showcasing the complex dynamics of cooperative communication under constraints. It features over 20K gameplay sessions from 916 players, capturing 263K sketches, 10K erases, 56K guesses and 19.4K iconic feedbacks. We introduce multimodal foundational agents with capabilities for generative sketching, guess generation and asynchronous communication. Our dataset also includes 800 human-agent sessions for benchmarking the agents. We introduce novel metrics to char-acterize collaborative success, responsiveness to feedback and inter-agent asynchronous communication. Sketchtopia pushes the boundaries of multimodal AI, establishing a new benchmark for studying asynchronous, goal-oriented interactions between humans and AI agents. The dataset can be found at https://sketchtopia25.github.io/

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.

In this work, we present IDD-CRS, a large-scale dataset focused on critical road scenarios, captured using Advanced Driver Assistance Systems (ADAS) and dash cameras. Unlike existing datasets that predominantly emphasize pedestrian safety and vehicle safety separately, IDD-CRS incorporates both vehicle and pedestrian behaviors, offering a more comprehensive view of road safety. The dataset includes diverse scenarios, such as high-speed lane changes, unsafe vehicle approaches to pedestrians and cyclists, and complex interactions between ego vehicles and other road agents. Leveraging ADAS technology allows us to accurately define the temporal boundaries of actions, resulting in precise annotations and more reliable safety analysis. With 90 hours of video footage, consisting of 5400 one-minute-long videos and 135,000 frames, IDD-CRS introduces new vehicle-related classes and hard negative classes, establishing baselines for action recognition and long-tail action recognition tasks. Our benchmarks reveal the limitations of current models, pointing toward future advancements needed for improving road safety technology.

Modern generative models often struggle to synthesize structured objects from detailed part specifications. They frequently produce anatomically implausible outputs or hallucinated components. We introduce PLATO, a novel two-stage framework that bridges this gap by enabling precise, part-controlled object generation. The first stage is PLayGen, our novel part layout generator which takes a list of parts and object category as input and synthesizes high-fidelity layouts of part bounding boxes. To enhance PLayGen's ability to learn inter-part relationships, we introduce novel structure-based loss functions. In the second stage, PLayGen's synthesized layout is used to condition a custom-tuned ControlNet-style adapter, enforcing spatial and connectivity constraints. This results in anatomically consistent, high-fidelity object generations containing precisely the user-specified parts. We further propose new part-level evaluation metrics to rigorously quantify adherence to part specifications. Extensive experiments show that PLATO significantly outperforms state-of-the-art generative models and produces structurally coherent objects in a controllable manner - marking a step forward in modular, part-driven asset generation.

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, pre-trained models, and sample videos are available at motion-rag. github.io.

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. Project page: https://dash-cop.github.io/

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.

This work presents a novel approach to identifying possible early accident-prone zones in a large city-scale road network using geo-tagged collision alert data from a vehicle fleet. The alert data has been collected for a year from 200 city buses installed with the Advanced Driver Assistance System (ADAS). To the best of our knowledge, no research paper has used ADAS alerts to identify the early accident-prone zones. A nonparametric technique called Kernel Density Estimation (KDE) is employed to model the distribution of alert data across stratified time intervals. A novel recall-based measure is introduced to assess the degree of support provided by our density-based approach for existing, manually determined accident-prone zones (‘blackspots’) provided by civic authorities. This shows that our KDE approach significantly outperforms existing approaches in terms of the recall-based measure. Introducing a novel linear assignment Earth Mover Distance based measure to predict previously unidentified accident-prone zones. The results and findings support the feasibility of utilizing alert data from vehicle fleets to aid civic planners in assessing accident-zone trends and deploying traffic calming measures, thereby improving overall road safety and saving lives.

The convergence of computer vision and advertising has sparked substantial interest lately. Existing advertisement datasets are either subsets of existing datasets with specialized annotations or feature diverse annotations without a cohesive taxonomy among ad images. Notably, no datasets encompass diverse advertisement styles or semantic grouping at various levels of granularity. Our work addresses this gap by introducing MAdVerse, an extensive, multilingual compilation of more than 50,000 ads from the web, social media websites, and e-newspapers. Advertisements are hierarchically grouped with uniform granularity into 11 categories, divided into 51 sub-categories, and 524 fine-grained brands at leaf level, each featuring ads in various languages. We provide comprehensive baseline classification results for prediction tasks within the realm of advertising analysis. These tasks include hierarchical ad classification, source classification, multilingual classification, and inducing hierarchy in existing ad datasets.The dataset, code and models are available on the project page https://madverse24.github.io/

This paper proposes a scalable distributed video analytics framework that can process thousands of video streams from sources such as CCTV cameras using semantic scene analysis. The main idea is to deploy deep learning pipelines on the fog nodes and generate semantic scene description records (SDRs) of video feeds from the associated CCTV cameras. These SDRs are transmitted to the cloud instead of video frames saving on network bandwidth. Using these SDRs stored on the cloud database, we can answer many complex queries and perform rich video analytics, within extremely low latencies. There is no need to scan and process the video streams again on a per query basis. The software architecture on the fog nodes allows for integrating new deep learning pipelines dynamically into the existing system, thereby supporting novel analytics and queries. We demonstrate the effectiveness of the system by proposing a novel distributed algorithm for real-time vehicle pursuit. The proposed algorithm involves asking multiple spatio-temporal queries in an adaptive fashion to reduce the query processing time and is robust to inaccuracies in the deployed deep learning pipelines and camera failures.

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. Code and pretrained models are available at https://actiongpt.github.io.

We introduce DSAG, a controllable deep neural framework for action-conditioned generation of full body multiactor variable duration actions. To compensate for incompletely detailed finger joints in existing large-scale datasets, we introduce full body dataset variants with detailed finger joints. To overcome shortcomings in existing generative approaches, we introduce dedicated representations for encoding finger joints. We also introduce novel spatiotemporal transformation blocks with multi-head self attention and specialized temporal processing. The design choices enable generations for a large range in body joint counts (24 - 52), frame rates (13 - 50), global body movement (inplace, locomotion) and action categories (12 - 120), across multiple datasets (NTU-120, HumanAct12, UESTC, Human3.6M). Our experimental results demonstrate DSAG’s significant improvements over state-of-the-art, its suitability for action-conditioned generation at scale.

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.

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.

We introduce SynSE (Syntactically guided Skeleton Embeddings), 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.

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.

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.

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.

The ability of intelligent agents to play games in human-like fashion is popularly considered a benchmark of progress in Artificial Intelligence. In our work, we introduce the first computational model aimed at Pictionary, the popular word-guessing social game. We first introduce Sketch-QA, a guessing task. Styled after Pictionary, Sketch-QA uses incrementally accumulated sketch stroke sequences as visual data. 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 propose a deep neural model which generates guess-words in response to temporally evolving human-drawn object 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.

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.

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.

The ability of machine-based agents to play games in human-like fashion is considered a benchmark of progress in AI. In this paper, 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. To mimic Pictionary-style guessing, we 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.

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 models 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.

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.

The study of eye gaze fixations on photographic images is an active research area. In contrast, the image sub-category 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 this paper, we show that the multi-level consistency in the fixation data can be exploited to 1) predict a test sketch's category given only its fixation sequence and 2) 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.

Studies from neuroscience show that part-mapping computations are employed by human visual system in the process of object recognition. In this paper, 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 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. Our method is general in applicability and can also be used to analyze part-based visual object representations for other depiction methods such as photographic images.

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.

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.

As a form of visual representation, freehand line sketches are typically studied as an end product of the sketching process. However, from a recognition point of view, one can also study various orderings and properties of the primitive strokes that compose the sketch. 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. Concurrently, the epitome construction provides a natural measure for quantifying the sparseness underlying the original sketch, which we term epitome-score. We analyze category-epitomes and epitome-scores for hand-drawn sketches from a sketch dataset of 160 object categories commonly encountered in daily life. Our analysis provides a novel viewpoint for examining the complexity of representation for visual object categories.

This proxemics study examines whether the physical distance between robots and humans differ based on the following factors: 1) age: children vs. adults, 2) who initiates the approach: humans approaching the robot vs. robot approaching humans, 3) prompting: verbal invitation vs. non-verbal gesture (e.g., beckoning), and 4) informing: announcement vs. permission vs. nothing. Results showed that both verbal and non-verbal prompting had significant influence on physical distance. Physiological data is also used to detect the appropriate timing of approach for a more natural and comfortable interaction.

The role of context in recognizing a person's affect is being increasingly studied. In particular, context arising from the presence of multi-modal information such as faces, speech and head pose has been used in recent studies to recognize facial expressions. In most approaches, the modalities are independently considered and the effect of one modality on the other, which we call inter-modal influence (e.g. speech or head pose modifying the facial appearance) is not modeled. In this paper, we describe a system that utilizes context from the presence of such inter-modal influences to recognize facial expressions. To do so, we use 2-D contextual masks which are activated within the facial expression recognition pipeline depending on the prevailing context. We also describe a framework called the Context Engine. The Context Engine offers a scalable mechanism for extending the current system to address additional modes of context that may arise during human-machine interactions. Results on standard data sets demonstrate the utility of modeling inter-modal contextual effects in recognizing facial expressions.

Two studies examined the different features of humanoid robots and the influence on children's affective behavior. The first study looked at interaction styles and general features of robots. The second study looked at how the robot's attention influences children's behavior and engagement. Through activities familiar to young children (e.g., table setting, story telling), the first study found that cooperative interaction style elicited more oculesic behavior and social engagement. The second study found that quality of attention, type of attention, and length of interaction influences affective behavior and engagement. In the quality of attention, Wizard-of-Oz (woz) elicited the most affective behavior, but automatic attention worked as well as woz when the interaction was short. The type of attention going from nonverbal to verbal attention increased children's oculesic behavior, utterance, and physiological response. Affective interactions did not seem to depend on a single mechanism, but a well-chosen confluence of technical features.

Extended human-robot interactions possess unique aspects which are not exhibited in short-term interactions spanning a few minutes or extremely long-term spanning days. In order to comprehensively monitor such interactions, we need special recording mechanisms which ensure the interaction is captured at multiple spatio-temporal scales, viewpoints and modalities(audio, video, physio). To minimize cognitive burden, we need tools which can automate the process of annotating and analyzing the resulting data. In addition, we also require these tools to be able to provide a unified, multi-scale view of the data and help discover patterns in the interaction process. In this paper, we describe recording and analysis tools which are helping us analyze extended human-robot interactions with children as subjects. We also provide some experimental results which highlight the utility of such tools.

Humanoid robots consist of biologically inspired features, human-like appearance, and intelligent behavior that naturally elicit social responses. Complex interactions are now possible, where children interact and learn from robots. A pilot study attempted to determine which features in robots led to changes in learning and behavior. Three common learning styles, lecture, cooperative, and self-directed, were implemented into ASIMO to see if children can learn from robots. General features such as monotone robot-like voice and human-like voice were compared. Thirty-seven children between the ages 4-to 10- years participated in the study. Each child engaged in a table-setting task with ASIMO that exhibited different learning styles and general features. Children answered questions in relation to a table-setting task with a learning measure. Promissory evidence shows that learning styles and general features matter especially for younger children.

We present a human-robot interactive scenario consisting of a memory card game between Hondapsilas humanoid robot ASIMO and a human player. The game features perception exclusively through ASIMOpsilas on-board cameras and both reactive and proactive behaviors specific to different situational contexts in the memory game. ASIMO is able to build a dynamic environmental map of relevant objects in the game such as the table and card layout as well as understand activities from the player such as pointing at cards, flipping cards and removing them from the table. Our system architecture, called the Cognitive Map, treats the memory game as a multi-agent system, with modules acting independently and communicating with each other via messages through a shared blackboard system. The game behavior module can model game state and contextual information to make decisions based on different pattern recognition modules. Behavior is then sent through high-level command interfaces to be resolved into actual physical actions by the robot via a multi-modal communication module. The experience gained in modeling this interactive scenario will allow us to reuse the architecture to create new scenarios and explore new research directions in learning how to respond to new interactive situations.